From c71c6fe5457cd70e3ac8657b768607c5a5e33c19 Mon Sep 17 00:00:00 2001 From: Quarto GHA Workflow Runner Date: Wed, 21 May 2025 15:22:54 +0000 Subject: [PATCH] Built site for gh-pages --- .nojekyll | 2 +- docs/api/core.trainers.dpo.trainer.html | 30 +- ...ore.trainers.mixins.sequence_parallel.html | 902 ------- docs/api/core.training_args.html | 86 +- docs/api/index.html | 4 - docs/multi-gpu.html | 277 +- docs/sequence_parallelism.html | 14 +- search.json | 2384 ++++++++--------- sitemap.xml | 1166 ++++---- 9 files changed, 1946 insertions(+), 2919 deletions(-) delete mode 100644 docs/api/core.trainers.mixins.sequence_parallel.html diff --git a/.nojekyll b/.nojekyll index f14f775c8..c91edf24c 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -3750d6c6 \ No newline at end of file +45aa1b5b \ No newline at end of file diff --git a/docs/api/core.trainers.dpo.trainer.html b/docs/api/core.trainers.dpo.trainer.html index b7ec1eef1..fddb23c31 100644 --- a/docs/api/core.trainers.dpo.trainer.html +++ b/docs/api/core.trainers.dpo.trainer.html @@ -478,7 +478,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin AxolotlDPOTrainer -Extend the base DPOTrainer for axolotl helpers +Extend the base DPOTrainer for axolotl helpers. @@ -490,7 +490,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin dataset_tags=None, **kwargs, ) -

Extend the base DPOTrainer for axolotl helpers

+

Extend the base DPOTrainer for axolotl helpers.

Methods

@@ -502,33 +502,17 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin - - - - - +
evaluation_loopOverriding built-in evaluation loop to store metrics for each batch.
push_to_hubOverwrite the push_to_hub method in order to force-add the tags when pushing theOverwrite the push_to_hub method in order to force-add the tags when pushing
-
-
evaluation_loop
-
core.trainers.dpo.trainer.AxolotlDPOTrainer.evaluation_loop(
-    dataloader,
-    description,
-    prediction_loss_only=None,
-    ignore_keys=None,
-    metric_key_prefix='eval',
-)
-

Overriding built-in evaluation loop to store metrics for each batch. -Prediction/evaluation loop, shared by Trainer.evaluate() and Trainer.predict().

-

Works both with or without labels.

-
push_to_hub
-
core.trainers.dpo.trainer.AxolotlDPOTrainer.push_to_hub(*args, **kwargs)
-

Overwrite the push_to_hub method in order to force-add the tags when pushing the -model on the Hub. Please refer to ~transformers.Trainer.push_to_hub for more details.

+
core.trainers.dpo.trainer.AxolotlDPOTrainer.push_to_hub(*args, **kwargs)
+

Overwrite the push_to_hub method in order to force-add the tags when pushing +the model on the Hub. Please refer to ~transformers.Trainer.push_to_hub +for more details.

diff --git a/docs/api/core.trainers.mixins.sequence_parallel.html b/docs/api/core.trainers.mixins.sequence_parallel.html deleted file mode 100644 index ff56c0c04..000000000 --- a/docs/api/core.trainers.mixins.sequence_parallel.html +++ /dev/null @@ -1,902 +0,0 @@ - - - - - - - - - -core.trainers.mixins.sequence_parallel – Axolotl - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
-
- - -
- -
- - -
- - - -
- - - - -
-

core.trainers.mixins.sequence_parallel

-

core.trainers.mixins.sequence_parallel

-

Module for Axolotl trainer sequence parallelism mixin

-
-

Classes

- - - - - - - - - - - - - -
NameDescription
SequenceParallelMixinMixin class for sequence parallelism support in trainers.
-
-

SequenceParallelMixin

-
core.trainers.mixins.sequence_parallel.SequenceParallelMixin()
-

Mixin class for sequence parallelism support in trainers.

-

This mixin provides functionality for handling sequence parallelism, -specifically for creating appropriate data samplers.

- - -
-
-
- -
- -
- - - - - \ No newline at end of file diff --git a/docs/api/core.training_args.html b/docs/api/core.training_args.html index 14b237512..ffb25b909 100644 --- a/docs/api/core.training_args.html +++ b/docs/api/core.training_args.html @@ -559,14 +559,12 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin kd_temperature=1.0, kd_zscore_base_temp=None, kd_top_k_before_softmax=None, - sequence_parallel_degree=1, - ring_attn_func=None, - adam_beta3=None, - adam_epsilon2=None, - image_size=None, - image_resize_algorithm=None, - simpo_gamma=None, -) + adam_beta3=None, + adam_epsilon2=None, + image_size=None, + image_resize_algorithm=None, + simpo_gamma=None, +)

CPO config for CPO training

@@ -616,13 +614,11 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin kd_temperature=1.0, kd_zscore_base_temp=None, kd_top_k_before_softmax=None, - sequence_parallel_degree=1, - ring_attn_func=None, - adam_beta3=None, - adam_epsilon2=None, - image_size=None, - image_resize_algorithm=None, -) + adam_beta3=None, + adam_epsilon2=None, + image_size=None, + image_resize_algorithm=None, +)

KTO config for KTO training

@@ -672,13 +668,11 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin kd_temperature=1.0, kd_zscore_base_temp=None, kd_top_k_before_softmax=None, - sequence_parallel_degree=1, - ring_attn_func=None, - adam_beta3=None, - adam_epsilon2=None, - image_size=None, - image_resize_algorithm=None, -) + adam_beta3=None, + adam_epsilon2=None, + image_size=None, + image_resize_algorithm=None, +)

ORPO config for ORPO training

@@ -728,13 +722,11 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin kd_temperature=1.0, kd_zscore_base_temp=None, kd_top_k_before_softmax=None, - sequence_parallel_degree=1, - ring_attn_func=None, - adam_beta3=None, - adam_epsilon2=None, - image_size=None, - image_resize_algorithm=None, -) + adam_beta3=None, + adam_epsilon2=None, + image_size=None, + image_resize_algorithm=None, +)

PRM config for PRM training

@@ -784,13 +776,11 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin kd_temperature=1.0, kd_zscore_base_temp=None, kd_top_k_before_softmax=None, - sequence_parallel_degree=1, - ring_attn_func=None, - adam_beta3=None, - adam_epsilon2=None, - image_size=None, - image_resize_algorithm=None, -) + adam_beta3=None, + adam_epsilon2=None, + image_size=None, + image_resize_algorithm=None, +)

Reward config for Reward training

@@ -840,13 +830,11 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin kd_temperature=1.0, kd_zscore_base_temp=None, kd_top_k_before_softmax=None, - sequence_parallel_degree=1, - ring_attn_func=None, - adam_beta3=None, - adam_epsilon2=None, - image_size=None, - image_resize_algorithm=None, -) + adam_beta3=None, + adam_epsilon2=None, + image_size=None, + image_resize_algorithm=None, +)

Training arguments for Causal trainer

This code is duplicated due to HF TrainingArguments not setting output_dir with a default value so it can’t be used as a mixin.

@@ -898,13 +886,11 @@ default value so it can’t be used as a mixin.

kd_temperature=1.0, kd_zscore_base_temp=None, kd_top_k_before_softmax=None, - sequence_parallel_degree=1, - ring_attn_func=None, - adam_beta3=None, - adam_epsilon2=None, - image_size=None, - image_resize_algorithm=None, -) + adam_beta3=None, + adam_epsilon2=None, + image_size=None, + image_resize_algorithm=None, +)

Mixin class for the Axolotl training args.

diff --git a/docs/api/index.html b/docs/api/index.html index 13f564565..13d3a976a 100644 --- a/docs/api/index.html +++ b/docs/api/index.html @@ -629,10 +629,6 @@ ul.task-list li input[type="checkbox"] { core.trainers.mixins.scheduler Module for Axolotl trainer scheduler mixin - -core.trainers.mixins.sequence_parallel -Module for Axolotl trainer sequence parallelism mixin -
diff --git a/docs/multi-gpu.html b/docs/multi-gpu.html index 286bbfb0e..277313b69 100644 --- a/docs/multi-gpu.html +++ b/docs/multi-gpu.html @@ -572,15 +572,7 @@ Tip ring-flash-attention project. This allows one to split up sequences across GPUs, which is useful in the event that a single sequence causes OOM errors during model training.

-

First, install ring-flash-attn, recommended via pip install axolotl[ring-flash-attn], -or from source with pip install .[ring-flash-attn].

-

Your Axolotl YAML config should contain the following lines:

-
sequence_parallel_degree: 4  # Split each sequence into 4 parts, one per GPU
-flash_attention: true  # Required with sequence parallelism
-
-# Optional; strides across the key dimension. Larger values use more memory but will make training faster.
-heads_k_stride: 1
-

See our dedicated guide for more details.

+

See our dedicated guide for more information.

4.1 FSDP + QLoRA

For combining FSDP with QLoRA, see our dedicated guide.

@@ -1080,146 +1072,133 @@ or from source with pip install .[ring-flash-attn].

} }); diff --git a/docs/sequence_parallelism.html b/docs/sequence_parallelism.html index a7bdf2bc3..d7d35eb71 100644 --- a/docs/sequence_parallelism.html +++ b/docs/sequence_parallelism.html @@ -520,7 +520,7 @@ through a ring communication pattern.

  1. Each sequence is divided into equal chunks across the GPUs in a sequence parallel group
  2. The data collator handles the chunking of input_ids, attention_mask, labels, and position_ids
    3. -
  3. Position IDs are adjusted to maintain proper relative positions, especially for packed sequences
    4. +
  4. Position IDs are adjusted to maintain proper relative positions
  5. The trainer uses special ring communication patterns for attention operations
@@ -551,11 +551,13 @@ through a ring communication pattern.

... sequence_parallel_degree: 4 # Split each sequence into 4 parts, one per GPU -flash_attention: true # Required with sequence parallelism -# Optional; strides across the key dimension. Larger values use more memory but should make training faster. -heads_k_stride: 1 - -... +# Optional; strides across the key dimension. Larger values use more memory but should make training faster. +heads_k_stride: 1 +# Optional; one of "varlen_llama3" or "batch_ring". Defaults to +# "varlen_llama3" when `sample_packing: true`, and "batch_ring" otherwise. +ring_attn_func: + +...

This will train the Llama 3 8B model with 8K context length, with each sequence split into 2 subsequences of length 4096 across 2 GPUs.

diff --git a/search.json b/search.json index 07c7917fe..1a98cec72 100644 --- a/search.json +++ b/search.json @@ -795,7 +795,7 @@ "href": "docs/sequence_parallelism.html#implementation-details", "title": "Sequence Parallelism", "section": "Implementation Details", - "text": "Implementation Details\nWhen sequence parallelism is enabled:\n\nEach sequence is divided into equal chunks across the GPUs in a sequence parallel group\nThe data collator handles the chunking of input_ids, attention_mask, labels, and position_ids\nPosition IDs are adjusted to maintain proper relative positions, especially for packed sequences\nThe trainer uses special ring communication patterns for attention operations", + "text": "Implementation Details\nWhen sequence parallelism is enabled:\n\nEach sequence is divided into equal chunks across the GPUs in a sequence parallel group\nThe data collator handles the chunking of input_ids, attention_mask, labels, and position_ids\nPosition IDs are adjusted to maintain proper relative positions\nThe trainer uses special ring communication patterns for attention operations", "crumbs": [ "Advanced Features", "Sequence Parallelism" @@ -828,7 +828,7 @@ "href": "docs/sequence_parallelism.html#example", "title": "Sequence Parallelism", "section": "Example", - "text": "Example\nbase_model: meta-llama/Llama-3-8B-Instruct\nsequence_len: 8192\n\n...\n\nsequence_parallel_degree: 4 # Split each sequence into 4 parts, one per GPU\nflash_attention: true # Required with sequence parallelism\n# Optional; strides across the key dimension. Larger values use more memory but should make training faster.\nheads_k_stride: 1\n\n...\nThis will train the Llama 3 8B model with 8K context length, with each sequence split\ninto 2 subsequences of length 4096 across 2 GPUs.", + "text": "Example\nbase_model: meta-llama/Llama-3-8B-Instruct\nsequence_len: 8192\n\n...\n\nsequence_parallel_degree: 4 # Split each sequence into 4 parts, one per GPU\n# Optional; strides across the key dimension. Larger values use more memory but should make training faster.\nheads_k_stride: 1\n# Optional; one of \"varlen_llama3\" or \"batch_ring\". Defaults to\n# \"varlen_llama3\" when `sample_packing: true`, and \"batch_ring\" otherwise.\nring_attn_func:\n\n...\nThis will train the Llama 3 8B model with 8K context length, with each sequence split\ninto 2 subsequences of length 4096 across 2 GPUs.", "crumbs": [ "Advanced Features", "Sequence Parallelism" @@ -905,7 +905,7 @@ "href": "docs/multi-gpu.html#sec-sequence-parallelism", "title": "Multi-GPU", "section": "4 Sequence parallelism", - "text": "4 Sequence parallelism\nWe support sequence parallelism (SP) via the\nring-flash-attention project. This\nallows one to split up sequences across GPUs, which is useful in the event that a\nsingle sequence causes OOM errors during model training.\nFirst, install ring-flash-attn, recommended via pip install axolotl[ring-flash-attn],\nor from source with pip install .[ring-flash-attn].\nYour Axolotl YAML config should contain the following lines:\nsequence_parallel_degree: 4 # Split each sequence into 4 parts, one per GPU\nflash_attention: true # Required with sequence parallelism\n\n# Optional; strides across the key dimension. Larger values use more memory but will make training faster.\nheads_k_stride: 1\nSee our dedicated guide for more details.\n\n4.1 FSDP + QLoRA\nFor combining FSDP with QLoRA, see our dedicated guide.", + "text": "4 Sequence parallelism\nWe support sequence parallelism (SP) via the\nring-flash-attention project. This\nallows one to split up sequences across GPUs, which is useful in the event that a\nsingle sequence causes OOM errors during model training.\nSee our dedicated guide for more information.\n\n4.1 FSDP + QLoRA\nFor combining FSDP with QLoRA, see our dedicated guide.", "crumbs": [ "Deployments", "Multi-GPU" @@ -969,907 +969,1019 @@ "text": "Name\nDescription\n\n\n\n\nAxolotlKDTrainer\nCustom trainer subclass for Knowledge Distillation (KD)\n\n\n\n\n\nintegrations.kd.trainer.AxolotlKDTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nCustom trainer subclass for Knowledge Distillation (KD)\n\n\n\n\n\nName\nDescription\n\n\n\n\ncompute_loss\nHow the loss is computed by Trainer. By default, all models return the loss in the first element.\n\n\n\n\n\nintegrations.kd.trainer.AxolotlKDTrainer.compute_loss(\n model,\n inputs,\n return_outputs=False,\n num_items_in_batch=None,\n)\nHow the loss is computed by Trainer. By default, all models return the loss in the first element.\nSubclass and override for custom behavior." }, { - "objectID": "docs/api/core.trainers.mixins.sequence_parallel.html", - "href": "docs/api/core.trainers.mixins.sequence_parallel.html", - "title": "core.trainers.mixins.sequence_parallel", + "objectID": "docs/api/prompt_strategies.kto.llama3.html", + "href": "docs/api/prompt_strategies.kto.llama3.html", + "title": "prompt_strategies.kto.llama3", "section": "", - "text": "core.trainers.mixins.sequence_parallel\nModule for Axolotl trainer sequence parallelism mixin\n\n\n\n\n\nName\nDescription\n\n\n\n\nSequenceParallelMixin\nMixin class for sequence parallelism support in trainers.\n\n\n\n\n\ncore.trainers.mixins.sequence_parallel.SequenceParallelMixin()\nMixin class for sequence parallelism support in trainers.\nThis mixin provides functionality for handling sequence parallelism,\nspecifically for creating appropriate data samplers." + "text": "prompt_strategies.kto.llama3\nKTO strategies for llama-3 chat template\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.llama3.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" }, { - "objectID": "docs/api/core.trainers.mixins.sequence_parallel.html#classes", - "href": "docs/api/core.trainers.mixins.sequence_parallel.html#classes", - "title": "core.trainers.mixins.sequence_parallel", + "objectID": "docs/api/prompt_strategies.kto.llama3.html#functions", + "href": "docs/api/prompt_strategies.kto.llama3.html#functions", + "title": "prompt_strategies.kto.llama3", "section": "", - "text": "Name\nDescription\n\n\n\n\nSequenceParallelMixin\nMixin class for sequence parallelism support in trainers.\n\n\n\n\n\ncore.trainers.mixins.sequence_parallel.SequenceParallelMixin()\nMixin class for sequence parallelism support in trainers.\nThis mixin provides functionality for handling sequence parallelism,\nspecifically for creating appropriate data samplers." + "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.llama3.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" }, { - "objectID": "docs/api/common.architectures.html", - "href": "docs/api/common.architectures.html", - "title": "common.architectures", + "objectID": "docs/api/prompt_strategies.alpaca_chat.html", + "href": "docs/api/prompt_strategies.alpaca_chat.html", + "title": "prompt_strategies.alpaca_chat", "section": "", - "text": "common.architectures\ncommon.architectures\nCommon architecture specific constants" + "text": "prompt_strategies.alpaca_chat\nModule for Alpaca prompt strategy classes\n\n\n\n\n\nName\nDescription\n\n\n\n\nAlpacaChatPrompter\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\nAlpacaConcisePrompter\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\nAlpacaQAPromptTokenizingStrategy\nTokenizing strategy for AlpacaQA\n\n\nCamelAIPromptTokenizingStrategy\nTokenizing strategy for CamelAI datasets\n\n\nNoSystemPrompter\nNull Prompter with no system prompts\n\n\n\n\n\nprompt_strategies.alpaca_chat.AlpacaChatPrompter(self)\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaConcisePrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaQAPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for AlpacaQA\n\n\n\nprompt_strategies.alpaca_chat.CamelAIPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for CamelAI datasets\n\n\n\nprompt_strategies.alpaca_chat.NoSystemPrompter(self)\nNull Prompter with no system prompts" }, { - "objectID": "docs/api/utils.optimizers.adopt.html", - "href": "docs/api/utils.optimizers.adopt.html", - "title": "utils.optimizers.adopt", + "objectID": "docs/api/prompt_strategies.alpaca_chat.html#classes", + "href": "docs/api/prompt_strategies.alpaca_chat.html#classes", + "title": "prompt_strategies.alpaca_chat", "section": "", - "text": "utils.optimizers.adopt\nCopied from https://github.com/iShohei220/adopt\nADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate (2024)\nTaniguchi, Shohei and Harada, Keno and Minegishi, Gouki and Oshima, Yuta and Jeong, Seong Cheol and Nagahara, Go and Iiyama, Tomoshi and Suzuki, Masahiro and Iwasawa, Yusuke and Matsuo, Yutaka\n\n\n\n\n\nName\nDescription\n\n\n\n\nadopt\nFunctional API that performs ADOPT algorithm computation.\n\n\n\n\n\nutils.optimizers.adopt.adopt(\n params,\n grads,\n exp_avgs,\n exp_avg_sqs,\n state_steps,\n foreach=None,\n capturable=False,\n differentiable=False,\n fused=None,\n grad_scale=None,\n found_inf=None,\n has_complex=False,\n *,\n beta1,\n beta2,\n lr,\n clip_lambda,\n weight_decay,\n decouple,\n eps,\n maximize,\n)\nFunctional API that performs ADOPT algorithm computation." + "text": "Name\nDescription\n\n\n\n\nAlpacaChatPrompter\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\nAlpacaConcisePrompter\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\nAlpacaQAPromptTokenizingStrategy\nTokenizing strategy for AlpacaQA\n\n\nCamelAIPromptTokenizingStrategy\nTokenizing strategy for CamelAI datasets\n\n\nNoSystemPrompter\nNull Prompter with no system prompts\n\n\n\n\n\nprompt_strategies.alpaca_chat.AlpacaChatPrompter(self)\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaConcisePrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaQAPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for AlpacaQA\n\n\n\nprompt_strategies.alpaca_chat.CamelAIPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for CamelAI datasets\n\n\n\nprompt_strategies.alpaca_chat.NoSystemPrompter(self)\nNull Prompter with no system prompts" }, { - "objectID": "docs/api/utils.optimizers.adopt.html#functions", - "href": "docs/api/utils.optimizers.adopt.html#functions", - "title": "utils.optimizers.adopt", + "objectID": "docs/api/logging_config.html", + "href": "docs/api/logging_config.html", + "title": "logging_config", "section": "", - "text": "Name\nDescription\n\n\n\n\nadopt\nFunctional API that performs ADOPT algorithm computation.\n\n\n\n\n\nutils.optimizers.adopt.adopt(\n params,\n grads,\n exp_avgs,\n exp_avg_sqs,\n state_steps,\n foreach=None,\n capturable=False,\n differentiable=False,\n fused=None,\n grad_scale=None,\n found_inf=None,\n has_complex=False,\n *,\n beta1,\n beta2,\n lr,\n clip_lambda,\n weight_decay,\n decouple,\n eps,\n maximize,\n)\nFunctional API that performs ADOPT algorithm computation." + "text": "logging_config\nCommon logging module for axolotl\n\n\n\n\n\nName\nDescription\n\n\n\n\nColorfulFormatter\nFormatter to add coloring to log messages by log type\n\n\n\n\n\nlogging_config.ColorfulFormatter()\nFormatter to add coloring to log messages by log type\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nconfigure_logging\nConfigure with default logging\n\n\n\n\n\nlogging_config.configure_logging()\nConfigure with default logging" }, { - "objectID": "docs/api/utils.callbacks.lisa.html", - "href": "docs/api/utils.callbacks.lisa.html", - "title": "utils.callbacks.lisa", + "objectID": "docs/api/logging_config.html#classes", + "href": "docs/api/logging_config.html#classes", + "title": "logging_config", "section": "", - "text": "utils.callbacks.lisa\nutils.callbacks.lisa\nmodule for LISA\nAdapted from https://github.com/OptimalScale/LMFlow/pull/701 for HF transformers & Axolotl\nArxiv: https://arxiv.org/abs/2403.17919\nLicense: Apache 2.0" + "text": "Name\nDescription\n\n\n\n\nColorfulFormatter\nFormatter to add coloring to log messages by log type\n\n\n\n\n\nlogging_config.ColorfulFormatter()\nFormatter to add coloring to log messages by log type" }, { - "objectID": "docs/api/utils.data.pretraining.html", - "href": "docs/api/utils.data.pretraining.html", - "title": "utils.data.pretraining", + "objectID": "docs/api/logging_config.html#functions", + "href": "docs/api/logging_config.html#functions", + "title": "logging_config", "section": "", - "text": "utils.data.pretraining\nutils.data.pretraining\ndata handling specific to pretraining" + "text": "Name\nDescription\n\n\n\n\nconfigure_logging\nConfigure with default logging\n\n\n\n\n\nlogging_config.configure_logging()\nConfigure with default logging" }, { - "objectID": "docs/api/utils.schemas.model.html", - "href": "docs/api/utils.schemas.model.html", - "title": "utils.schemas.model", + "objectID": "docs/api/monkeypatch.mixtral.html", + "href": "docs/api/monkeypatch.mixtral.html", + "title": "monkeypatch.mixtral", "section": "", - "text": "utils.schemas.model\nPydantic models for model input / output, etc. configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nModelInputConfig\nModel configuration subset\n\n\nModelOutputConfig\nmodel save configuration subset\n\n\nSpecialTokensConfig\nSpecial tokens configuration subset\n\n\n\n\n\nutils.schemas.model.ModelInputConfig()\nModel configuration subset\n\n\n\nutils.schemas.model.ModelOutputConfig()\nmodel save configuration subset\n\n\n\nutils.schemas.model.SpecialTokensConfig()\nSpecial tokens configuration subset" + "text": "monkeypatch.mixtral\nmonkeypatch.mixtral\nPatches to support multipack for mixtral" }, { - "objectID": "docs/api/utils.schemas.model.html#classes", - "href": "docs/api/utils.schemas.model.html#classes", - "title": "utils.schemas.model", + "objectID": "docs/api/integrations.lm_eval.args.html", + "href": "docs/api/integrations.lm_eval.args.html", + "title": "integrations.lm_eval.args", "section": "", - "text": "Name\nDescription\n\n\n\n\nModelInputConfig\nModel configuration subset\n\n\nModelOutputConfig\nmodel save configuration subset\n\n\nSpecialTokensConfig\nSpecial tokens configuration subset\n\n\n\n\n\nutils.schemas.model.ModelInputConfig()\nModel configuration subset\n\n\n\nutils.schemas.model.ModelOutputConfig()\nmodel save configuration subset\n\n\n\nutils.schemas.model.SpecialTokensConfig()\nSpecial tokens configuration subset" + "text": "integrations.lm_eval.args\nModule for handling lm eval harness input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nLMEvalArgs\nInput args for lm eval harness\n\n\n\n\n\nintegrations.lm_eval.args.LMEvalArgs()\nInput args for lm eval harness" }, { - "objectID": "docs/api/kernels.utils.html", - "href": "docs/api/kernels.utils.html", - "title": "kernels.utils", + "objectID": "docs/api/integrations.lm_eval.args.html#classes", + "href": "docs/api/integrations.lm_eval.args.html#classes", + "title": "integrations.lm_eval.args", "section": "", - "text": "kernels.utils\nkernels.utils\nUtilities for axolotl.kernels submodules." + "text": "Name\nDescription\n\n\n\n\nLMEvalArgs\nInput args for lm eval harness\n\n\n\n\n\nintegrations.lm_eval.args.LMEvalArgs()\nInput args for lm eval harness" }, { - "objectID": "docs/api/prompt_strategies.base.html", - "href": "docs/api/prompt_strategies.base.html", - "title": "prompt_strategies.base", + "objectID": "docs/api/utils.model_shard_quant.html", + "href": "docs/api/utils.model_shard_quant.html", + "title": "utils.model_shard_quant", "section": "", - "text": "prompt_strategies.base\nprompt_strategies.base\nmodule for base dataset transform strategies" + "text": "utils.model_shard_quant\nmodule to handle loading model on cpu/meta device for FSDP\n\n\n\n\n\nName\nDescription\n\n\n\n\nload_and_quantize\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\n\n\n\n\n\nutils.model_shard_quant.load_and_quantize(\n module,\n name,\n value,\n device=None,\n dtype=None,\n skip_names=None,\n to_cpu=False,\n to_meta=False,\n verbose=False,\n quant_method='bnb',\n)\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\nQuantizes Params4bit on device then places on “cpu” if to_cpu=True or “meta” if to_meta=True." }, { - "objectID": "docs/api/prompt_strategies.kto.chatml.html", - "href": "docs/api/prompt_strategies.kto.chatml.html", - "title": "prompt_strategies.kto.chatml", + "objectID": "docs/api/utils.model_shard_quant.html#functions", + "href": "docs/api/utils.model_shard_quant.html#functions", + "title": "utils.model_shard_quant", "section": "", - "text": "prompt_strategies.kto.chatml\nKTO strategies for chatml\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.chatml.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" + "text": "Name\nDescription\n\n\n\n\nload_and_quantize\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\n\n\n\n\n\nutils.model_shard_quant.load_and_quantize(\n module,\n name,\n value,\n device=None,\n dtype=None,\n skip_names=None,\n to_cpu=False,\n to_meta=False,\n verbose=False,\n quant_method='bnb',\n)\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\nQuantizes Params4bit on device then places on “cpu” if to_cpu=True or “meta” if to_meta=True." }, { - "objectID": "docs/api/prompt_strategies.kto.chatml.html#functions", - "href": "docs/api/prompt_strategies.kto.chatml.html#functions", - "title": "prompt_strategies.kto.chatml", + "objectID": "docs/api/utils.schemas.utils.html", + "href": "docs/api/utils.schemas.utils.html", + "title": "utils.schemas.utils", "section": "", - "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.chatml.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" + "text": "utils.schemas.utils\nUtilities for Axolotl Pydantic models\n\n\n\n\n\nName\nDescription\n\n\n\n\nhandle_legacy_message_fields_logic\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.utils.handle_legacy_message_fields_logic(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\nPreviously, the config only supported mapping ‘role’ and ‘content’ fields via dedicated config options:\n- message_field_role: Mapped to the role field\n- message_field_content: Mapped to the content field\nThe new system uses message_property_mappings to support arbitrary field mappings:\nmessage_property_mappings:\nrole: source_role_field\ncontent: source_content_field\nadditional_field: source_field\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndata\ndict\nDictionary containing configuration data\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ndict\nUpdated dictionary with message field mappings consolidated\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf there are conflicts between legacy and new mappings" }, { - "objectID": "docs/api/cli.sweeps.html", - "href": "docs/api/cli.sweeps.html", - "title": "cli.sweeps", + "objectID": "docs/api/utils.schemas.utils.html#functions", + "href": "docs/api/utils.schemas.utils.html#functions", + "title": "utils.schemas.utils", "section": "", - "text": "cli.sweeps\nUtilities for handling sweeps over configs for axolotl train CLI command\n\n\n\n\n\nName\nDescription\n\n\n\n\ngenerate_sweep_configs\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\ncli.sweeps.generate_sweep_configs(base_config, sweeps_config)\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_config\ndict\nThe original configuration dictionary\nrequired\n\n\nsweeps_config\ndict\nDictionary where keys are parameters and values are either: - lists of values to sweep independently - or for paired values, a list of dicts under the ’_’ key\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nlist\nlist[dict[str, list]]\nList of all possible configuration dictionaries\n\n\n\n\n\n\nsweeps_config = {\n‘learning_rate’: [0.1, 0.01],\n’_’: [\n{‘load_in_8bit’: True, ‘adapter’: ‘lora’},\n{‘load_in_4bit’: True, ‘adapter’: ‘qlora’}\n]\n}" + "text": "Name\nDescription\n\n\n\n\nhandle_legacy_message_fields_logic\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.utils.handle_legacy_message_fields_logic(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\nPreviously, the config only supported mapping ‘role’ and ‘content’ fields via dedicated config options:\n- message_field_role: Mapped to the role field\n- message_field_content: Mapped to the content field\nThe new system uses message_property_mappings to support arbitrary field mappings:\nmessage_property_mappings:\nrole: source_role_field\ncontent: source_content_field\nadditional_field: source_field\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndata\ndict\nDictionary containing configuration data\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ndict\nUpdated dictionary with message field mappings consolidated\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf there are conflicts between legacy and new mappings" }, { - "objectID": "docs/api/cli.sweeps.html#functions", - "href": "docs/api/cli.sweeps.html#functions", - "title": "cli.sweeps", + "objectID": "docs/api/core.trainers.trl.html", + "href": "docs/api/core.trainers.trl.html", + "title": "core.trainers.trl", "section": "", - "text": "Name\nDescription\n\n\n\n\ngenerate_sweep_configs\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\ncli.sweeps.generate_sweep_configs(base_config, sweeps_config)\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_config\ndict\nThe original configuration dictionary\nrequired\n\n\nsweeps_config\ndict\nDictionary where keys are parameters and values are either: - lists of values to sweep independently - or for paired values, a list of dicts under the ’_’ key\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nlist\nlist[dict[str, list]]\nList of all possible configuration dictionaries\n\n\n\n\n\n\nsweeps_config = {\n‘learning_rate’: [0.1, 0.01],\n’_’: [\n{‘load_in_8bit’: True, ‘adapter’: ‘lora’},\n{‘load_in_4bit’: True, ‘adapter’: ‘qlora’}\n]\n}" + "text": "core.trainers.trl\nModule for TRL PPO trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlCPOTrainer\nExtend the base CPOTrainer for axolotl helpers\n\n\nAxolotlKTOTrainer\nExtend the base KTOTrainer for axolotl helpers\n\n\nAxolotlORPOTrainer\nExtend the base ORPOTrainer for axolotl helpers\n\n\nAxolotlPRMTrainer\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\nAxolotlRewardTrainer\nExtend the base RewardTrainer for axolotl helpers\n\n\nTRLPPOTrainer\nWrapper for TRL PPO trainer to handle customizations\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer()\nExtend the base CPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlKTOTrainer()\nExtend the base KTOTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer()\nExtend the base ORPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlPRMTrainer()\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlRewardTrainer()\nExtend the base RewardTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.TRLPPOTrainer()\nWrapper for TRL PPO trainer to handle customizations" }, { - "objectID": "docs/api/monkeypatch.multipack.html", - "href": "docs/api/monkeypatch.multipack.html", - "title": "monkeypatch.multipack", + "objectID": "docs/api/core.trainers.trl.html#classes", + "href": "docs/api/core.trainers.trl.html#classes", + "title": "core.trainers.trl", "section": "", - "text": "monkeypatch.multipack\nmonkeypatch.multipack\nmultipack patching for v2 of sample packing" + "text": "Name\nDescription\n\n\n\n\nAxolotlCPOTrainer\nExtend the base CPOTrainer for axolotl helpers\n\n\nAxolotlKTOTrainer\nExtend the base KTOTrainer for axolotl helpers\n\n\nAxolotlORPOTrainer\nExtend the base ORPOTrainer for axolotl helpers\n\n\nAxolotlPRMTrainer\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\nAxolotlRewardTrainer\nExtend the base RewardTrainer for axolotl helpers\n\n\nTRLPPOTrainer\nWrapper for TRL PPO trainer to handle customizations\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer()\nExtend the base CPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlKTOTrainer()\nExtend the base KTOTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer()\nExtend the base ORPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlPRMTrainer()\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlRewardTrainer()\nExtend the base RewardTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.TRLPPOTrainer()\nWrapper for TRL PPO trainer to handle customizations" }, { - "objectID": "docs/api/cli.evaluate.html", - "href": "docs/api/cli.evaluate.html", - "title": "cli.evaluate", + "objectID": "docs/api/utils.collators.batching.html", + "href": "docs/api/utils.collators.batching.html", + "title": "utils.collators.batching", "section": "", - "text": "cli.evaluate\nCLI to run evaluation on a model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\ndo_evaluate\nEvaluates a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.evaluate.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.evaluate.do_evaluate(cfg, cli_args)\nEvaluates a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.evaluate.evaluate, which computes\nevaluation metrics on the given dataset(s) and writes them to disk.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nCLI arguments.\nrequired" + "text": "utils.collators.batching\nData collators for axolotl to pad labels and position_ids for packed sequences\n\n\n\n\n\nName\nDescription\n\n\n\n\nBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nDataCollatorForSeq2Seq\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\nPretrainingBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nV2BatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\n\n\n\nutils.collators.batching.BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.DataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer\n[PreTrainedTokenizer] or [PreTrainedTokenizerFast]\nThe tokenizer used for encoding the data.\nrequired\n\n\nmodel\n[PreTrainedModel]\nThe model that is being trained. If set and has the prepare_decoder_input_ids_from_labels, use it to prepare the decoder_input_ids This is useful when using label_smoothing to avoid calculating loss twice.\nNone\n\n\npadding\nbool, str or [~utils.PaddingStrategy], optional, defaults to True\nSelect a strategy to pad the returned sequences (according to the model’s padding side and padding index) among: - True or 'longest' (default): Pad to the longest sequence in the batch (or no padding if only a single sequence is provided). - 'max_length': Pad to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. - False or 'do_not_pad': No padding (i.e., can output a batch with sequences of different lengths).\nTrue\n\n\nmax_length\nint, optional\nMaximum length of the returned list and optionally padding length (see above).\nNone\n\n\npad_to_multiple_of\nint, optional\nIf set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta).\nNone\n\n\nlabel_pad_token_id\nint, optional, defaults to -100\nThe id to use when padding the labels (-100 will be automatically ignored by PyTorch loss functions).\n-100\n\n\nreturn_tensors\nstr\nThe type of Tensor to return. Allowable values are “np”, “pt” and “tf”.\n'pt'\n\n\n\n\n\n\n\nutils.collators.batching.PretrainingBatchSamplerDataCollatorForSeq2Seq(\n self,\n *args,\n multipack_attn=True,\n **kwargs,\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.V2BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler" }, { - "objectID": "docs/api/cli.evaluate.html#functions", - "href": "docs/api/cli.evaluate.html#functions", - "title": "cli.evaluate", + "objectID": "docs/api/utils.collators.batching.html#classes", + "href": "docs/api/utils.collators.batching.html#classes", + "title": "utils.collators.batching", "section": "", - "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\ndo_evaluate\nEvaluates a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.evaluate.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.evaluate.do_evaluate(cfg, cli_args)\nEvaluates a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.evaluate.evaluate, which computes\nevaluation metrics on the given dataset(s) and writes them to disk.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nCLI arguments.\nrequired" + "text": "Name\nDescription\n\n\n\n\nBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nDataCollatorForSeq2Seq\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\nPretrainingBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nV2BatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\n\n\n\nutils.collators.batching.BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.DataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer\n[PreTrainedTokenizer] or [PreTrainedTokenizerFast]\nThe tokenizer used for encoding the data.\nrequired\n\n\nmodel\n[PreTrainedModel]\nThe model that is being trained. If set and has the prepare_decoder_input_ids_from_labels, use it to prepare the decoder_input_ids This is useful when using label_smoothing to avoid calculating loss twice.\nNone\n\n\npadding\nbool, str or [~utils.PaddingStrategy], optional, defaults to True\nSelect a strategy to pad the returned sequences (according to the model’s padding side and padding index) among: - True or 'longest' (default): Pad to the longest sequence in the batch (or no padding if only a single sequence is provided). - 'max_length': Pad to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. - False or 'do_not_pad': No padding (i.e., can output a batch with sequences of different lengths).\nTrue\n\n\nmax_length\nint, optional\nMaximum length of the returned list and optionally padding length (see above).\nNone\n\n\npad_to_multiple_of\nint, optional\nIf set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta).\nNone\n\n\nlabel_pad_token_id\nint, optional, defaults to -100\nThe id to use when padding the labels (-100 will be automatically ignored by PyTorch loss functions).\n-100\n\n\nreturn_tensors\nstr\nThe type of Tensor to return. Allowable values are “np”, “pt” and “tf”.\n'pt'\n\n\n\n\n\n\n\nutils.collators.batching.PretrainingBatchSamplerDataCollatorForSeq2Seq(\n self,\n *args,\n multipack_attn=True,\n **kwargs,\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.V2BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler" }, { - "objectID": "docs/api/prompt_strategies.orcamini.html", - "href": "docs/api/prompt_strategies.orcamini.html", - "title": "prompt_strategies.orcamini", + "objectID": "docs/api/prompt_strategies.alpaca_w_system.html", + "href": "docs/api/prompt_strategies.alpaca_w_system.html", + "title": "prompt_strategies.alpaca_w_system", "section": "", - "text": "prompt_strategies.orcamini\nPrompt Strategy for finetuning Orca Mini (v2) models\nsee also https://huggingface.co/psmathur/orca_mini_v2_7b for more information\nUse dataset type: orcamini in conig.yml to use this prompt style.\nCompared to the alpaca_w_system.open_orca dataset type,\nthis one specifies the system prompt with “### System:”.\nNot suited/tested for multiple-turn conversations without further adjustments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nOrcaMiniPrompter\nAdjusted Prompter for Orca Mini (v2) datasets\n\n\n\n\n\nprompt_strategies.orcamini.OrcaMiniPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAdjusted Prompter for Orca Mini (v2) datasets" + "text": "prompt_strategies.alpaca_w_system\nPrompt strategies loader for alpaca instruction datasets with system prompts\n\n\n\n\n\nName\nDescription\n\n\n\n\nInstructionWSystemPromptTokenizingStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nOpenOrcaPromptTokenizingStrategy\nTokenizing strategy for OpenOrca datasets\n\n\nOpenOrcaSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\nSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset\n\n\n\n\n\nprompt_strategies.alpaca_w_system.InstructionWSystemPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for OpenOrca datasets\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaSystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\n\nprompt_strategies.alpaca_w_system.SystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset" }, { - "objectID": "docs/api/prompt_strategies.orcamini.html#classes", - "href": "docs/api/prompt_strategies.orcamini.html#classes", - "title": "prompt_strategies.orcamini", + "objectID": "docs/api/prompt_strategies.alpaca_w_system.html#classes", + "href": "docs/api/prompt_strategies.alpaca_w_system.html#classes", + "title": "prompt_strategies.alpaca_w_system", "section": "", - "text": "Name\nDescription\n\n\n\n\nOrcaMiniPrompter\nAdjusted Prompter for Orca Mini (v2) datasets\n\n\n\n\n\nprompt_strategies.orcamini.OrcaMiniPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAdjusted Prompter for Orca Mini (v2) datasets" + "text": "Name\nDescription\n\n\n\n\nInstructionWSystemPromptTokenizingStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nOpenOrcaPromptTokenizingStrategy\nTokenizing strategy for OpenOrca datasets\n\n\nOpenOrcaSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\nSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset\n\n\n\n\n\nprompt_strategies.alpaca_w_system.InstructionWSystemPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for OpenOrca datasets\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaSystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\n\nprompt_strategies.alpaca_w_system.SystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset" }, { - "objectID": "docs/api/prompt_strategies.dpo.passthrough.html", - "href": "docs/api/prompt_strategies.dpo.passthrough.html", - "title": "prompt_strategies.dpo.passthrough", + "objectID": "docs/api/integrations.base.html", + "href": "docs/api/integrations.base.html", + "title": "integrations.base", "section": "", - "text": "prompt_strategies.dpo.passthrough\nprompt_strategies.dpo.passthrough\nDPO prompt strategies passthrough/zero-processing strategy" + "text": "integrations.base\nBase class for all plugins.\nA plugin is a reusable, modular, and self-contained piece of code that extends the functionality of Axolotl.\nPlugins can be used to integrate third-party models, modify the training process, or add new features.\nTo create a new plugin, you need to inherit from the BasePlugin class and implement the required methods.\n\n\n\n\n\nName\nDescription\n\n\n\n\nBaseOptimizerFactory\nBase class for factories to create custom optimizers\n\n\nBasePlugin\nBase class for all plugins. Defines the interface for plugin methods.\n\n\nPluginManager\nThe PluginManager class is responsible for loading and managing plugins.\n\n\n\n\n\nintegrations.base.BaseOptimizerFactory()\nBase class for factories to create custom optimizers\n\n\n\nintegrations.base.BasePlugin(self)\nBase class for all plugins. Defines the interface for plugin methods.\nAttributes:\nNone\nMethods:\nregister(cfg): Registers the plugin with the given configuration.\nload_datasets(cfg): Loads and preprocesses the dataset for training.\npre_model_load(cfg): Performs actions before the model is loaded.\npost_model_build(cfg, model): Performs actions after the model is loaded, but before LoRA adapters are applied.\npre_lora_load(cfg, model): Performs actions before LoRA weights are loaded.\npost_lora_load(cfg, model): Performs actions after LoRA weights are loaded.\npost_model_load(cfg, model): Performs actions after the model is loaded, inclusive of any adapters.\npost_trainer_create(cfg, trainer): Performs actions after the trainer is created.\ncreate_optimizer(cfg, trainer): Creates and returns an optimizer for training.\ncreate_lr_scheduler(cfg, trainer, optimizer, num_training_steps): Creates and returns a learning rate scheduler.\nadd_callbacks_pre_trainer(cfg, model): Adds callbacks to the trainer before training.\nadd_callbacks_post_trainer(cfg, trainer): Adds callbacks to the trainer after training.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nAdds callbacks to the trainer after creating the trainer.\n\n\nadd_callbacks_pre_trainer\nsetup callbacks before creating the trainer.\n\n\ncreate_lr_scheduler\nCreates and returns a learning rate scheduler.\n\n\ncreate_optimizer\nCreates and returns an optimizer for training.\n\n\nget_input_args\nReturns a pydantic model for the plugin’s input arguments.\n\n\nget_trainer_cls\nReturns a custom class for the trainer.\n\n\nload_datasets\nLoads and preprocesses the dataset for training.\n\n\npost_lora_load\nPerforms actions after LoRA weights are loaded.\n\n\npost_model_build\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\npost_model_load\nPerforms actions after the model is loaded.\n\n\npost_train\nPerforms actions after training is complete.\n\n\npost_train_unload\nPerforms actions after training is complete and the model is unloaded.\n\n\npost_trainer_create\nPerforms actions after the trainer is created.\n\n\npre_lora_load\nPerforms actions before LoRA weights are loaded.\n\n\npre_model_load\nPerforms actions before the model is loaded.\n\n\nregister\nRegisters the plugin with the given configuration.\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_post_trainer(cfg, trainer)\nAdds callbacks to the trainer after creating the trainer.\nThis is useful for callbacks that require access to the model or trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_pre_trainer(cfg, model)\nsetup callbacks before creating the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added to the TrainingArgs\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_lr_scheduler(\n cfg,\n trainer,\n optimizer,\n num_training_steps,\n)\nCreates and returns a learning rate scheduler.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\noptimizer\nobject\nThe optimizer for training.\nrequired\n\n\nnum_training_steps\nint\nTotal number of training steps\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\nLRScheduler\nThe created learning rate scheduler.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_optimizer(cfg, trainer)\nCreates and returns an optimizer for training.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\n\nThe created optimizer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.get_input_args()\nReturns a pydantic model for the plugin’s input arguments.\n\n\n\nintegrations.base.BasePlugin.get_trainer_cls(cfg)\nReturns a custom class for the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe global axolotl configuration.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nclass\n\nThe class for the trainer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.load_datasets(cfg, preprocess=False)\nLoads and preprocesses the dataset for training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration for the plugin.\nrequired\n\n\npreprocess\nbool\nWhether this is the preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe metadata for the training dataset.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_lora_load(cfg, model)\nPerforms actions after LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_build(cfg, model)\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_load(cfg, model)\nPerforms actions after the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train(cfg, model)\nPerforms actions after training is complete.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe axolotl configuration\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train_unload(cfg)\nPerforms actions after training is complete and the model is unloaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_trainer_create(cfg, trainer)\nPerforms actions after the trainer is created.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_lora_load(cfg, model)\nPerforms actions before LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_model_load(cfg)\nPerforms actions before the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.register(cfg)\nRegisters the plugin with the given configuration.\nParameters:\ncfg (dict): The configuration for the plugin.\nReturns:\nNone\n\n\n\n\n\nintegrations.base.PluginManager()\nThe PluginManager class is responsible for loading and managing plugins.\nIt should be a singleton so it can be accessed from anywhere in the codebase.\nAttributes:\nplugins (ListBasePlugin): A list of loaded plugins.\nMethods:\nget_instance(): Static method to get the singleton instance of PluginManager.\nregister(plugin_name: str): Registers a new plugin by its name.\npre_model_load(cfg): Calls the pre_model_load method of all registered plugins.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nCalls the add_callbacks_post_trainer method of all registered plugins.\n\n\nadd_callbacks_pre_trainer\nCalls the add_callbacks_pre_trainer method of all registered plugins.\n\n\ncreate_lr_scheduler\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\n\n\ncreate_optimizer\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\n\n\nget_input_args\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\n\n\nget_instance\nReturns the singleton instance of PluginManager.\n\n\nget_trainer_cls\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\n\n\nload_datasets\nCalls the load_datasets method of each registered plugin.\n\n\npost_lora_load\nCalls the post_lora_load method of all registered plugins.\n\n\npost_model_build\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\n\n\npost_model_load\nCalls the post_model_load method of all registered plugins after the model has been loaded\n\n\npost_train\nCalls the post_train method of all registered plugins.\n\n\npost_train_unload\nCalls the post_train_unload method of all registered plugins.\n\n\npost_trainer_create\nCalls the post_trainer_create method of all registered plugins.\n\n\npre_lora_load\nCalls the pre_lora_load method of all registered plugins.\n\n\npre_model_load\nCalls the pre_model_load method of all registered plugins.\n\n\nregister\nRegisters a new plugin by its name.\n\n\n\n\n\nintegrations.base.PluginManager.add_callbacks_post_trainer(cfg, trainer)\nCalls the add_callbacks_post_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.add_callbacks_pre_trainer(cfg, model)\nCalls the add_callbacks_pre_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.create_lr_scheduler(\n trainer,\n optimizer,\n num_training_steps,\n)\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\nParameters:\ntrainer (object): The trainer object for training.\noptimizer (object): The optimizer for training.\nReturns:\nobject: The created learning rate scheduler, or None if none was found.\n\n\n\nintegrations.base.PluginManager.create_optimizer(trainer)\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\nParameters:\ntrainer (object): The trainer object for training.\nReturns:\nobject: The created optimizer, or None if none was found.\n\n\n\nintegrations.base.PluginManager.get_input_args()\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\nReturns:\nlist[str]: A list of Pydantic classes for all registered plugins’ input arguments.’\n\n\n\nintegrations.base.PluginManager.get_instance()\nReturns the singleton instance of PluginManager.\nIf the instance doesn’t exist, it creates a new one.\n\n\n\nintegrations.base.PluginManager.get_trainer_cls(cfg)\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nobject: The trainer class, or None if none was found.\n\n\n\nintegrations.base.PluginManager.load_datasets(cfg, preprocess=False)\nCalls the load_datasets method of each registered plugin.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nThe configuration for the plugins.\nrequired\n\n\npreprocess\n\nWhether this is preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe dataset metadata loaded from all registered plugins.\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_lora_load(cfg, model)\nCalls the post_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_model_build(cfg, model)\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\nbut before any adapters have been applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugins.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_model_load(cfg, model)\nCalls the post_model_load method of all registered plugins after the model has been loaded\ninclusive of any adapters\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train(cfg, model)\nCalls the post_train method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train_unload(cfg)\nCalls the post_train_unload method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_trainer_create(cfg, trainer)\nCalls the post_trainer_create method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_lora_load(cfg, model)\nCalls the pre_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_model_load(cfg)\nCalls the pre_model_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.register(plugin_name)\nRegisters a new plugin by its name.\nParameters:\nplugin_name (str): The name of the plugin to be registered.\nReturns:\nNone\nRaises:\nImportError: If the plugin module cannot be imported.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nload_plugin\nLoads a plugin based on the given plugin name.\n\n\n\n\n\nintegrations.base.load_plugin(plugin_name)\nLoads a plugin based on the given plugin name.\nThe plugin name should be in the format “module_name.class_name”.\nThis function splits the plugin name into module and class, imports the module,\nretrieves the class from the module, and creates an instance of the class.\nParameters:\nplugin_name (str): The name of the plugin to be loaded. The name should be in the format “module_name.class_name”.\nReturns:\nBasePlugin: An instance of the loaded plugin.\nRaises:\nImportError: If the plugin module cannot be imported." }, { - "objectID": "docs/api/monkeypatch.unsloth_.html", - "href": "docs/api/monkeypatch.unsloth_.html", - "title": "monkeypatch.unsloth_", + "objectID": "docs/api/integrations.base.html#classes", + "href": "docs/api/integrations.base.html#classes", + "title": "integrations.base", "section": "", - "text": "monkeypatch.unsloth_\nmonkeypatch.unsloth_\nmodule for patching with unsloth optimizations" + "text": "Name\nDescription\n\n\n\n\nBaseOptimizerFactory\nBase class for factories to create custom optimizers\n\n\nBasePlugin\nBase class for all plugins. Defines the interface for plugin methods.\n\n\nPluginManager\nThe PluginManager class is responsible for loading and managing plugins.\n\n\n\n\n\nintegrations.base.BaseOptimizerFactory()\nBase class for factories to create custom optimizers\n\n\n\nintegrations.base.BasePlugin(self)\nBase class for all plugins. Defines the interface for plugin methods.\nAttributes:\nNone\nMethods:\nregister(cfg): Registers the plugin with the given configuration.\nload_datasets(cfg): Loads and preprocesses the dataset for training.\npre_model_load(cfg): Performs actions before the model is loaded.\npost_model_build(cfg, model): Performs actions after the model is loaded, but before LoRA adapters are applied.\npre_lora_load(cfg, model): Performs actions before LoRA weights are loaded.\npost_lora_load(cfg, model): Performs actions after LoRA weights are loaded.\npost_model_load(cfg, model): Performs actions after the model is loaded, inclusive of any adapters.\npost_trainer_create(cfg, trainer): Performs actions after the trainer is created.\ncreate_optimizer(cfg, trainer): Creates and returns an optimizer for training.\ncreate_lr_scheduler(cfg, trainer, optimizer, num_training_steps): Creates and returns a learning rate scheduler.\nadd_callbacks_pre_trainer(cfg, model): Adds callbacks to the trainer before training.\nadd_callbacks_post_trainer(cfg, trainer): Adds callbacks to the trainer after training.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nAdds callbacks to the trainer after creating the trainer.\n\n\nadd_callbacks_pre_trainer\nsetup callbacks before creating the trainer.\n\n\ncreate_lr_scheduler\nCreates and returns a learning rate scheduler.\n\n\ncreate_optimizer\nCreates and returns an optimizer for training.\n\n\nget_input_args\nReturns a pydantic model for the plugin’s input arguments.\n\n\nget_trainer_cls\nReturns a custom class for the trainer.\n\n\nload_datasets\nLoads and preprocesses the dataset for training.\n\n\npost_lora_load\nPerforms actions after LoRA weights are loaded.\n\n\npost_model_build\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\npost_model_load\nPerforms actions after the model is loaded.\n\n\npost_train\nPerforms actions after training is complete.\n\n\npost_train_unload\nPerforms actions after training is complete and the model is unloaded.\n\n\npost_trainer_create\nPerforms actions after the trainer is created.\n\n\npre_lora_load\nPerforms actions before LoRA weights are loaded.\n\n\npre_model_load\nPerforms actions before the model is loaded.\n\n\nregister\nRegisters the plugin with the given configuration.\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_post_trainer(cfg, trainer)\nAdds callbacks to the trainer after creating the trainer.\nThis is useful for callbacks that require access to the model or trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_pre_trainer(cfg, model)\nsetup callbacks before creating the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added to the TrainingArgs\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_lr_scheduler(\n cfg,\n trainer,\n optimizer,\n num_training_steps,\n)\nCreates and returns a learning rate scheduler.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\noptimizer\nobject\nThe optimizer for training.\nrequired\n\n\nnum_training_steps\nint\nTotal number of training steps\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\nLRScheduler\nThe created learning rate scheduler.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_optimizer(cfg, trainer)\nCreates and returns an optimizer for training.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\n\nThe created optimizer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.get_input_args()\nReturns a pydantic model for the plugin’s input arguments.\n\n\n\nintegrations.base.BasePlugin.get_trainer_cls(cfg)\nReturns a custom class for the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe global axolotl configuration.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nclass\n\nThe class for the trainer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.load_datasets(cfg, preprocess=False)\nLoads and preprocesses the dataset for training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration for the plugin.\nrequired\n\n\npreprocess\nbool\nWhether this is the preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe metadata for the training dataset.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_lora_load(cfg, model)\nPerforms actions after LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_build(cfg, model)\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_load(cfg, model)\nPerforms actions after the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train(cfg, model)\nPerforms actions after training is complete.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe axolotl configuration\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train_unload(cfg)\nPerforms actions after training is complete and the model is unloaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_trainer_create(cfg, trainer)\nPerforms actions after the trainer is created.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_lora_load(cfg, model)\nPerforms actions before LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_model_load(cfg)\nPerforms actions before the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.register(cfg)\nRegisters the plugin with the given configuration.\nParameters:\ncfg (dict): The configuration for the plugin.\nReturns:\nNone\n\n\n\n\n\nintegrations.base.PluginManager()\nThe PluginManager class is responsible for loading and managing plugins.\nIt should be a singleton so it can be accessed from anywhere in the codebase.\nAttributes:\nplugins (ListBasePlugin): A list of loaded plugins.\nMethods:\nget_instance(): Static method to get the singleton instance of PluginManager.\nregister(plugin_name: str): Registers a new plugin by its name.\npre_model_load(cfg): Calls the pre_model_load method of all registered plugins.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nCalls the add_callbacks_post_trainer method of all registered plugins.\n\n\nadd_callbacks_pre_trainer\nCalls the add_callbacks_pre_trainer method of all registered plugins.\n\n\ncreate_lr_scheduler\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\n\n\ncreate_optimizer\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\n\n\nget_input_args\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\n\n\nget_instance\nReturns the singleton instance of PluginManager.\n\n\nget_trainer_cls\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\n\n\nload_datasets\nCalls the load_datasets method of each registered plugin.\n\n\npost_lora_load\nCalls the post_lora_load method of all registered plugins.\n\n\npost_model_build\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\n\n\npost_model_load\nCalls the post_model_load method of all registered plugins after the model has been loaded\n\n\npost_train\nCalls the post_train method of all registered plugins.\n\n\npost_train_unload\nCalls the post_train_unload method of all registered plugins.\n\n\npost_trainer_create\nCalls the post_trainer_create method of all registered plugins.\n\n\npre_lora_load\nCalls the pre_lora_load method of all registered plugins.\n\n\npre_model_load\nCalls the pre_model_load method of all registered plugins.\n\n\nregister\nRegisters a new plugin by its name.\n\n\n\n\n\nintegrations.base.PluginManager.add_callbacks_post_trainer(cfg, trainer)\nCalls the add_callbacks_post_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.add_callbacks_pre_trainer(cfg, model)\nCalls the add_callbacks_pre_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.create_lr_scheduler(\n trainer,\n optimizer,\n num_training_steps,\n)\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\nParameters:\ntrainer (object): The trainer object for training.\noptimizer (object): The optimizer for training.\nReturns:\nobject: The created learning rate scheduler, or None if none was found.\n\n\n\nintegrations.base.PluginManager.create_optimizer(trainer)\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\nParameters:\ntrainer (object): The trainer object for training.\nReturns:\nobject: The created optimizer, or None if none was found.\n\n\n\nintegrations.base.PluginManager.get_input_args()\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\nReturns:\nlist[str]: A list of Pydantic classes for all registered plugins’ input arguments.’\n\n\n\nintegrations.base.PluginManager.get_instance()\nReturns the singleton instance of PluginManager.\nIf the instance doesn’t exist, it creates a new one.\n\n\n\nintegrations.base.PluginManager.get_trainer_cls(cfg)\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nobject: The trainer class, or None if none was found.\n\n\n\nintegrations.base.PluginManager.load_datasets(cfg, preprocess=False)\nCalls the load_datasets method of each registered plugin.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nThe configuration for the plugins.\nrequired\n\n\npreprocess\n\nWhether this is preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe dataset metadata loaded from all registered plugins.\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_lora_load(cfg, model)\nCalls the post_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_model_build(cfg, model)\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\nbut before any adapters have been applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugins.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_model_load(cfg, model)\nCalls the post_model_load method of all registered plugins after the model has been loaded\ninclusive of any adapters\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train(cfg, model)\nCalls the post_train method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train_unload(cfg)\nCalls the post_train_unload method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_trainer_create(cfg, trainer)\nCalls the post_trainer_create method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_lora_load(cfg, model)\nCalls the pre_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_model_load(cfg)\nCalls the pre_model_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.register(plugin_name)\nRegisters a new plugin by its name.\nParameters:\nplugin_name (str): The name of the plugin to be registered.\nReturns:\nNone\nRaises:\nImportError: If the plugin module cannot be imported." }, { - "objectID": "docs/api/utils.schemas.config.html", - "href": "docs/api/utils.schemas.config.html", - "title": "utils.schemas.config", + "objectID": "docs/api/integrations.base.html#functions", + "href": "docs/api/integrations.base.html#functions", + "title": "integrations.base", "section": "", - "text": "utils.schemas.config\nModule with Pydantic models for configuration.\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlConfigWCapabilities\nwrapper to valdiate gpu capabilities with the configured options\n\n\nAxolotlInputConfig\nWrapper of all config options\n\n\n\n\n\nutils.schemas.config.AxolotlConfigWCapabilities()\nwrapper to valdiate gpu capabilities with the configured options\n\n\n\nutils.schemas.config.AxolotlInputConfig()\nWrapper of all config options" + "text": "Name\nDescription\n\n\n\n\nload_plugin\nLoads a plugin based on the given plugin name.\n\n\n\n\n\nintegrations.base.load_plugin(plugin_name)\nLoads a plugin based on the given plugin name.\nThe plugin name should be in the format “module_name.class_name”.\nThis function splits the plugin name into module and class, imports the module,\nretrieves the class from the module, and creates an instance of the class.\nParameters:\nplugin_name (str): The name of the plugin to be loaded. The name should be in the format “module_name.class_name”.\nReturns:\nBasePlugin: An instance of the loaded plugin.\nRaises:\nImportError: If the plugin module cannot be imported." }, { - "objectID": "docs/api/utils.schemas.config.html#classes", - "href": "docs/api/utils.schemas.config.html#classes", - "title": "utils.schemas.config", + "objectID": "docs/api/core.chat.messages.html", + "href": "docs/api/core.chat.messages.html", + "title": "core.chat.messages", "section": "", - "text": "Name\nDescription\n\n\n\n\nAxolotlConfigWCapabilities\nwrapper to valdiate gpu capabilities with the configured options\n\n\nAxolotlInputConfig\nWrapper of all config options\n\n\n\n\n\nutils.schemas.config.AxolotlConfigWCapabilities()\nwrapper to valdiate gpu capabilities with the configured options\n\n\n\nutils.schemas.config.AxolotlInputConfig()\nWrapper of all config options" + "text": "core.chat.messages\ninternal message representations of chat messages\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatFormattedChats\nChat formatted chats with formatter and optional train on inputs\n\n\nChats\ntop level data structure for chat conversations\n\n\nMessageContentTypes\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\nMessageContents\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\nMessageRoles\nMessage roles for the system, user, assistant, and tools\n\n\nMessages\nMessages with role, content, metadata, weight, and chat formatting\n\n\nPreferenceChats\nrepresentation for preference data for chat\n\n\nSpecialToken\nSpecial tokens for beginning of string and end of string\n\n\nTool\nTool with description, function, and parameters\n\n\nToolCallContents\nTool call contents with name, arguments, and optional id\n\n\nToolCallFunction\nTool call function with name and arguments\n\n\nToolResponseContents\nTool response contents with name, content, and optional id\n\n\n\n\n\ncore.chat.messages.ChatFormattedChats()\nChat formatted chats with formatter and optional train on inputs\n\n\n\ncore.chat.messages.Chats()\ntop level data structure for chat conversations\n\n\n\ncore.chat.messages.MessageContentTypes()\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\n\ncore.chat.messages.MessageContents()\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\n\ncore.chat.messages.MessageRoles()\nMessage roles for the system, user, assistant, and tools\n\n\n\ncore.chat.messages.Messages()\nMessages with role, content, metadata, weight, and chat formatting\n\n\n\ncore.chat.messages.PreferenceChats()\nrepresentation for preference data for chat\n\n\n\ncore.chat.messages.SpecialToken()\nSpecial tokens for beginning of string and end of string\n\n\n\ncore.chat.messages.Tool()\nTool with description, function, and parameters\n\n\n\ncore.chat.messages.ToolCallContents()\nTool call contents with name, arguments, and optional id\n\n\n\ncore.chat.messages.ToolCallFunction()\nTool call function with name and arguments\n\n\n\ncore.chat.messages.ToolResponseContents()\nTool response contents with name, content, and optional id" }, { - "objectID": "docs/api/prompt_strategies.dpo.zephyr.html", - "href": "docs/api/prompt_strategies.dpo.zephyr.html", - "title": "prompt_strategies.dpo.zephyr", + "objectID": "docs/api/core.chat.messages.html#classes", + "href": "docs/api/core.chat.messages.html#classes", + "title": "core.chat.messages", "section": "", - "text": "prompt_strategies.dpo.zephyr\nprompt_strategies.dpo.zephyr\nDPO strategies for zephyr" + "text": "Name\nDescription\n\n\n\n\nChatFormattedChats\nChat formatted chats with formatter and optional train on inputs\n\n\nChats\ntop level data structure for chat conversations\n\n\nMessageContentTypes\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\nMessageContents\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\nMessageRoles\nMessage roles for the system, user, assistant, and tools\n\n\nMessages\nMessages with role, content, metadata, weight, and chat formatting\n\n\nPreferenceChats\nrepresentation for preference data for chat\n\n\nSpecialToken\nSpecial tokens for beginning of string and end of string\n\n\nTool\nTool with description, function, and parameters\n\n\nToolCallContents\nTool call contents with name, arguments, and optional id\n\n\nToolCallFunction\nTool call function with name and arguments\n\n\nToolResponseContents\nTool response contents with name, content, and optional id\n\n\n\n\n\ncore.chat.messages.ChatFormattedChats()\nChat formatted chats with formatter and optional train on inputs\n\n\n\ncore.chat.messages.Chats()\ntop level data structure for chat conversations\n\n\n\ncore.chat.messages.MessageContentTypes()\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\n\ncore.chat.messages.MessageContents()\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\n\ncore.chat.messages.MessageRoles()\nMessage roles for the system, user, assistant, and tools\n\n\n\ncore.chat.messages.Messages()\nMessages with role, content, metadata, weight, and chat formatting\n\n\n\ncore.chat.messages.PreferenceChats()\nrepresentation for preference data for chat\n\n\n\ncore.chat.messages.SpecialToken()\nSpecial tokens for beginning of string and end of string\n\n\n\ncore.chat.messages.Tool()\nTool with description, function, and parameters\n\n\n\ncore.chat.messages.ToolCallContents()\nTool call contents with name, arguments, and optional id\n\n\n\ncore.chat.messages.ToolCallFunction()\nTool call function with name and arguments\n\n\n\ncore.chat.messages.ToolResponseContents()\nTool response contents with name, content, and optional id" }, { - "objectID": "docs/api/monkeypatch.attention.mllama.html", - "href": "docs/api/monkeypatch.attention.mllama.html", - "title": "monkeypatch.attention.mllama", + "objectID": "docs/api/kernels.lora.html", + "href": "docs/api/kernels.lora.html", + "title": "kernels.lora", "section": "", - "text": "monkeypatch.attention.mllama\nMonkeypatch for Vision Llama for FA2 support\n\n\n\n\n\nName\nDescription\n\n\n\n\nMllamaTextCrossFlashAttention2\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\n\n\nMllamaTextSelfFlashAttention2\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\n\n\n\n\n\nmonkeypatch.attention.mllama.MllamaTextCrossFlashAttention2(\n self,\n *args,\n **kwargs,\n)\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\nimplements the forward pass using Flash Attention for improved performance.\n\n\n\nmonkeypatch.attention.mllama.MllamaTextSelfFlashAttention2(\n self,\n config,\n layer_idx,\n *args,\n **kwargs,\n)\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\nimplements the forward pass using Flash Attention for improved performance." + "text": "kernels.lora\nModule for definition of Low-Rank Adaptation (LoRA) Triton kernels.\nSee “LoRA: Low-Rank Adaptation of Large Language Models”\n(https://arxiv.org/abs/2106.09685).\nCredit to unsloth (https://unsloth.ai/) for inspiration for this implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nLoRA_MLP\nOptimized LoRA MLP implementation.\n\n\nLoRA_O\nOptimized LoRA implementation for output projection.\n\n\nLoRA_QKV\nOptimized LoRA QKV implementation with quantization support.\n\n\n\n\n\nkernels.lora.LoRA_MLP()\nOptimized LoRA MLP implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nPerforms backward pass computation for LoRA MLP.\n\n\nforward\nForward pass for LoRA MLP.\n\n\n\n\n\nkernels.lora.LoRA_MLP.backward(ctx, grad_output)\nPerforms backward pass computation for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nContext object storing tensors saved during forward pass\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to layer output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor | None\nTuple containing gradients for all inputs from forward pass:\n\n\n\nNone\n- Input gradient tensor (or None)\n\n\n\nNone\n- None for weights/quantization states\n\n\n\ntorch.Tensor | None\n- LoRA A/B matrix gradients (or None)\n\n\n\ntorch.Tensor | None\n- None for scaling factors\n\n\n\nNone\n- None for activation functions and flags\n\n\n\n\n\n\n\nkernels.lora.LoRA_MLP.forward(\n ctx,\n X,\n gate_weight,\n gate_quant,\n gate_A,\n gate_B,\n gate_scale,\n up_weight,\n up_quant,\n up_A,\n up_B,\n up_scale,\n down_weight,\n down_quant,\n down_A,\n down_B,\n down_scale,\n activation_fn,\n activation_fn_backward,\n inplace=True,\n)\nForward pass for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\n\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput features\nrequired\n\n\ngate_weight\ntorch.Tensor\nGate projection weight\nrequired\n\n\ngate_quant\nobject | None\nGate quantization state\nrequired\n\n\ngate_A\ntorch.Tensor | None\nGate LoRA A matrix\nrequired\n\n\ngate_B\ntorch.Tensor | None\nGate LoRA B matrix\nrequired\n\n\ngate_scale\nfloat\nGate LoRA scale\nrequired\n\n\nup_weight\ntorch.Tensor\nUp-projection weight\nrequired\n\n\nup_quant\nobject | None\nUp-projection quantization state\nrequired\n\n\nup_A\ntorch.Tensor | None\nUp-projection LoRA A matrix\nrequired\n\n\nup_B\ntorch.Tensor | None\nUp-projection LoRA B matrix\nrequired\n\n\nup_scale\nfloat\nUp-projection LoRA scale\nrequired\n\n\ndown_weight\ntorch.Tensor\nDown-projection weight\nrequired\n\n\ndown_quant\nobject | None\nDown-projection quantization state\nrequired\n\n\ndown_A\ntorch.Tensor | None\nDown-projection LoRA A matrix\nrequired\n\n\ndown_B\ntorch.Tensor | None\nDown-projection LoRA B matrix\nrequired\n\n\ndown_scale\nfloat\nDown-projection LoRA scale\nrequired\n\n\nactivation_fn\nCallable\nForward activation function\nrequired\n\n\nactivation_fn_backward\nCallable\nBackward activation function\nrequired\n\n\ninplace\nbool | None\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput transformed by multi-layer perceptron and activation function\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_O()\nOptimized LoRA implementation for output projection.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA output projection.\n\n\nforward\nForward pass for output projection with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_O.backward(ctx, dY)\nBackward pass computing gradients for LoRA output projection.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\ndY\ntorch.Tensor\nGradient of loss with respect to output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_O.forward(ctx, X, W, W_quant, A, B, S)\nForward pass for output projection with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nW\ntorch.Tensor\nOutput projection weight\nrequired\n\n\nW_quant\nQuantState | None\nWeight quantization state\nrequired\n\n\nA\ntorch.Tensor | None\nLoRA A matrix\nrequired\n\n\nB\ntorch.Tensor | None\nLoRA B matrix\nrequired\n\n\nS\nfloat\nLoRA scaling factor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput projection tensor\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV()\nOptimized LoRA QKV implementation with quantization support.\nImplements efficient computation of query, key, value projections with LoRA,\nsupporting quantization and memory optimization.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA QKV.\n\n\nforward\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_QKV.backward(ctx, q_grad, k_grad, v_grad)\nBackward pass computing gradients for LoRA QKV.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nq_grad\ntorch.Tensor\nGradient for query projection\nrequired\n\n\nk_grad\ntorch.Tensor\nGradient for key projection\nrequired\n\n\nv_grad\ntorch.Tensor\nGradient for value projection\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV.forward(\n ctx,\n X,\n q_weight,\n q_quant,\n q_A,\n q_B,\n q_scale,\n k_weight,\n k_quant,\n k_A,\n k_B,\n k_scale,\n v_weight,\n v_quant,\n v_A,\n v_B,\n v_scale,\n inplace=True,\n)\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nq_weight\ntorch.Tensor\nQuery projection weight\nrequired\n\n\nq_quant\nQuantState | None\nQuery quantization state\nrequired\n\n\nq_A\ntorch.Tensor | None\nQuery LoRA A matrix\nrequired\n\n\nq_B\ntorch.Tensor | None\nQuery LoRA B matrix\nrequired\n\n\nq_scale\nfloat\nQuery LoRA scale\nrequired\n\n\nk_weight\ntorch.Tensor\nKey projection weight\nrequired\n\n\nk_quant\nQuantState | None\nKey quantization state\nrequired\n\n\nk_A\ntorch.Tensor | None\nKey LoRA A matrix\nrequired\n\n\nk_B\ntorch.Tensor | None\nKey LoRA B matrix\nrequired\n\n\nk_scale\nfloat\nKey LoRA scale\nrequired\n\n\nv_weight\ntorch.Tensor\nValue projection weight\nrequired\n\n\nv_quant\nQuantState | None\nValue quantization state\nrequired\n\n\nv_A\ntorch.Tensor | None\nValue LoRA A matrix\nrequired\n\n\nv_B\ntorch.Tensor | None\nValue LoRA B matrix\nrequired\n\n\nv_scale\nfloat\nValue LoRA scale\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\napply_lora_mlp_geglu\nApplies LoRA to MLP layer with GEGLU activation.\n\n\napply_lora_mlp_swiglu\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\napply_lora_o\nApplies LoRA to output projection layer.\n\n\napply_lora_qkv\nApplies LoRA to compute Query, Key, Value projections.\n\n\nget_lora_parameters\nGets LoRA parameters from a projection module.\n\n\nmatmul_lora\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\nkernels.lora.apply_lora_mlp_geglu(self, X, inplace=True)\nApplies LoRA to MLP layer with GEGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with GEGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_mlp_swiglu(self, X, inplace=True)\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with SwiGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_o(self, X)\nApplies LoRA to output projection layer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTransformed output tensor\n\n\n\n\n\n\n\nkernels.lora.apply_lora_qkv(self, X, inplace=True)\nApplies LoRA to compute Query, Key, Value projections.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors\n\n\n\n\n\n\n\nkernels.lora.get_lora_parameters(proj)\nGets LoRA parameters from a projection module.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nproj\nnn.Module\nThe projection module to extract parameters from.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nA tuple containing the base weight matrix, quantization state, LoRA A matrix,\n\n\n\nQuantState | None\nLoRA B matrix, and scaling factor. States and matrices may be None if not\n\n\n\ntorch.Tensor | None\navailable.\n\n\n\n\n\n\n\nkernels.lora.matmul_lora(X, W, W_quant, A, B, s, out=None)\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor [*, in_features]\nrequired\n\n\nW\ntorch.Tensor\nBase weight matrix [out_features, in_features]\nrequired\n\n\nW_quant\nQuantState\nQuantization state for W\nrequired\n\n\nA\ntorch.Tensor\nLoRA A matrix [rank, in_features]\nrequired\n\n\nB\ntorch.Tensor\nLoRA B matrix [out_features, rank]\nrequired\n\n\ns\nfloat\nLoRA scaling factor\nrequired\n\n\nout\ntorch.Tensor | None\nOptional output tensor for inplace operations\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nResult of X @ W + X @ A @ B" }, { - "objectID": "docs/api/monkeypatch.attention.mllama.html#classes", - "href": "docs/api/monkeypatch.attention.mllama.html#classes", - "title": "monkeypatch.attention.mllama", + "objectID": "docs/api/kernels.lora.html#classes", + "href": "docs/api/kernels.lora.html#classes", + "title": "kernels.lora", "section": "", - "text": "Name\nDescription\n\n\n\n\nMllamaTextCrossFlashAttention2\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\n\n\nMllamaTextSelfFlashAttention2\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\n\n\n\n\n\nmonkeypatch.attention.mllama.MllamaTextCrossFlashAttention2(\n self,\n *args,\n **kwargs,\n)\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\nimplements the forward pass using Flash Attention for improved performance.\n\n\n\nmonkeypatch.attention.mllama.MllamaTextSelfFlashAttention2(\n self,\n config,\n layer_idx,\n *args,\n **kwargs,\n)\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\nimplements the forward pass using Flash Attention for improved performance." + "text": "Name\nDescription\n\n\n\n\nLoRA_MLP\nOptimized LoRA MLP implementation.\n\n\nLoRA_O\nOptimized LoRA implementation for output projection.\n\n\nLoRA_QKV\nOptimized LoRA QKV implementation with quantization support.\n\n\n\n\n\nkernels.lora.LoRA_MLP()\nOptimized LoRA MLP implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nPerforms backward pass computation for LoRA MLP.\n\n\nforward\nForward pass for LoRA MLP.\n\n\n\n\n\nkernels.lora.LoRA_MLP.backward(ctx, grad_output)\nPerforms backward pass computation for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nContext object storing tensors saved during forward pass\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to layer output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor | None\nTuple containing gradients for all inputs from forward pass:\n\n\n\nNone\n- Input gradient tensor (or None)\n\n\n\nNone\n- None for weights/quantization states\n\n\n\ntorch.Tensor | None\n- LoRA A/B matrix gradients (or None)\n\n\n\ntorch.Tensor | None\n- None for scaling factors\n\n\n\nNone\n- None for activation functions and flags\n\n\n\n\n\n\n\nkernels.lora.LoRA_MLP.forward(\n ctx,\n X,\n gate_weight,\n gate_quant,\n gate_A,\n gate_B,\n gate_scale,\n up_weight,\n up_quant,\n up_A,\n up_B,\n up_scale,\n down_weight,\n down_quant,\n down_A,\n down_B,\n down_scale,\n activation_fn,\n activation_fn_backward,\n inplace=True,\n)\nForward pass for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\n\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput features\nrequired\n\n\ngate_weight\ntorch.Tensor\nGate projection weight\nrequired\n\n\ngate_quant\nobject | None\nGate quantization state\nrequired\n\n\ngate_A\ntorch.Tensor | None\nGate LoRA A matrix\nrequired\n\n\ngate_B\ntorch.Tensor | None\nGate LoRA B matrix\nrequired\n\n\ngate_scale\nfloat\nGate LoRA scale\nrequired\n\n\nup_weight\ntorch.Tensor\nUp-projection weight\nrequired\n\n\nup_quant\nobject | None\nUp-projection quantization state\nrequired\n\n\nup_A\ntorch.Tensor | None\nUp-projection LoRA A matrix\nrequired\n\n\nup_B\ntorch.Tensor | None\nUp-projection LoRA B matrix\nrequired\n\n\nup_scale\nfloat\nUp-projection LoRA scale\nrequired\n\n\ndown_weight\ntorch.Tensor\nDown-projection weight\nrequired\n\n\ndown_quant\nobject | None\nDown-projection quantization state\nrequired\n\n\ndown_A\ntorch.Tensor | None\nDown-projection LoRA A matrix\nrequired\n\n\ndown_B\ntorch.Tensor | None\nDown-projection LoRA B matrix\nrequired\n\n\ndown_scale\nfloat\nDown-projection LoRA scale\nrequired\n\n\nactivation_fn\nCallable\nForward activation function\nrequired\n\n\nactivation_fn_backward\nCallable\nBackward activation function\nrequired\n\n\ninplace\nbool | None\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput transformed by multi-layer perceptron and activation function\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_O()\nOptimized LoRA implementation for output projection.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA output projection.\n\n\nforward\nForward pass for output projection with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_O.backward(ctx, dY)\nBackward pass computing gradients for LoRA output projection.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\ndY\ntorch.Tensor\nGradient of loss with respect to output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_O.forward(ctx, X, W, W_quant, A, B, S)\nForward pass for output projection with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nW\ntorch.Tensor\nOutput projection weight\nrequired\n\n\nW_quant\nQuantState | None\nWeight quantization state\nrequired\n\n\nA\ntorch.Tensor | None\nLoRA A matrix\nrequired\n\n\nB\ntorch.Tensor | None\nLoRA B matrix\nrequired\n\n\nS\nfloat\nLoRA scaling factor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput projection tensor\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV()\nOptimized LoRA QKV implementation with quantization support.\nImplements efficient computation of query, key, value projections with LoRA,\nsupporting quantization and memory optimization.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA QKV.\n\n\nforward\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_QKV.backward(ctx, q_grad, k_grad, v_grad)\nBackward pass computing gradients for LoRA QKV.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nq_grad\ntorch.Tensor\nGradient for query projection\nrequired\n\n\nk_grad\ntorch.Tensor\nGradient for key projection\nrequired\n\n\nv_grad\ntorch.Tensor\nGradient for value projection\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV.forward(\n ctx,\n X,\n q_weight,\n q_quant,\n q_A,\n q_B,\n q_scale,\n k_weight,\n k_quant,\n k_A,\n k_B,\n k_scale,\n v_weight,\n v_quant,\n v_A,\n v_B,\n v_scale,\n inplace=True,\n)\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nq_weight\ntorch.Tensor\nQuery projection weight\nrequired\n\n\nq_quant\nQuantState | None\nQuery quantization state\nrequired\n\n\nq_A\ntorch.Tensor | None\nQuery LoRA A matrix\nrequired\n\n\nq_B\ntorch.Tensor | None\nQuery LoRA B matrix\nrequired\n\n\nq_scale\nfloat\nQuery LoRA scale\nrequired\n\n\nk_weight\ntorch.Tensor\nKey projection weight\nrequired\n\n\nk_quant\nQuantState | None\nKey quantization state\nrequired\n\n\nk_A\ntorch.Tensor | None\nKey LoRA A matrix\nrequired\n\n\nk_B\ntorch.Tensor | None\nKey LoRA B matrix\nrequired\n\n\nk_scale\nfloat\nKey LoRA scale\nrequired\n\n\nv_weight\ntorch.Tensor\nValue projection weight\nrequired\n\n\nv_quant\nQuantState | None\nValue quantization state\nrequired\n\n\nv_A\ntorch.Tensor | None\nValue LoRA A matrix\nrequired\n\n\nv_B\ntorch.Tensor | None\nValue LoRA B matrix\nrequired\n\n\nv_scale\nfloat\nValue LoRA scale\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors" }, { - "objectID": "docs/api/core.chat.format.chatml.html", - "href": "docs/api/core.chat.format.chatml.html", - "title": "core.chat.format.chatml", + "objectID": "docs/api/kernels.lora.html#functions", + "href": "docs/api/kernels.lora.html#functions", + "title": "kernels.lora", "section": "", - "text": "core.chat.format.chatml\ncore.chat.format.chatml\nChatML transformation functions for MessageContents" + "text": "Name\nDescription\n\n\n\n\napply_lora_mlp_geglu\nApplies LoRA to MLP layer with GEGLU activation.\n\n\napply_lora_mlp_swiglu\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\napply_lora_o\nApplies LoRA to output projection layer.\n\n\napply_lora_qkv\nApplies LoRA to compute Query, Key, Value projections.\n\n\nget_lora_parameters\nGets LoRA parameters from a projection module.\n\n\nmatmul_lora\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\nkernels.lora.apply_lora_mlp_geglu(self, X, inplace=True)\nApplies LoRA to MLP layer with GEGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with GEGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_mlp_swiglu(self, X, inplace=True)\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with SwiGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_o(self, X)\nApplies LoRA to output projection layer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTransformed output tensor\n\n\n\n\n\n\n\nkernels.lora.apply_lora_qkv(self, X, inplace=True)\nApplies LoRA to compute Query, Key, Value projections.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors\n\n\n\n\n\n\n\nkernels.lora.get_lora_parameters(proj)\nGets LoRA parameters from a projection module.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nproj\nnn.Module\nThe projection module to extract parameters from.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nA tuple containing the base weight matrix, quantization state, LoRA A matrix,\n\n\n\nQuantState | None\nLoRA B matrix, and scaling factor. States and matrices may be None if not\n\n\n\ntorch.Tensor | None\navailable.\n\n\n\n\n\n\n\nkernels.lora.matmul_lora(X, W, W_quant, A, B, s, out=None)\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor [*, in_features]\nrequired\n\n\nW\ntorch.Tensor\nBase weight matrix [out_features, in_features]\nrequired\n\n\nW_quant\nQuantState\nQuantization state for W\nrequired\n\n\nA\ntorch.Tensor\nLoRA A matrix [rank, in_features]\nrequired\n\n\nB\ntorch.Tensor\nLoRA B matrix [out_features, rank]\nrequired\n\n\ns\nfloat\nLoRA scaling factor\nrequired\n\n\nout\ntorch.Tensor | None\nOptional output tensor for inplace operations\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nResult of X @ W + X @ A @ B" }, { - "objectID": "docs/api/prompt_strategies.alpaca_instruct.html", - "href": "docs/api/prompt_strategies.alpaca_instruct.html", - "title": "prompt_strategies.alpaca_instruct", + "objectID": "docs/api/utils.callbacks.perplexity.html", + "href": "docs/api/utils.callbacks.perplexity.html", + "title": "utils.callbacks.perplexity", "section": "", - "text": "prompt_strategies.alpaca_instruct\nprompt_strategies.alpaca_instruct\nModule loading the AlpacaInstructPromptTokenizingStrategy class" + "text": "utils.callbacks.perplexity\ncallback to calculate perplexity as an evaluation metric.\n\n\n\n\n\nName\nDescription\n\n\n\n\nPerplexity\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity(self, tokenizer, max_seq_len, stride=512)\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\nThis is a custom variant that doesn’t re-tokenize the input or re-load the model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncompute\nCompute perplexity in a fixed length sliding window across the sequence.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity.compute(model, references=None)\nCompute perplexity in a fixed length sliding window across the sequence." }, { - "objectID": "docs/api/common.datasets.html", - "href": "docs/api/common.datasets.html", - "title": "common.datasets", + "objectID": "docs/api/utils.callbacks.perplexity.html#classes", + "href": "docs/api/utils.callbacks.perplexity.html#classes", + "title": "utils.callbacks.perplexity", "section": "", - "text": "common.datasets\nDataset loading utilities.\n\n\n\n\n\nName\nDescription\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and validation datasets and metadata.\n\n\n\n\n\ncommon.datasets.TrainDatasetMeta(\n self,\n train_dataset,\n eval_dataset=None,\n total_num_steps=None,\n)\nDataclass with fields for training and validation datasets and metadata.\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nload_datasets\nLoads one or more training or evaluation datasets, calling\n\n\nload_preference_datasets\nLoads one or more training or evaluation datasets for RL training using paired\n\n\nsample_dataset\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\ncommon.datasets.load_datasets(cfg, cli_args=None, debug=False)\nLoads one or more training or evaluation datasets, calling\naxolotl.utils.data.prepare_dataset. Optionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs | TrainerCliArgs | None\nCommand-specific CLI arguments.\nNone\n\n\ndebug\nbool\nWhether to print out tokenization of sample\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.load_preference_datasets(cfg, cli_args)\nLoads one or more training or evaluation datasets for RL training using paired\npreference data, calling axolotl.utils.data.rl.load_prepare_preference_datasets.\nOptionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nUnion[PreprocessCliArgs, TrainerCliArgs]\nCommand-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.sample_dataset(dataset, num_samples)\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nDataset\nDataset.\nrequired\n\n\nnum_samples\nint\nNumber of samples to return.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDataset\nRandom sample (with replacement) of examples in dataset." + "text": "Name\nDescription\n\n\n\n\nPerplexity\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity(self, tokenizer, max_seq_len, stride=512)\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\nThis is a custom variant that doesn’t re-tokenize the input or re-load the model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncompute\nCompute perplexity in a fixed length sliding window across the sequence.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity.compute(model, references=None)\nCompute perplexity in a fixed length sliding window across the sequence." }, { - "objectID": "docs/api/common.datasets.html#classes", - "href": "docs/api/common.datasets.html#classes", - "title": "common.datasets", + "objectID": "docs/api/utils.schemas.training.html", + "href": "docs/api/utils.schemas.training.html", + "title": "utils.schemas.training", "section": "", - "text": "Name\nDescription\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and validation datasets and metadata.\n\n\n\n\n\ncommon.datasets.TrainDatasetMeta(\n self,\n train_dataset,\n eval_dataset=None,\n total_num_steps=None,\n)\nDataclass with fields for training and validation datasets and metadata." + "text": "utils.schemas.training\nPydantic models for training hyperparameters\n\n\n\n\n\nName\nDescription\n\n\n\n\nHyperparametersConfig\nTraining hyperparams configuration subset\n\n\nLrGroup\nCustom learning rate group configuration\n\n\n\n\n\nutils.schemas.training.HyperparametersConfig()\nTraining hyperparams configuration subset\n\n\n\nutils.schemas.training.LrGroup()\nCustom learning rate group configuration" }, { - "objectID": "docs/api/common.datasets.html#functions", - "href": "docs/api/common.datasets.html#functions", - "title": "common.datasets", + "objectID": "docs/api/utils.schemas.training.html#classes", + "href": "docs/api/utils.schemas.training.html#classes", + "title": "utils.schemas.training", "section": "", - "text": "Name\nDescription\n\n\n\n\nload_datasets\nLoads one or more training or evaluation datasets, calling\n\n\nload_preference_datasets\nLoads one or more training or evaluation datasets for RL training using paired\n\n\nsample_dataset\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\ncommon.datasets.load_datasets(cfg, cli_args=None, debug=False)\nLoads one or more training or evaluation datasets, calling\naxolotl.utils.data.prepare_dataset. Optionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs | TrainerCliArgs | None\nCommand-specific CLI arguments.\nNone\n\n\ndebug\nbool\nWhether to print out tokenization of sample\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.load_preference_datasets(cfg, cli_args)\nLoads one or more training or evaluation datasets for RL training using paired\npreference data, calling axolotl.utils.data.rl.load_prepare_preference_datasets.\nOptionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nUnion[PreprocessCliArgs, TrainerCliArgs]\nCommand-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.sample_dataset(dataset, num_samples)\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nDataset\nDataset.\nrequired\n\n\nnum_samples\nint\nNumber of samples to return.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDataset\nRandom sample (with replacement) of examples in dataset." + "text": "Name\nDescription\n\n\n\n\nHyperparametersConfig\nTraining hyperparams configuration subset\n\n\nLrGroup\nCustom learning rate group configuration\n\n\n\n\n\nutils.schemas.training.HyperparametersConfig()\nTraining hyperparams configuration subset\n\n\n\nutils.schemas.training.LrGroup()\nCustom learning rate group configuration" }, { - "objectID": "docs/api/core.datasets.transforms.chat_builder.html", - "href": "docs/api/core.datasets.transforms.chat_builder.html", - "title": "core.datasets.transforms.chat_builder", + "objectID": "docs/api/prompt_strategies.dpo.user_defined.html", + "href": "docs/api/prompt_strategies.dpo.user_defined.html", + "title": "prompt_strategies.dpo.user_defined", "section": "", - "text": "core.datasets.transforms.chat_builder\nThis module contains a function that builds a transform that takes a row from the dataset and converts it to a Chat.\n\n\n\n\n\nName\nDescription\n\n\n\n\nchat_message_transform_builder\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\ncore.datasets.transforms.chat_builder.chat_message_transform_builder(\n train_on_inputs=False,\n conversations_field='conversations',\n message_field_role=['role', 'from'],\n message_field_content=['value', 'text', 'content'],\n message_field_training=['train', 'weight'],\n)\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrain_on_inputs\nbool\nIf True, the transform will train on the inputs. If False, the transform will train on the targets. Defaults to False.\nFalse\n\n\nconversations_field\nstr\nThe field name of the conversations. Defaults to “conversations”.\n'conversations'\n\n\nmessage_field_role\nstr | list[str]\nThe field name of the role. Defaults to “role”.\n['role', 'from']\n\n\nmessage_field_content\nstr | list[str]\nThe field name of the message content. Defaults to “content”.\n['value', 'text', 'content']\n\n\nmessage_field_training\nstr | list[str]\nThe field name of the train/weight. Defaults to “weight”.\n['train', 'weight']\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nCallable\n\nA function that takes a list of conversations and returns a list of messages." + "text": "prompt_strategies.dpo.user_defined\nprompt_strategies.dpo.user_defined\nUser-defined DPO strategies" }, { - "objectID": "docs/api/core.datasets.transforms.chat_builder.html#functions", - "href": "docs/api/core.datasets.transforms.chat_builder.html#functions", - "title": "core.datasets.transforms.chat_builder", + "objectID": "docs/api/utils.samplers.multipack.html", + "href": "docs/api/utils.samplers.multipack.html", + "title": "utils.samplers.multipack", "section": "", - "text": "Name\nDescription\n\n\n\n\nchat_message_transform_builder\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\ncore.datasets.transforms.chat_builder.chat_message_transform_builder(\n train_on_inputs=False,\n conversations_field='conversations',\n message_field_role=['role', 'from'],\n message_field_content=['value', 'text', 'content'],\n message_field_training=['train', 'weight'],\n)\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrain_on_inputs\nbool\nIf True, the transform will train on the inputs. If False, the transform will train on the targets. Defaults to False.\nFalse\n\n\nconversations_field\nstr\nThe field name of the conversations. Defaults to “conversations”.\n'conversations'\n\n\nmessage_field_role\nstr | list[str]\nThe field name of the role. Defaults to “role”.\n['role', 'from']\n\n\nmessage_field_content\nstr | list[str]\nThe field name of the message content. Defaults to “content”.\n['value', 'text', 'content']\n\n\nmessage_field_training\nstr | list[str]\nThe field name of the train/weight. Defaults to “weight”.\n['train', 'weight']\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nCallable\n\nA function that takes a list of conversations and returns a list of messages." + "text": "utils.samplers.multipack\nMultipack Batch Sampler - An efficient batch sampler for packing variable-length sequences\ninto fixed-capacity batches to optimize memory usage and training throughput.\n\n\n\n\n\nName\nDescription\n\n\n\n\nMultipackBatchSampler\nBatch sampler class for efficient packing of variable-length sequences\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler(\n self,\n sampler,\n batch_size,\n batch_max_len,\n lengths,\n packing_efficiency_estimate=1.0,\n drop_last=False,\n num_count_samples=16,\n sequential=False,\n group_size=100000,\n bin_size=200,\n num_processes=None,\n safe_mode=True,\n **kwargs,\n)\nBatch sampler class for efficient packing of variable-length sequences\nThis sampler packs sequences into fixed-capacity bins (batches) to maximize\nGPU memory utilization and training throughput by reducing padding.\nIt supports both parallel packing (using FFD algorithm) and\nsequential packing (preserving original sequence order).\n\n\n\n\n\nName\nDescription\n\n\n\n\nefficiency\nCalculate the packing efficiency (ratio of tokens used to total token slots)\n\n\ngather_efficiency\nGather and synchronize packing efficiency estimates across all distributed ranks\n\n\ngather_len_batches\nGather and synchronize batch counts across all distributed ranks\n\n\ngenerate_batches\nGenerate packed batches for training\n\n\nset_epoch\nSet the epoch number, used for reproducible shuffling across epochs\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.efficiency()\nCalculate the packing efficiency (ratio of tokens used to total token slots)\nHigher is better - 1.0 would mean perfect packing with no wasted space\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_efficiency()\nGather and synchronize packing efficiency estimates across all distributed ranks\nReturns a conservative efficiency estimate based on the measurements\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_len_batches(num)\nGather and synchronize batch counts across all distributed ranks\nReturns the minimum number of batches available on any rank\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.generate_batches(set_stats=False)\nGenerate packed batches for training\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nset_stats\n\nWhether to update efficiency statistics\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of batches, where each batch contains multiple bins,\n\n\n\n\nand each bin contains multiple sequence indices\n\n\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.set_epoch(epoch)\nSet the epoch number, used for reproducible shuffling across epochs\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nallocate_sequentially\nSequential allocator that preserves example order\n\n\nffd_check\nFirst-fit-decreasing bin packing algorithm check\n\n\npack_group\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\npack_parallel\nPack sequences into bins using parallel processing\n\n\n\n\n\nutils.samplers.multipack.allocate_sequentially(\n sequence_lengths,\n rank,\n bin_capacity,\n num_ranks,\n)\nSequential allocator that preserves example order\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nThe lengths of all examples\nrequired\n\n\nrank\nint\nThe current rank (for distributed training)\nrequired\n\n\nbin_capacity\nint\nThe capacity of each bin (maximum sequence length)\nrequired\n\n\nnum_ranks\nint\nNumber of ranks (processes/GPUs)\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nrank_batches\n\nList of batches for the current rank\n\n\ntotal_tokens_used\n\nNumber of actual example tokens\n\n\ntotal_token_slots\n\nMaximum theoretical number of example tokens (number of bins * bin capacity)\n\n\n\n\n\n\n\nutils.samplers.multipack.ffd_check(sequence_lengths, bin_capacity, num_bins)\nFirst-fit-decreasing bin packing algorithm check\nChecks if sequences with the given lengths could fit in the specified number of bins\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nnum_bins\nint\nNumber of bins available\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nTrue if all sequences can be packed, False otherwise\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_group(\n sequence_lengths,\n group_offset,\n bin_capacity,\n max_bins,\n bin_size,\n safe_mode=True,\n)\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\ngroup_offset\nint\nOffset to apply to indices when returning results\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nmax_bins\nint\nMaximum number of bins to use\nrequired\n\n\nbin_size\nint\nMaximum number of sequences per bin\nrequired\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of bins, where each bin contains indices of sequences assigned to it\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_parallel(\n sequence_lengths,\n bin_capacity,\n group_size,\n bin_size,\n num_processes=None,\n safe_mode=True,\n mp_start_method='spawn',\n)\nPack sequences into bins using parallel processing\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin as total number of tokens\nrequired\n\n\ngroup_size\nint\nNumber of sequences to process in each group\nrequired\n\n\nbin_size\nint\nMaximum number of bins to use\nrequired\n\n\nnum_processes\nint | None\nNumber of parallel processes to use\nNone\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\nmp_start_method\nstr | None\nMultiprocessing start method (‘fork’, ‘spawn’, ‘forkserver’). ‘spawn’ is often safer with Numba/PyTorch. Set to None to use system default.\n'spawn'\n\n\n\nReturns:\nList of bins, where each bin contains indices of sequences assigned to it" }, { - "objectID": "docs/api/cli.vllm_serve.html", - "href": "docs/api/cli.vllm_serve.html", - "title": "cli.vllm_serve", + "objectID": "docs/api/utils.samplers.multipack.html#classes", + "href": "docs/api/utils.samplers.multipack.html#classes", + "title": "utils.samplers.multipack", "section": "", - "text": "cli.vllm_serve\nCLI to start the vllm server for online RL\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_vllm_serve\nStarts the VLLM server for serving LLM models used for online RL\n\n\n\n\n\ncli.vllm_serve.do_vllm_serve(config, cli_args)\nStarts the VLLM server for serving LLM models used for online RL\nArgs\n:param cfg: Parsed doct of the YAML config\n:param cli_args: dict of additional command-line arguments of type VllmServeCliArgs\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nprocess_id\n\nthe process id of the started VLLM server" + "text": "Name\nDescription\n\n\n\n\nMultipackBatchSampler\nBatch sampler class for efficient packing of variable-length sequences\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler(\n self,\n sampler,\n batch_size,\n batch_max_len,\n lengths,\n packing_efficiency_estimate=1.0,\n drop_last=False,\n num_count_samples=16,\n sequential=False,\n group_size=100000,\n bin_size=200,\n num_processes=None,\n safe_mode=True,\n **kwargs,\n)\nBatch sampler class for efficient packing of variable-length sequences\nThis sampler packs sequences into fixed-capacity bins (batches) to maximize\nGPU memory utilization and training throughput by reducing padding.\nIt supports both parallel packing (using FFD algorithm) and\nsequential packing (preserving original sequence order).\n\n\n\n\n\nName\nDescription\n\n\n\n\nefficiency\nCalculate the packing efficiency (ratio of tokens used to total token slots)\n\n\ngather_efficiency\nGather and synchronize packing efficiency estimates across all distributed ranks\n\n\ngather_len_batches\nGather and synchronize batch counts across all distributed ranks\n\n\ngenerate_batches\nGenerate packed batches for training\n\n\nset_epoch\nSet the epoch number, used for reproducible shuffling across epochs\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.efficiency()\nCalculate the packing efficiency (ratio of tokens used to total token slots)\nHigher is better - 1.0 would mean perfect packing with no wasted space\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_efficiency()\nGather and synchronize packing efficiency estimates across all distributed ranks\nReturns a conservative efficiency estimate based on the measurements\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_len_batches(num)\nGather and synchronize batch counts across all distributed ranks\nReturns the minimum number of batches available on any rank\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.generate_batches(set_stats=False)\nGenerate packed batches for training\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nset_stats\n\nWhether to update efficiency statistics\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of batches, where each batch contains multiple bins,\n\n\n\n\nand each bin contains multiple sequence indices\n\n\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.set_epoch(epoch)\nSet the epoch number, used for reproducible shuffling across epochs" }, { - "objectID": "docs/api/cli.vllm_serve.html#functions", - "href": "docs/api/cli.vllm_serve.html#functions", - "title": "cli.vllm_serve", + "objectID": "docs/api/utils.samplers.multipack.html#functions", + "href": "docs/api/utils.samplers.multipack.html#functions", + "title": "utils.samplers.multipack", "section": "", - "text": "Name\nDescription\n\n\n\n\ndo_vllm_serve\nStarts the VLLM server for serving LLM models used for online RL\n\n\n\n\n\ncli.vllm_serve.do_vllm_serve(config, cli_args)\nStarts the VLLM server for serving LLM models used for online RL\nArgs\n:param cfg: Parsed doct of the YAML config\n:param cli_args: dict of additional command-line arguments of type VllmServeCliArgs\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nprocess_id\n\nthe process id of the started VLLM server" + "text": "Name\nDescription\n\n\n\n\nallocate_sequentially\nSequential allocator that preserves example order\n\n\nffd_check\nFirst-fit-decreasing bin packing algorithm check\n\n\npack_group\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\npack_parallel\nPack sequences into bins using parallel processing\n\n\n\n\n\nutils.samplers.multipack.allocate_sequentially(\n sequence_lengths,\n rank,\n bin_capacity,\n num_ranks,\n)\nSequential allocator that preserves example order\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nThe lengths of all examples\nrequired\n\n\nrank\nint\nThe current rank (for distributed training)\nrequired\n\n\nbin_capacity\nint\nThe capacity of each bin (maximum sequence length)\nrequired\n\n\nnum_ranks\nint\nNumber of ranks (processes/GPUs)\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nrank_batches\n\nList of batches for the current rank\n\n\ntotal_tokens_used\n\nNumber of actual example tokens\n\n\ntotal_token_slots\n\nMaximum theoretical number of example tokens (number of bins * bin capacity)\n\n\n\n\n\n\n\nutils.samplers.multipack.ffd_check(sequence_lengths, bin_capacity, num_bins)\nFirst-fit-decreasing bin packing algorithm check\nChecks if sequences with the given lengths could fit in the specified number of bins\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nnum_bins\nint\nNumber of bins available\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nTrue if all sequences can be packed, False otherwise\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_group(\n sequence_lengths,\n group_offset,\n bin_capacity,\n max_bins,\n bin_size,\n safe_mode=True,\n)\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\ngroup_offset\nint\nOffset to apply to indices when returning results\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nmax_bins\nint\nMaximum number of bins to use\nrequired\n\n\nbin_size\nint\nMaximum number of sequences per bin\nrequired\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of bins, where each bin contains indices of sequences assigned to it\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_parallel(\n sequence_lengths,\n bin_capacity,\n group_size,\n bin_size,\n num_processes=None,\n safe_mode=True,\n mp_start_method='spawn',\n)\nPack sequences into bins using parallel processing\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin as total number of tokens\nrequired\n\n\ngroup_size\nint\nNumber of sequences to process in each group\nrequired\n\n\nbin_size\nint\nMaximum number of bins to use\nrequired\n\n\nnum_processes\nint | None\nNumber of parallel processes to use\nNone\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\nmp_start_method\nstr | None\nMultiprocessing start method (‘fork’, ‘spawn’, ‘forkserver’). ‘spawn’ is often safer with Numba/PyTorch. Set to None to use system default.\n'spawn'\n\n\n\nReturns:\nList of bins, where each bin contains indices of sequences assigned to it" }, { - "objectID": "docs/api/cli.config.html", - "href": "docs/api/cli.config.html", - "title": "cli.config", + "objectID": "docs/api/utils.collators.mamba.html", + "href": "docs/api/utils.collators.mamba.html", + "title": "utils.collators.mamba", "section": "", - "text": "cli.config\nConfiguration loading and processing.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncheck_remote_config\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\n\n\nchoose_config\nHelper method for choosing a axolotl config YAML file (considering only files\n\n\nload_cfg\nLoads the axolotl configuration stored at config, validates it, and performs\n\n\nprepare_plugins\nRegisters the plugins for the given configuration.\n\n\n\n\n\ncli.config.check_remote_config(config)\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\nfor it and parse its content, first as JSON, then as YAML (YAML is preferred).\nFinally, the parsed content is written to a local file and its path is returned.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[str, Path]\nHTTPS URL to a YAML or JSON file.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nUnion[str, Path]\nEither the original config if it’s not a valid HTTPS URL, or the path to the\n\n\n\nUnion[str, Path]\ndownloaded remote config.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the remote configuration is neither valid JSON or YAML.\n\n\n\nRuntimeError\nIf some request-related exception occurs from the file download.\n\n\n\nException\nCatch-all for any other exception.\n\n\n\n\n\n\n\ncli.config.choose_config(path)\nHelper method for choosing a axolotl config YAML file (considering only files\nending with .yml or .yaml). If more than one config file exists in the passed\npath, the user is prompted to choose one.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\npath\nPath\nDirectory in which config file(s) are stored.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to either (1) the sole YAML file, or (2) if more than one YAML files exist,\n\n\n\nstr\nthe user-selected YAML file.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf no YAML files are found in the given path.\n\n\n\n\n\n\n\ncli.config.load_cfg(config=Path('examples/'), **kwargs)\nLoads the axolotl configuration stored at config, validates it, and performs\nvarious setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr | Path | DictDefault\nPath (local or remote) to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDictDefault\nDictDefault mapping configuration keys to values.\n\n\n\n\n\n\n\ncli.config.prepare_plugins(cfg)\nRegisters the plugins for the given configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" + "text": "utils.collators.mamba\ncollators for Mamba\n\n\n\n\n\nName\nDescription\n\n\n\n\nMambaDataCollator\nCollator for State Space Models (Mamba)\n\n\n\n\n\nutils.collators.mamba.MambaDataCollator(self, tokenizer)\nCollator for State Space Models (Mamba)" }, { - "objectID": "docs/api/cli.config.html#functions", - "href": "docs/api/cli.config.html#functions", - "title": "cli.config", + "objectID": "docs/api/utils.collators.mamba.html#classes", + "href": "docs/api/utils.collators.mamba.html#classes", + "title": "utils.collators.mamba", "section": "", - "text": "Name\nDescription\n\n\n\n\ncheck_remote_config\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\n\n\nchoose_config\nHelper method for choosing a axolotl config YAML file (considering only files\n\n\nload_cfg\nLoads the axolotl configuration stored at config, validates it, and performs\n\n\nprepare_plugins\nRegisters the plugins for the given configuration.\n\n\n\n\n\ncli.config.check_remote_config(config)\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\nfor it and parse its content, first as JSON, then as YAML (YAML is preferred).\nFinally, the parsed content is written to a local file and its path is returned.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[str, Path]\nHTTPS URL to a YAML or JSON file.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nUnion[str, Path]\nEither the original config if it’s not a valid HTTPS URL, or the path to the\n\n\n\nUnion[str, Path]\ndownloaded remote config.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the remote configuration is neither valid JSON or YAML.\n\n\n\nRuntimeError\nIf some request-related exception occurs from the file download.\n\n\n\nException\nCatch-all for any other exception.\n\n\n\n\n\n\n\ncli.config.choose_config(path)\nHelper method for choosing a axolotl config YAML file (considering only files\nending with .yml or .yaml). If more than one config file exists in the passed\npath, the user is prompted to choose one.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\npath\nPath\nDirectory in which config file(s) are stored.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to either (1) the sole YAML file, or (2) if more than one YAML files exist,\n\n\n\nstr\nthe user-selected YAML file.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf no YAML files are found in the given path.\n\n\n\n\n\n\n\ncli.config.load_cfg(config=Path('examples/'), **kwargs)\nLoads the axolotl configuration stored at config, validates it, and performs\nvarious setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr | Path | DictDefault\nPath (local or remote) to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDictDefault\nDictDefault mapping configuration keys to values.\n\n\n\n\n\n\n\ncli.config.prepare_plugins(cfg)\nRegisters the plugins for the given configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" + "text": "Name\nDescription\n\n\n\n\nMambaDataCollator\nCollator for State Space Models (Mamba)\n\n\n\n\n\nutils.collators.mamba.MambaDataCollator(self, tokenizer)\nCollator for State Space Models (Mamba)" }, { - "objectID": "docs/api/utils.schemas.trl.html", - "href": "docs/api/utils.schemas.trl.html", - "title": "utils.schemas.trl", + "objectID": "docs/api/cli.merge_sharded_fsdp_weights.html", + "href": "docs/api/cli.merge_sharded_fsdp_weights.html", + "title": "cli.merge_sharded_fsdp_weights", "section": "", - "text": "utils.schemas.trl\nPydantic models for TRL trainer configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nTRLConfig\nInput args for TRL.\n\n\n\n\n\nutils.schemas.trl.TRLConfig()\nInput args for TRL." + "text": "cli.merge_sharded_fsdp_weights\nCLI to merge sharded FSDP model checkpoints into a single combined checkpoint.\n\n\n\n\n\nName\nDescription\n\n\n\n\nBFloat16CastPlanner\nA custom planner to cast tensors to bfloat16 on the fly during loading.\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.BFloat16CastPlanner()\nA custom planner to cast tensors to bfloat16 on the fly during loading.\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\nmerge_fsdp_weights\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.merge_fsdp_weights(\n checkpoint_dir,\n output_path,\n safe_serialization=False,\n remove_checkpoint_dir=False,\n)\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\nSHARDED_STATE_DICT was used for the model. Weights will be saved to {output_path}/model.safetensors if\nsafe_serialization else pytorch_model.bin.\nNote: this is a CPU-bound process.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncheckpoint_dir\nstr\nThe directory containing the FSDP checkpoints (can be either the model or optimizer).\nrequired\n\n\noutput_path\nstr\nThe path to save the merged checkpoint.\nrequired\n\n\nsafe_serialization\nbool, optional, defaults to True\nWhether to save the merged weights with safetensors (recommended).\nFalse\n\n\nremove_checkpoint_dir\nbool, optional, defaults to False\nWhether to remove the checkpoint directory after merging.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf torch version < 2.3.0, or if checkpoint_dir does not exist." }, { - "objectID": "docs/api/utils.schemas.trl.html#classes", - "href": "docs/api/utils.schemas.trl.html#classes", - "title": "utils.schemas.trl", + "objectID": "docs/api/cli.merge_sharded_fsdp_weights.html#classes", + "href": "docs/api/cli.merge_sharded_fsdp_weights.html#classes", + "title": "cli.merge_sharded_fsdp_weights", "section": "", - "text": "Name\nDescription\n\n\n\n\nTRLConfig\nInput args for TRL.\n\n\n\n\n\nutils.schemas.trl.TRLConfig()\nInput args for TRL." + "text": "Name\nDescription\n\n\n\n\nBFloat16CastPlanner\nA custom planner to cast tensors to bfloat16 on the fly during loading.\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.BFloat16CastPlanner()\nA custom planner to cast tensors to bfloat16 on the fly during loading." }, { - "objectID": "docs/api/core.trainers.mamba.html", - "href": "docs/api/core.trainers.mamba.html", - "title": "core.trainers.mamba", + "objectID": "docs/api/cli.merge_sharded_fsdp_weights.html#functions", + "href": "docs/api/cli.merge_sharded_fsdp_weights.html#functions", + "title": "cli.merge_sharded_fsdp_weights", "section": "", - "text": "core.trainers.mamba\nModule for mamba trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlMambaTrainer\nMamba specific trainer to handle loss calculation\n\n\n\n\n\ncore.trainers.mamba.AxolotlMambaTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nMamba specific trainer to handle loss calculation" + "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\nmerge_fsdp_weights\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.merge_fsdp_weights(\n checkpoint_dir,\n output_path,\n safe_serialization=False,\n remove_checkpoint_dir=False,\n)\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\nSHARDED_STATE_DICT was used for the model. Weights will be saved to {output_path}/model.safetensors if\nsafe_serialization else pytorch_model.bin.\nNote: this is a CPU-bound process.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncheckpoint_dir\nstr\nThe directory containing the FSDP checkpoints (can be either the model or optimizer).\nrequired\n\n\noutput_path\nstr\nThe path to save the merged checkpoint.\nrequired\n\n\nsafe_serialization\nbool, optional, defaults to True\nWhether to save the merged weights with safetensors (recommended).\nFalse\n\n\nremove_checkpoint_dir\nbool, optional, defaults to False\nWhether to remove the checkpoint directory after merging.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf torch version < 2.3.0, or if checkpoint_dir does not exist." }, { - "objectID": "docs/api/core.trainers.mamba.html#classes", - "href": "docs/api/core.trainers.mamba.html#classes", - "title": "core.trainers.mamba", + "objectID": "docs/api/utils.callbacks.profiler.html", + "href": "docs/api/utils.callbacks.profiler.html", + "title": "utils.callbacks.profiler", "section": "", - "text": "Name\nDescription\n\n\n\n\nAxolotlMambaTrainer\nMamba specific trainer to handle loss calculation\n\n\n\n\n\ncore.trainers.mamba.AxolotlMambaTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nMamba specific trainer to handle loss calculation" + "text": "utils.callbacks.profiler\nHF Trainer callback for creating pytorch profiling snapshots\n\n\n\n\n\nName\nDescription\n\n\n\n\nPytorchProfilerCallback\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps.\n\n\n\n\n\nutils.callbacks.profiler.PytorchProfilerCallback(self, steps_to_profile=5)\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps." }, { - "objectID": "docs/api/integrations.grokfast.optimizer.html", - "href": "docs/api/integrations.grokfast.optimizer.html", - "title": "integrations.grokfast.optimizer", + "objectID": "docs/api/utils.callbacks.profiler.html#classes", + "href": "docs/api/utils.callbacks.profiler.html#classes", + "title": "utils.callbacks.profiler", "section": "", - "text": "integrations.grokfast.optimizer\nintegrations.grokfast.optimizer" + "text": "Name\nDescription\n\n\n\n\nPytorchProfilerCallback\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps.\n\n\n\n\n\nutils.callbacks.profiler.PytorchProfilerCallback(self, steps_to_profile=5)\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps." }, { - "objectID": "docs/api/core.trainers.dpo.trainer.html", - "href": "docs/api/core.trainers.dpo.trainer.html", - "title": "core.trainers.dpo.trainer", + "objectID": "docs/api/prompt_strategies.stepwise_supervised.html", + "href": "docs/api/prompt_strategies.stepwise_supervised.html", + "title": "prompt_strategies.stepwise_supervised", "section": "", - "text": "core.trainers.dpo.trainer\nDPO trainer for axolotl\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlDPOTrainer\nExtend the base DPOTrainer for axolotl helpers\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer(\n self,\n *args,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base DPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nevaluation_loop\nOverriding built-in evaluation loop to store metrics for each batch.\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer.evaluation_loop(\n dataloader,\n description,\n prediction_loss_only=None,\n ignore_keys=None,\n metric_key_prefix='eval',\n)\nOverriding built-in evaluation loop to store metrics for each batch.\nPrediction/evaluation loop, shared by Trainer.evaluate() and Trainer.predict().\nWorks both with or without labels.\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\nmodel on the Hub. Please refer to ~transformers.Trainer.push_to_hub for more details." + "text": "prompt_strategies.stepwise_supervised\nModule for stepwise datasets, typically including a prompt and reasoning traces,\nand (optionally) per-step, or per-prompt-trace labels for reward modelling.\n\n\n\n\n\nName\nDescription\n\n\n\n\nStepwiseSupervisedPromptTokenizingStrategy\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\n\n\n\n\n\nprompt_strategies.stepwise_supervised.StepwiseSupervisedPromptTokenizingStrategy(\n self,\n tokenizer,\n sequence_len=2048,\n step_separator='\\n',\n max_completion_length=None,\n train_on_last_step_only=False,\n)\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\nThese datasets should include the following columns:\n- prompt: the prompt text\n- completions: a list of n completion steps\n- labels: a list of n labels indicating the “correctness” of each step" }, { - "objectID": "docs/api/core.trainers.dpo.trainer.html#classes", - "href": "docs/api/core.trainers.dpo.trainer.html#classes", - "title": "core.trainers.dpo.trainer", + "objectID": "docs/api/prompt_strategies.stepwise_supervised.html#classes", + "href": "docs/api/prompt_strategies.stepwise_supervised.html#classes", + "title": "prompt_strategies.stepwise_supervised", "section": "", - "text": "Name\nDescription\n\n\n\n\nAxolotlDPOTrainer\nExtend the base DPOTrainer for axolotl helpers\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer(\n self,\n *args,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base DPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nevaluation_loop\nOverriding built-in evaluation loop to store metrics for each batch.\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer.evaluation_loop(\n dataloader,\n description,\n prediction_loss_only=None,\n ignore_keys=None,\n metric_key_prefix='eval',\n)\nOverriding built-in evaluation loop to store metrics for each batch.\nPrediction/evaluation loop, shared by Trainer.evaluate() and Trainer.predict().\nWorks both with or without labels.\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\nmodel on the Hub. Please refer to ~transformers.Trainer.push_to_hub for more details." + "text": "Name\nDescription\n\n\n\n\nStepwiseSupervisedPromptTokenizingStrategy\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\n\n\n\n\n\nprompt_strategies.stepwise_supervised.StepwiseSupervisedPromptTokenizingStrategy(\n self,\n tokenizer,\n sequence_len=2048,\n step_separator='\\n',\n max_completion_length=None,\n train_on_last_step_only=False,\n)\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\nThese datasets should include the following columns:\n- prompt: the prompt text\n- completions: a list of n completion steps\n- labels: a list of n labels indicating the “correctness” of each step" }, { - "objectID": "docs/api/cli.inference.html", - "href": "docs/api/cli.inference.html", - "title": "cli.inference", + "objectID": "docs/api/monkeypatch.trainer_fsdp_optim.html", + "href": "docs/api/monkeypatch.trainer_fsdp_optim.html", + "title": "monkeypatch.trainer_fsdp_optim", "section": "", - "text": "cli.inference\nCLI to run inference on a trained model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\ndo_inference\nRuns inference on the command line in a loop. User input is accepted, a chat template\n\n\ndo_inference_gradio\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n\n\nget_multi_line_input\nGets multi-line input from terminal.\n\n\n\n\n\ncli.inference.do_cli(config=Path('examples/'), gradio=False, **kwargs)\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.inference.do_inference(cfg, cli_args)\nRuns inference on the command line in a loop. User input is accepted, a chat template\nis (optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.do_inference_gradio(cfg, cli_args)\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n(optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.get_multi_line_input()\nGets multi-line input from terminal.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPossibly multi-line, possibly empty stdin input as a string." + "text": "monkeypatch.trainer_fsdp_optim\nfix for FSDP optimizer save in trainer w 4.47.0\n\n\n\n\n\nName\nDescription\n\n\n\n\npatch_training_loop_for_fsdp\nmonkeypatch for fixing the training loop for fsdp with optimizer save\n\n\n\n\n\nmonkeypatch.trainer_fsdp_optim.patch_training_loop_for_fsdp()\nmonkeypatch for fixing the training loop for fsdp with optimizer save" }, { - "objectID": "docs/api/cli.inference.html#functions", - "href": "docs/api/cli.inference.html#functions", - "title": "cli.inference", + "objectID": "docs/api/monkeypatch.trainer_fsdp_optim.html#functions", + "href": "docs/api/monkeypatch.trainer_fsdp_optim.html#functions", + "title": "monkeypatch.trainer_fsdp_optim", "section": "", - "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\ndo_inference\nRuns inference on the command line in a loop. User input is accepted, a chat template\n\n\ndo_inference_gradio\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n\n\nget_multi_line_input\nGets multi-line input from terminal.\n\n\n\n\n\ncli.inference.do_cli(config=Path('examples/'), gradio=False, **kwargs)\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.inference.do_inference(cfg, cli_args)\nRuns inference on the command line in a loop. User input is accepted, a chat template\nis (optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.do_inference_gradio(cfg, cli_args)\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n(optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.get_multi_line_input()\nGets multi-line input from terminal.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPossibly multi-line, possibly empty stdin input as a string." + "text": "Name\nDescription\n\n\n\n\npatch_training_loop_for_fsdp\nmonkeypatch for fixing the training loop for fsdp with optimizer save\n\n\n\n\n\nmonkeypatch.trainer_fsdp_optim.patch_training_loop_for_fsdp()\nmonkeypatch for fixing the training loop for fsdp with optimizer save" }, { - "objectID": "docs/api/prompt_strategies.input_output.html", - "href": "docs/api/prompt_strategies.input_output.html", - "title": "prompt_strategies.input_output", + "objectID": "docs/api/integrations.cut_cross_entropy.args.html", + "href": "docs/api/integrations.cut_cross_entropy.args.html", + "title": "integrations.cut_cross_entropy.args", "section": "", - "text": "prompt_strategies.input_output\nModule for plain input/output prompt pairs\n\n\n\n\n\nName\nDescription\n\n\n\n\nRawInputOutputPrompter\nprompter for raw i/o data\n\n\nRawInputOutputStrategy\nPrompt Strategy class for input/output pairs\n\n\n\n\n\nprompt_strategies.input_output.RawInputOutputPrompter()\nprompter for raw i/o data\n\n\n\nprompt_strategies.input_output.RawInputOutputStrategy(\n self,\n *args,\n eos_token=None,\n **kwargs,\n)\nPrompt Strategy class for input/output pairs" + "text": "integrations.cut_cross_entropy.args\nModule for handling Cut Cross Entropy input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nCutCrossEntropyArgs\nInput args for Cut Cross Entropy.\n\n\n\n\n\nintegrations.cut_cross_entropy.args.CutCrossEntropyArgs()\nInput args for Cut Cross Entropy." }, { - "objectID": "docs/api/prompt_strategies.input_output.html#classes", - "href": "docs/api/prompt_strategies.input_output.html#classes", - "title": "prompt_strategies.input_output", + "objectID": "docs/api/integrations.cut_cross_entropy.args.html#classes", + "href": "docs/api/integrations.cut_cross_entropy.args.html#classes", + "title": "integrations.cut_cross_entropy.args", "section": "", - "text": "Name\nDescription\n\n\n\n\nRawInputOutputPrompter\nprompter for raw i/o data\n\n\nRawInputOutputStrategy\nPrompt Strategy class for input/output pairs\n\n\n\n\n\nprompt_strategies.input_output.RawInputOutputPrompter()\nprompter for raw i/o data\n\n\n\nprompt_strategies.input_output.RawInputOutputStrategy(\n self,\n *args,\n eos_token=None,\n **kwargs,\n)\nPrompt Strategy class for input/output pairs" + "text": "Name\nDescription\n\n\n\n\nCutCrossEntropyArgs\nInput args for Cut Cross Entropy.\n\n\n\n\n\nintegrations.cut_cross_entropy.args.CutCrossEntropyArgs()\nInput args for Cut Cross Entropy." }, { - "objectID": "docs/api/utils.bench.html", - "href": "docs/api/utils.bench.html", - "title": "utils.bench", + "objectID": "docs/api/utils.chat_templates.html", + "href": "docs/api/utils.chat_templates.html", + "title": "utils.chat_templates", "section": "", - "text": "utils.bench\nBenchmarking and measurement utilities\n\n\n\n\n\nName\nDescription\n\n\n\n\ncheck_cuda_device\nwraps a function and returns the default value instead of running the\n\n\n\n\n\nutils.bench.check_cuda_device(default_value)\nwraps a function and returns the default value instead of running the\nwrapped function if cuda isn’t available or the device is auto\n:param default_value:\n:return:" + "text": "utils.chat_templates\nThis module provides functionality for selecting chat templates based on user choices.\nThese templates are used for formatting messages in a conversation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_chat_template\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\nregister_chat_template\nRegisters chat templates.\n\n\n\n\n\nutils.chat_templates.get_chat_template(\n user_choice,\n jinja_template=None,\n tokenizer=None,\n)\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nuser_choice\nstr\nThe user’s choice of template.\nrequired\n\n\njinja_template\nOptional[str]\nThe jinja template string. Defaults to None.\nNone\n\n\ntokenizer\nOptional[PreTrainedTokenizerBase]\nThe tokenizer. Defaults to None.\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nstr\nstr\nThe chosen template string.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the user_choice is not found in the templates.\n\n\n\n\n\n\n\nutils.chat_templates.register_chat_template(template_name, chat_template)\nRegisters chat templates.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntemplate_name\nstr\nThe name of the template.\nrequired\n\n\nchat_template\nstr\nThe template string.\nrequired" }, { - "objectID": "docs/api/utils.bench.html#functions", - "href": "docs/api/utils.bench.html#functions", - "title": "utils.bench", + "objectID": "docs/api/utils.chat_templates.html#functions", + "href": "docs/api/utils.chat_templates.html#functions", + "title": "utils.chat_templates", "section": "", - "text": "Name\nDescription\n\n\n\n\ncheck_cuda_device\nwraps a function and returns the default value instead of running the\n\n\n\n\n\nutils.bench.check_cuda_device(default_value)\nwraps a function and returns the default value instead of running the\nwrapped function if cuda isn’t available or the device is auto\n:param default_value:\n:return:" + "text": "Name\nDescription\n\n\n\n\nget_chat_template\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\nregister_chat_template\nRegisters chat templates.\n\n\n\n\n\nutils.chat_templates.get_chat_template(\n user_choice,\n jinja_template=None,\n tokenizer=None,\n)\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nuser_choice\nstr\nThe user’s choice of template.\nrequired\n\n\njinja_template\nOptional[str]\nThe jinja template string. Defaults to None.\nNone\n\n\ntokenizer\nOptional[PreTrainedTokenizerBase]\nThe tokenizer. Defaults to None.\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nstr\nstr\nThe chosen template string.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the user_choice is not found in the templates.\n\n\n\n\n\n\n\nutils.chat_templates.register_chat_template(template_name, chat_template)\nRegisters chat templates.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntemplate_name\nstr\nThe name of the template.\nrequired\n\n\nchat_template\nstr\nThe template string.\nrequired" }, { - "objectID": "docs/api/core.trainers.relora.html", - "href": "docs/api/core.trainers.relora.html", - "title": "core.trainers.relora", + "objectID": "docs/api/monkeypatch.btlm_attn_hijack_flash.html", + "href": "docs/api/monkeypatch.btlm_attn_hijack_flash.html", + "title": "monkeypatch.btlm_attn_hijack_flash", "section": "", - "text": "core.trainers.relora\nModule for ReLoRA trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nReLoRATrainer\nTrainer subclass that uses the OneCycleLR scheduler\n\n\n\n\n\ncore.trainers.relora.ReLoRATrainer(self, *args, **kwargs)\nTrainer subclass that uses the OneCycleLR scheduler" + "text": "monkeypatch.btlm_attn_hijack_flash\nmonkeypatch.btlm_attn_hijack_flash\nFlash attention monkey patch for cerebras btlm model" }, { - "objectID": "docs/api/core.trainers.relora.html#classes", - "href": "docs/api/core.trainers.relora.html#classes", - "title": "core.trainers.relora", + "objectID": "docs/api/utils.lora.html", + "href": "docs/api/utils.lora.html", + "title": "utils.lora", "section": "", - "text": "Name\nDescription\n\n\n\n\nReLoRATrainer\nTrainer subclass that uses the OneCycleLR scheduler\n\n\n\n\n\ncore.trainers.relora.ReLoRATrainer(self, *args, **kwargs)\nTrainer subclass that uses the OneCycleLR scheduler" + "text": "utils.lora\nmodule to get the state dict of a merged lora model\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_lora_merged_state_dict\nCreate and return a state_dict that has the LoRA deltas\n\n\n\n\n\nutils.lora.get_lora_merged_state_dict(model)\nCreate and return a state_dict that has the LoRA deltas\nmerged into the base model’s weights, without modifying model in place.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\ntorch.nn.Module\nA model that has LoRA/PEFT adapters attached.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndict\ndict\nA state_dict of the merged parameters." }, { - "objectID": "docs/api/integrations.spectrum.args.html", - "href": "docs/api/integrations.spectrum.args.html", - "title": "integrations.spectrum.args", + "objectID": "docs/api/utils.lora.html#functions", + "href": "docs/api/utils.lora.html#functions", + "title": "utils.lora", "section": "", - "text": "integrations.spectrum.args\nModule for handling Spectrum input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nSpectrumArgs\nInput args for Spectrum.\n\n\n\n\n\nintegrations.spectrum.args.SpectrumArgs()\nInput args for Spectrum." + "text": "Name\nDescription\n\n\n\n\nget_lora_merged_state_dict\nCreate and return a state_dict that has the LoRA deltas\n\n\n\n\n\nutils.lora.get_lora_merged_state_dict(model)\nCreate and return a state_dict that has the LoRA deltas\nmerged into the base model’s weights, without modifying model in place.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\ntorch.nn.Module\nA model that has LoRA/PEFT adapters attached.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndict\ndict\nA state_dict of the merged parameters." }, { - "objectID": "docs/api/integrations.spectrum.args.html#classes", - "href": "docs/api/integrations.spectrum.args.html#classes", - "title": "integrations.spectrum.args", + "objectID": "docs/api/prompt_strategies.chat_template.html", + "href": "docs/api/prompt_strategies.chat_template.html", + "title": "prompt_strategies.chat_template", "section": "", - "text": "Name\nDescription\n\n\n\n\nSpectrumArgs\nInput args for Spectrum.\n\n\n\n\n\nintegrations.spectrum.args.SpectrumArgs()\nInput args for Spectrum." + "text": "prompt_strategies.chat_template\nHF Chat Templates prompt strategy\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatTemplatePrompter\nPrompter for HF chat templates\n\n\nChatTemplateStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nStrategyLoader\nLoad chat template strategy based on configuration.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplatePrompter(\n self,\n tokenizer,\n chat_template,\n processor=None,\n max_length=2048,\n message_property_mappings=None,\n message_field_training=None,\n message_field_training_detail=None,\n field_messages='messages',\n field_system='system',\n roles=None,\n drop_system_message=False,\n)\nPrompter for HF chat templates\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs,\n sequence_len,\n roles_to_train=None,\n train_on_eos=None,\n train_on_eot=None,\n eot_tokens=None,\n split_thinking=False,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\n\n\nName\nDescription\n\n\n\n\nfind_first_eot_token\nFind the first EOT token in the input_ids starting from start_idx.\n\n\nfind_turn\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\ntokenize_prompt\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token(\n input_ids,\n start_idx,\n)\nFind the first EOT token in the input_ids starting from start_idx.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_turn(turns, turn_idx)\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt(prompt)\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.StrategyLoader()\nLoad chat template strategy based on configuration." }, { - "objectID": "docs/api/core.trainers.grpo.trainer.html", - "href": "docs/api/core.trainers.grpo.trainer.html", - "title": "core.trainers.grpo.trainer", + "objectID": "docs/api/prompt_strategies.chat_template.html#classes", + "href": "docs/api/prompt_strategies.chat_template.html#classes", + "title": "prompt_strategies.chat_template", "section": "", - "text": "core.trainers.grpo.trainer\nAxolotl GRPO trainers (with and without sequence parallelism handling)\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlGRPOSequenceParallelTrainer\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\nAxolotlGRPOTrainer\nExtend the base GRPOTrainer for axolotl helpers\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer(\n self,\n model,\n reward_funcs,\n args=None,\n train_dataset=None,\n eval_dataset=None,\n processing_class=None,\n reward_processing_classes=None,\n callbacks=None,\n optimizers=(None, None),\n peft_config=None,\n)\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_train_dataloader\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer.get_train_dataloader(\n)\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOTrainer()\nExtend the base GRPOTrainer for axolotl helpers" + "text": "Name\nDescription\n\n\n\n\nChatTemplatePrompter\nPrompter for HF chat templates\n\n\nChatTemplateStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nStrategyLoader\nLoad chat template strategy based on configuration.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplatePrompter(\n self,\n tokenizer,\n chat_template,\n processor=None,\n max_length=2048,\n message_property_mappings=None,\n message_field_training=None,\n message_field_training_detail=None,\n field_messages='messages',\n field_system='system',\n roles=None,\n drop_system_message=False,\n)\nPrompter for HF chat templates\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs,\n sequence_len,\n roles_to_train=None,\n train_on_eos=None,\n train_on_eot=None,\n eot_tokens=None,\n split_thinking=False,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\n\n\nName\nDescription\n\n\n\n\nfind_first_eot_token\nFind the first EOT token in the input_ids starting from start_idx.\n\n\nfind_turn\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\ntokenize_prompt\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token(\n input_ids,\n start_idx,\n)\nFind the first EOT token in the input_ids starting from start_idx.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_turn(turns, turn_idx)\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt(prompt)\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.StrategyLoader()\nLoad chat template strategy based on configuration." }, { - "objectID": "docs/api/core.trainers.grpo.trainer.html#classes", - "href": "docs/api/core.trainers.grpo.trainer.html#classes", - "title": "core.trainers.grpo.trainer", + "objectID": "docs/api/utils.schemas.multimodal.html", + "href": "docs/api/utils.schemas.multimodal.html", + "title": "utils.schemas.multimodal", "section": "", - "text": "Name\nDescription\n\n\n\n\nAxolotlGRPOSequenceParallelTrainer\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\nAxolotlGRPOTrainer\nExtend the base GRPOTrainer for axolotl helpers\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer(\n self,\n model,\n reward_funcs,\n args=None,\n train_dataset=None,\n eval_dataset=None,\n processing_class=None,\n reward_processing_classes=None,\n callbacks=None,\n optimizers=(None, None),\n peft_config=None,\n)\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_train_dataloader\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer.get_train_dataloader(\n)\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOTrainer()\nExtend the base GRPOTrainer for axolotl helpers" + "text": "utils.schemas.multimodal\nPydantic models for multimodal-related configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nMultiModalConfig\nMulti-modal configuration subset\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig()\nMulti-modal configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nconvert_image_resize_algorithm\nConvert the image resize algorithm to a PIL.Image.Resampling enum.\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm(\n image_resize_algorithm,\n)\nConvert the image resize algorithm to a PIL.Image.Resampling enum." }, { - "objectID": "docs/api/monkeypatch.llama_expand_mask.html", - "href": "docs/api/monkeypatch.llama_expand_mask.html", - "title": "monkeypatch.llama_expand_mask", + "objectID": "docs/api/utils.schemas.multimodal.html#classes", + "href": "docs/api/utils.schemas.multimodal.html#classes", + "title": "utils.schemas.multimodal", "section": "", - "text": "monkeypatch.llama_expand_mask\nmonkeypatch.llama_expand_mask\nexpands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf" + "text": "Name\nDescription\n\n\n\n\nMultiModalConfig\nMulti-modal configuration subset\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig()\nMulti-modal configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nconvert_image_resize_algorithm\nConvert the image resize algorithm to a PIL.Image.Resampling enum.\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm(\n image_resize_algorithm,\n)\nConvert the image resize algorithm to a PIL.Image.Resampling enum." }, { - "objectID": "docs/api/utils.schemas.peft.html", - "href": "docs/api/utils.schemas.peft.html", - "title": "utils.schemas.peft", + "objectID": "docs/api/monkeypatch.utils.html", + "href": "docs/api/monkeypatch.utils.html", + "title": "monkeypatch.utils", "section": "", - "text": "utils.schemas.peft\nPydantic models for PEFT-related configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nLoftQConfig\nLoftQ configuration subset\n\n\nLoraConfig\nPeft / LoRA configuration subset\n\n\nPeftConfig\npeftq configuration subset\n\n\nReLoRAConfig\nReLoRA configuration subset\n\n\n\n\n\nutils.schemas.peft.LoftQConfig()\nLoftQ configuration subset\n\n\n\nutils.schemas.peft.LoraConfig()\nPeft / LoRA configuration subset\n\n\n\nutils.schemas.peft.PeftConfig()\npeftq configuration subset\n\n\n\nutils.schemas.peft.ReLoRAConfig()\nReLoRA configuration subset" + "text": "monkeypatch.utils\nShared utils for the monkeypatches\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_cu_seqlens\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\nget_cu_seqlens_from_pos_ids\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\nmask_2d_to_4d\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\n\n\n\n\n\nmonkeypatch.utils.get_cu_seqlens(attn_mask)\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\n\nmonkeypatch.utils.get_cu_seqlens_from_pos_ids(position_ids)\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\n\nmonkeypatch.utils.mask_2d_to_4d(mask, dtype, tgt_len=None)\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\nThis expansion handles packed sequences so that sequences share the same attention mask integer value\nwhen they attend to each other within that sequence.\nThis expansion transforms the mask to lower triangular form to prevent future peeking." }, { - "objectID": "docs/api/utils.schemas.peft.html#classes", - "href": "docs/api/utils.schemas.peft.html#classes", - "title": "utils.schemas.peft", + "objectID": "docs/api/monkeypatch.utils.html#functions", + "href": "docs/api/monkeypatch.utils.html#functions", + "title": "monkeypatch.utils", "section": "", - "text": "Name\nDescription\n\n\n\n\nLoftQConfig\nLoftQ configuration subset\n\n\nLoraConfig\nPeft / LoRA configuration subset\n\n\nPeftConfig\npeftq configuration subset\n\n\nReLoRAConfig\nReLoRA configuration subset\n\n\n\n\n\nutils.schemas.peft.LoftQConfig()\nLoftQ configuration subset\n\n\n\nutils.schemas.peft.LoraConfig()\nPeft / LoRA configuration subset\n\n\n\nutils.schemas.peft.PeftConfig()\npeftq configuration subset\n\n\n\nutils.schemas.peft.ReLoRAConfig()\nReLoRA configuration subset" + "text": "Name\nDescription\n\n\n\n\nget_cu_seqlens\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\nget_cu_seqlens_from_pos_ids\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\nmask_2d_to_4d\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\n\n\n\n\n\nmonkeypatch.utils.get_cu_seqlens(attn_mask)\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\n\nmonkeypatch.utils.get_cu_seqlens_from_pos_ids(position_ids)\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\n\nmonkeypatch.utils.mask_2d_to_4d(mask, dtype, tgt_len=None)\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\nThis expansion handles packed sequences so that sequences share the same attention mask integer value\nwhen they attend to each other within that sequence.\nThis expansion transforms the mask to lower triangular form to prevent future peeking." }, { - "objectID": "docs/api/cli.main.html", - "href": "docs/api/cli.main.html", - "title": "cli.main", + "objectID": "docs/api/prompt_strategies.kto.user_defined.html", + "href": "docs/api/prompt_strategies.kto.user_defined.html", + "title": "prompt_strategies.kto.user_defined", "section": "", - "text": "cli.main\nClick CLI definitions for various axolotl commands.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncli\nAxolotl CLI - Train and fine-tune large language models\n\n\nevaluate\nEvaluate a model.\n\n\nfetch\nFetch example configs or other resources.\n\n\ninference\nRun inference with a trained model.\n\n\nmerge_lora\nMerge trained LoRA adapters into a base model.\n\n\nmerge_sharded_fsdp_weights\nMerge sharded FSDP model weights.\n\n\npreprocess\nPreprocess datasets before training.\n\n\ntrain\nTrain or fine-tune a model.\n\n\n\n\n\ncli.main.cli()\nAxolotl CLI - Train and fine-tune large language models\n\n\n\ncli.main.evaluate(config, accelerate, **kwargs)\nEvaluate a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.fetch(directory, dest)\nFetch example configs or other resources.\nAvailable directories:\n- examples: Example configuration files\n- deepspeed_configs: DeepSpeed configuration files\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndirectory\nstr\nOne of examples, deepspeed_configs.\nrequired\n\n\ndest\nOptional[str]\nOptional destination directory.\nrequired\n\n\n\n\n\n\n\ncli.main.inference(config, accelerate, gradio, **kwargs)\nRun inference with a trained model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ngradio\nbool\nWhether to use Gradio browser interface or command line for inference.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_lora(config, **kwargs)\nMerge trained LoRA adapters into a base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_sharded_fsdp_weights(config, accelerate, **kwargs)\nMerge sharded FSDP model weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.preprocess(config, cloud=None, **kwargs)\nPreprocess datasets before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.train(config, accelerate, cloud=None, sweep=None, **kwargs)\nTrain or fine-tune a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file\nNone\n\n\nsweep\nOptional[str]\nPath to YAML config for sweeping hyperparameters.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}" + "text": "prompt_strategies.kto.user_defined\nprompt_strategies.kto.user_defined\nUser-defined KTO strategies" }, { - "objectID": "docs/api/cli.main.html#functions", - "href": "docs/api/cli.main.html#functions", - "title": "cli.main", + "objectID": "docs/api/core.trainers.mixins.rng_state_loader.html", + "href": "docs/api/core.trainers.mixins.rng_state_loader.html", + "title": "core.trainers.mixins.rng_state_loader", "section": "", - "text": "Name\nDescription\n\n\n\n\ncli\nAxolotl CLI - Train and fine-tune large language models\n\n\nevaluate\nEvaluate a model.\n\n\nfetch\nFetch example configs or other resources.\n\n\ninference\nRun inference with a trained model.\n\n\nmerge_lora\nMerge trained LoRA adapters into a base model.\n\n\nmerge_sharded_fsdp_weights\nMerge sharded FSDP model weights.\n\n\npreprocess\nPreprocess datasets before training.\n\n\ntrain\nTrain or fine-tune a model.\n\n\n\n\n\ncli.main.cli()\nAxolotl CLI - Train and fine-tune large language models\n\n\n\ncli.main.evaluate(config, accelerate, **kwargs)\nEvaluate a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.fetch(directory, dest)\nFetch example configs or other resources.\nAvailable directories:\n- examples: Example configuration files\n- deepspeed_configs: DeepSpeed configuration files\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndirectory\nstr\nOne of examples, deepspeed_configs.\nrequired\n\n\ndest\nOptional[str]\nOptional destination directory.\nrequired\n\n\n\n\n\n\n\ncli.main.inference(config, accelerate, gradio, **kwargs)\nRun inference with a trained model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ngradio\nbool\nWhether to use Gradio browser interface or command line for inference.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_lora(config, **kwargs)\nMerge trained LoRA adapters into a base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_sharded_fsdp_weights(config, accelerate, **kwargs)\nMerge sharded FSDP model weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.preprocess(config, cloud=None, **kwargs)\nPreprocess datasets before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.train(config, accelerate, cloud=None, sweep=None, **kwargs)\nTrain or fine-tune a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file\nNone\n\n\nsweep\nOptional[str]\nPath to YAML config for sweeping hyperparameters.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}" + "text": "core.trainers.mixins.rng_state_loader\nTemporary fix/override for bug in resume from checkpoint\nSee https://github.com/huggingface/transformers/pull/37162\nTODO: Remove when upstream added PR to release\n\n\n\n\n\nName\nDescription\n\n\n\n\nRngLoaderMixin\nmixin for method override to load RNG states from a checkpoint\n\n\n\n\n\ncore.trainers.mixins.rng_state_loader.RngLoaderMixin()\nmixin for method override to load RNG states from a checkpoint" }, { - "objectID": "docs/api/prompt_strategies.dpo.chatml.html", - "href": "docs/api/prompt_strategies.dpo.chatml.html", - "title": "prompt_strategies.dpo.chatml", + "objectID": "docs/api/core.trainers.mixins.rng_state_loader.html#classes", + "href": "docs/api/core.trainers.mixins.rng_state_loader.html#classes", + "title": "core.trainers.mixins.rng_state_loader", "section": "", - "text": "prompt_strategies.dpo.chatml\nDPO strategies for chatml\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.chatml.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.chatml.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" + "text": "Name\nDescription\n\n\n\n\nRngLoaderMixin\nmixin for method override to load RNG states from a checkpoint\n\n\n\n\n\ncore.trainers.mixins.rng_state_loader.RngLoaderMixin()\nmixin for method override to load RNG states from a checkpoint" }, { - "objectID": "docs/api/prompt_strategies.dpo.chatml.html#functions", - "href": "docs/api/prompt_strategies.dpo.chatml.html#functions", - "title": "prompt_strategies.dpo.chatml", + "objectID": "docs/api/integrations.liger.args.html", + "href": "docs/api/integrations.liger.args.html", + "title": "integrations.liger.args", "section": "", - "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.chatml.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.chatml.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" + "text": "integrations.liger.args\nModule for handling LIGER input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nLigerArgs\nInput args for LIGER.\n\n\n\n\n\nintegrations.liger.args.LigerArgs()\nInput args for LIGER." }, { - "objectID": "docs/api/core.trainer_builder.html", - "href": "docs/api/core.trainer_builder.html", - "title": "core.trainer_builder", + "objectID": "docs/api/integrations.liger.args.html#classes", + "href": "docs/api/integrations.liger.args.html#classes", + "title": "integrations.liger.args", "section": "", - "text": "core.trainer_builder\nBuilder for the training args and trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nHFCausalTrainerBuilder\nBuild the HuggingFace training args/trainer for causal models and reward modeling\n\n\nHFPPOTrainerBuilder\nHF Factory class for PPO Trainer\n\n\nHFRLTrainerBuilder\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\nTrainerBuilderBase\nBase class for trainer builder.\n\n\n\n\n\ncore.trainer_builder.HFCausalTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBuild the HuggingFace training args/trainer for causal models and reward modeling\nusing TRL.\n\n\n\ncore.trainer_builder.HFPPOTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nHF Factory class for PPO Trainer\n\n\n\ncore.trainer_builder.HFRLTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\n\ncore.trainer_builder.TrainerBuilderBase(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBase class for trainer builder.\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_post_trainer_create_callbacks\nCallbacks added after the trainer is created, usually b/c these need access to the trainer\n\n\n\n\n\ncore.trainer_builder.TrainerBuilderBase.get_post_trainer_create_callbacks(\n trainer,\n)\nCallbacks added after the trainer is created, usually b/c these need access to the trainer" + "text": "Name\nDescription\n\n\n\n\nLigerArgs\nInput args for LIGER.\n\n\n\n\n\nintegrations.liger.args.LigerArgs()\nInput args for LIGER." }, { - "objectID": "docs/api/core.trainer_builder.html#classes", - "href": "docs/api/core.trainer_builder.html#classes", - "title": "core.trainer_builder", + "objectID": "docs/api/utils.data.sft.html", + "href": "docs/api/utils.data.sft.html", + "title": "utils.data.sft", "section": "", - "text": "Name\nDescription\n\n\n\n\nHFCausalTrainerBuilder\nBuild the HuggingFace training args/trainer for causal models and reward modeling\n\n\nHFPPOTrainerBuilder\nHF Factory class for PPO Trainer\n\n\nHFRLTrainerBuilder\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\nTrainerBuilderBase\nBase class for trainer builder.\n\n\n\n\n\ncore.trainer_builder.HFCausalTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBuild the HuggingFace training args/trainer for causal models and reward modeling\nusing TRL.\n\n\n\ncore.trainer_builder.HFPPOTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nHF Factory class for PPO Trainer\n\n\n\ncore.trainer_builder.HFRLTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\n\ncore.trainer_builder.TrainerBuilderBase(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBase class for trainer builder.\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_post_trainer_create_callbacks\nCallbacks added after the trainer is created, usually b/c these need access to the trainer\n\n\n\n\n\ncore.trainer_builder.TrainerBuilderBase.get_post_trainer_create_callbacks(\n trainer,\n)\nCallbacks added after the trainer is created, usually b/c these need access to the trainer" + "text": "utils.data.sft\nutils.data.sft\ndata handling specific to SFT" }, { - "objectID": "docs/api/models.mamba.modeling_mamba.html", - "href": "docs/api/models.mamba.modeling_mamba.html", - "title": "models.mamba.modeling_mamba", + "objectID": "docs/api/utils.freeze.html", + "href": "docs/api/utils.freeze.html", + "title": "utils.freeze", "section": "", - "text": "models.mamba.modeling_mamba\nmodels.mamba.modeling_mamba" + "text": "utils.freeze\nmodule to freeze/unfreeze parameters by name\n\n\n\n\n\nName\nDescription\n\n\n\n\nLayerNamePattern\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nutils.freeze.LayerNamePattern(self, pattern)\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nName\nDescription\n\n\n\n\nmatch\nChecks if the given layer name matches the regex pattern.\n\n\n\n\n\nutils.freeze.LayerNamePattern.match(name)\nChecks if the given layer name matches the regex pattern.\nParameters:\n- name (str): The layer name to check.\nReturns:\n- bool: True if the layer name matches the pattern, False otherwise.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nfreeze_layers_except\nFreezes all layers of the given model except for the layers that match given regex patterns.\n\n\n\n\n\nutils.freeze.freeze_layers_except(model, regex_patterns)\nFreezes all layers of the given model except for the layers that match given regex patterns.\nPeriods in the patterns are treated as literal periods, not as wildcard characters.\nParameters:\n- model (nn.Module): The PyTorch model to be modified.\n- regex_patterns (list of str): List of regex patterns to match layer names to keep unfrozen.\nNote that you cannot use a dot as a wildcard character in the patterns since it is reserved for separating layer names.\nAlso, to match the entire layer name, the pattern should start with “^” and end with “\\(\", otherwise it will match any part of the layer name.\n The range pattern part is optional and it is not compiled as a regex pattern which means you must put \"\\)” before the range pattern if you want to match the entire layer name.\nE.g., [“^model.embed_tokens.weight\\([:32000]\", \"layers.2[0-9]+.block_sparse_moe.gate.[a-z]+\\)”]\nReturns:\nNone; the model is modified in place." }, { - "objectID": "docs/api/prompt_strategies.dpo.chat_template.html", - "href": "docs/api/prompt_strategies.dpo.chat_template.html", - "title": "prompt_strategies.dpo.chat_template", + "objectID": "docs/api/utils.freeze.html#classes", + "href": "docs/api/utils.freeze.html#classes", + "title": "utils.freeze", "section": "", - "text": "prompt_strategies.dpo.chat_template\nprompt_strategies.dpo.chat_template\nDPO prompt strategies for using tokenizer chat templates." + "text": "Name\nDescription\n\n\n\n\nLayerNamePattern\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nutils.freeze.LayerNamePattern(self, pattern)\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nName\nDescription\n\n\n\n\nmatch\nChecks if the given layer name matches the regex pattern.\n\n\n\n\n\nutils.freeze.LayerNamePattern.match(name)\nChecks if the given layer name matches the regex pattern.\nParameters:\n- name (str): The layer name to check.\nReturns:\n- bool: True if the layer name matches the pattern, False otherwise." }, { - "objectID": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html", - "href": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html", - "title": "monkeypatch.stablelm_attn_hijack_flash", + "objectID": "docs/api/utils.freeze.html#functions", + "href": "docs/api/utils.freeze.html#functions", + "title": "utils.freeze", "section": "", - "text": "monkeypatch.stablelm_attn_hijack_flash\nPyTorch StableLM Epoch model.\n\n\n\n\n\nName\nDescription\n\n\n\n\nrepeat_kv\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\n\n\nrotate_half\nRotates half the hidden dims of the input.\n\n\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.repeat_kv(hidden_states, n_rep)\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\nnum_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.rotate_half(x)\nRotates half the hidden dims of the input." + "text": "Name\nDescription\n\n\n\n\nfreeze_layers_except\nFreezes all layers of the given model except for the layers that match given regex patterns.\n\n\n\n\n\nutils.freeze.freeze_layers_except(model, regex_patterns)\nFreezes all layers of the given model except for the layers that match given regex patterns.\nPeriods in the patterns are treated as literal periods, not as wildcard characters.\nParameters:\n- model (nn.Module): The PyTorch model to be modified.\n- regex_patterns (list of str): List of regex patterns to match layer names to keep unfrozen.\nNote that you cannot use a dot as a wildcard character in the patterns since it is reserved for separating layer names.\nAlso, to match the entire layer name, the pattern should start with “^” and end with “\\(\", otherwise it will match any part of the layer name.\n The range pattern part is optional and it is not compiled as a regex pattern which means you must put \"\\)” before the range pattern if you want to match the entire layer name.\nE.g., [“^model.embed_tokens.weight\\([:32000]\", \"layers.2[0-9]+.block_sparse_moe.gate.[a-z]+\\)”]\nReturns:\nNone; the model is modified in place." }, { - "objectID": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html#functions", - "href": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html#functions", - "title": "monkeypatch.stablelm_attn_hijack_flash", + "objectID": "docs/api/cli.preprocess.html", + "href": "docs/api/cli.preprocess.html", + "title": "cli.preprocess", "section": "", - "text": "Name\nDescription\n\n\n\n\nrepeat_kv\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\n\n\nrotate_half\nRotates half the hidden dims of the input.\n\n\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.repeat_kv(hidden_states, n_rep)\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\nnum_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.rotate_half(x)\nRotates half the hidden dims of the input." + "text": "cli.preprocess\nCLI to run preprocessing of a dataset.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\ndo_preprocess\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\ncli.preprocess.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.preprocess.do_preprocess(cfg, cli_args)\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs\nPreprocessing-specific CLI arguments.\nrequired" }, { - "objectID": "docs/api/utils.gradient_checkpointing.offload_disk.html", - "href": "docs/api/utils.gradient_checkpointing.offload_disk.html", - "title": "utils.gradient_checkpointing.offload_disk", + "objectID": "docs/api/cli.preprocess.html#functions", + "href": "docs/api/cli.preprocess.html#functions", + "title": "cli.preprocess", "section": "", - "text": "utils.gradient_checkpointing.offload_disk\nDISCO - DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\n\n\n\nName\nDescription\n\n\n\n\nDisco\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\nDiskOffloadManager\nManages offloaded tensors and handles prefetching in a separate thread.\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco()\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\nAdvanced disk-based gradient checkpointer with prefetching.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass that loads activations from disk with prefetching\n\n\nforward\nForward pass that offloads activations to disk asynchronously\n\n\nget_instance\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.backward(ctx, *grad_outputs)\nBackward pass that loads activations from disk with prefetching\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.forward(\n ctx,\n forward_function,\n hidden_states,\n *args,\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nForward pass that offloads activations to disk asynchronously\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.get_instance(\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager(\n self,\n prefetch_size=3,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nManages offloaded tensors and handles prefetching in a separate thread.\nIncludes synchronization to prevent race conditions.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncleanup\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\ncleanup_tensor\nClean up a specific tensor file after it’s been used\n\n\nload_tensor\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\nsave_tensor\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\ntrigger_prefetch\nTrigger prefetching of the next N tensors with proper synchronization\n\n\nwait_for_save\nWait for a tensor to be saved to disk\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup()\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup_tensor(\n file_path,\n)\nClean up a specific tensor file after it’s been used\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.load_tensor(\n file_path,\n target_device='cuda',\n)\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.save_tensor(tensor)\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.trigger_prefetch(\n n=None,\n)\nTrigger prefetching of the next N tensors with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.wait_for_save(\n file_path,\n timeout=None,\n)\nWait for a tensor to be saved to disk" + "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\ndo_preprocess\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\ncli.preprocess.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.preprocess.do_preprocess(cfg, cli_args)\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs\nPreprocessing-specific CLI arguments.\nrequired" }, { - "objectID": "docs/api/utils.gradient_checkpointing.offload_disk.html#classes", - "href": "docs/api/utils.gradient_checkpointing.offload_disk.html#classes", - "title": "utils.gradient_checkpointing.offload_disk", + "objectID": "docs/api/index.html", + "href": "docs/api/index.html", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nDisco\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\nDiskOffloadManager\nManages offloaded tensors and handles prefetching in a separate thread.\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco()\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\nAdvanced disk-based gradient checkpointer with prefetching.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass that loads activations from disk with prefetching\n\n\nforward\nForward pass that offloads activations to disk asynchronously\n\n\nget_instance\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.backward(ctx, *grad_outputs)\nBackward pass that loads activations from disk with prefetching\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.forward(\n ctx,\n forward_function,\n hidden_states,\n *args,\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nForward pass that offloads activations to disk asynchronously\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.get_instance(\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager(\n self,\n prefetch_size=3,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nManages offloaded tensors and handles prefetching in a separate thread.\nIncludes synchronization to prevent race conditions.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncleanup\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\ncleanup_tensor\nClean up a specific tensor file after it’s been used\n\n\nload_tensor\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\nsave_tensor\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\ntrigger_prefetch\nTrigger prefetching of the next N tensors with proper synchronization\n\n\nwait_for_save\nWait for a tensor to be saved to disk\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup()\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup_tensor(\n file_path,\n)\nClean up a specific tensor file after it’s been used\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.load_tensor(\n file_path,\n target_device='cuda',\n)\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.save_tensor(tensor)\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.trigger_prefetch(\n n=None,\n)\nTrigger prefetching of the next N tensors with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.wait_for_save(\n file_path,\n timeout=None,\n)\nWait for a tensor to be saved to disk" + "text": "Core functionality for training\n\n\n\ntrain\nPrepare and train a model on a dataset. Can also infer from a model or merge lora\n\n\nevaluate\nModule for evaluating models.\n\n\ndatasets\nModule containing Dataset functionality\n\n\nconvert\nModule containing File Reader, File Writer, Json Parser, and Jsonl Serializer classes\n\n\nprompt_tokenizers\nModule containing PromptTokenizingStrategy and Prompter classes\n\n\nlogging_config\nCommon logging module for axolotl\n\n\ncore.trainer_builder\nBuilder for the training args and trainer\n\n\ncore.training_args\nextra axolotl specific training args\n\n\ncore.chat.messages\ninternal message representations of chat messages\n\n\ncore.chat.format.chatml\nChatML transformation functions for MessageContents\n\n\ncore.chat.format.llama3x\nLlama 3.x chat formatting functions for MessageContents\n\n\ncore.chat.format.shared\nshared functions for format transforms\n\n\ncore.datasets.chat\nchat dataset module\n\n\ncore.datasets.transforms.chat_builder\nThis module contains a function that builds a transform that takes a row from the dataset and converts it to a Chat.\n\n\n\n\n\n\nCommand-line interface\n\n\n\ncli.main\nClick CLI definitions for various axolotl commands.\n\n\ncli.train\nCLI to run training on a model.\n\n\ncli.evaluate\nCLI to run evaluation on a model.\n\n\ncli.args\nModule for axolotl CLI command arguments.\n\n\ncli.checks\nVarious checks for Axolotl CLI.\n\n\ncli.config\nConfiguration loading and processing.\n\n\ncli.inference\nCLI to run inference on a trained model.\n\n\ncli.merge_lora\nCLI to merge a trained LoRA into a base model.\n\n\ncli.merge_sharded_fsdp_weights\nCLI to merge sharded FSDP model checkpoints into a single combined checkpoint.\n\n\ncli.preprocess\nCLI to run preprocessing of a dataset.\n\n\ncli.sweeps\nUtilities for handling sweeps over configs for axolotl train CLI command\n\n\ncli.utils\nUtility methods for axolotl CLI.\n\n\ncli.vllm_serve\nCLI to start the vllm server for online RL\n\n\ncli.cloud.base\nbase class for cloud platforms from cli\n\n\ncli.cloud.modal_\nModal Cloud support from CLI\n\n\n\n\n\n\nTraining implementations\n\n\n\ncore.trainers.base\nModule for customized trainers\n\n\ncore.trainers.trl\nModule for TRL PPO trainer\n\n\ncore.trainers.mamba\nModule for mamba trainer\n\n\ncore.trainers.relora\nModule for ReLoRA trainer\n\n\ncore.trainers.dpo.trainer\nDPO trainer for axolotl\n\n\ncore.trainers.grpo.trainer\nAxolotl GRPO trainers (with and without sequence parallelism handling)\n\n\ncore.trainers.grpo.sampler\nRepeat random sampler (similar to the one implemented in\n\n\ncore.trainers.utils\nUtils for Axolotl trainers\n\n\n\n\n\n\nMixin classes for augmenting trainers\n\n\n\ncore.trainers.mixins.optimizer\nModule for Axolotl trainer optimizer mixin\n\n\ncore.trainers.mixins.rng_state_loader\nTemporary fix/override for bug in resume from checkpoint\n\n\ncore.trainers.mixins.scheduler\nModule for Axolotl trainer scheduler mixin\n\n\n\n\n\n\nContext managers for altering trainer behaviors\n\n\n\nutils.ctx_managers.sequence_parallel\nModule for Axolotl trainer sequence parallelism manager and utilities\n\n\n\n\n\n\nPrompt formatting strategies\n\n\n\nprompt_strategies.base\nmodule for base dataset transform strategies\n\n\nprompt_strategies.chat_template\nHF Chat Templates prompt strategy\n\n\nprompt_strategies.alpaca_chat\nModule for Alpaca prompt strategy classes\n\n\nprompt_strategies.alpaca_instruct\nModule loading the AlpacaInstructPromptTokenizingStrategy class\n\n\nprompt_strategies.alpaca_w_system\nPrompt strategies loader for alpaca instruction datasets with system prompts\n\n\nprompt_strategies.user_defined\nUser Defined prompts with configuration from the YML config\n\n\nprompt_strategies.llama2_chat\nPrompt Strategy for finetuning Llama2 chat models\n\n\nprompt_strategies.completion\nBasic completion text\n\n\nprompt_strategies.input_output\nModule for plain input/output prompt pairs\n\n\nprompt_strategies.stepwise_supervised\nModule for stepwise datasets, typically including a prompt and reasoning traces,\n\n\nprompt_strategies.metharme\nModule containing the MetharmenPromptTokenizingStrategy and MetharmePrompter class\n\n\nprompt_strategies.orcamini\nPrompt Strategy for finetuning Orca Mini (v2) models\n\n\nprompt_strategies.pygmalion\nModule containing the PygmalionPromptTokenizingStrategy and PygmalionPrompter class\n\n\nprompt_strategies.messages.chat\nChat dataset wrapping strategy for new internal messages representations\n\n\nprompt_strategies.dpo.chat_template\nDPO prompt strategies for using tokenizer chat templates.\n\n\nprompt_strategies.dpo.llama3\nDPO strategies for llama-3 chat template\n\n\nprompt_strategies.dpo.chatml\nDPO strategies for chatml\n\n\nprompt_strategies.dpo.zephyr\nDPO strategies for zephyr\n\n\nprompt_strategies.dpo.user_defined\nUser-defined DPO strategies\n\n\nprompt_strategies.dpo.passthrough\nDPO prompt strategies passthrough/zero-processing strategy\n\n\nprompt_strategies.kto.llama3\nKTO strategies for llama-3 chat template\n\n\nprompt_strategies.kto.chatml\nKTO strategies for chatml\n\n\nprompt_strategies.kto.user_defined\nUser-defined KTO strategies\n\n\nprompt_strategies.orpo.chat_template\nchatml prompt tokenization strategy for ORPO\n\n\nprompt_strategies.bradley_terry.llama3\nchatml transforms for datasets with system, input, chosen, rejected to match llama3 chat template\n\n\n\n\n\n\nLow-level performance optimizations\n\n\n\nkernels.lora\nModule for definition of Low-Rank Adaptation (LoRA) Triton kernels.\n\n\nkernels.geglu\nModule for definition of GEGLU Triton kernels.\n\n\nkernels.swiglu\nModule for definition of SwiGLU Triton kernels.\n\n\nkernels.quantize\nDequantization utilities for bitsandbytes integration.\n\n\nkernels.utils\nUtilities for axolotl.kernels submodules.\n\n\n\n\n\n\nRuntime patches for model optimizations\n\n\n\nmonkeypatch.llama_attn_hijack_flash\nFlash attention monkey patch for llama model\n\n\nmonkeypatch.llama_attn_hijack_xformers\nDirectly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments\n\n\nmonkeypatch.mistral_attn_hijack_flash\nFlash attention monkey patch for mistral model\n\n\nmonkeypatch.multipack\nmultipack patching for v2 of sample packing\n\n\nmonkeypatch.relora\nImplements the ReLoRA training procedure from https://arxiv.org/abs/2307.05695, minus the initial full fine-tune.\n\n\nmonkeypatch.llama_expand_mask\nexpands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf\n\n\nmonkeypatch.lora_kernels\nModule for patching custom LoRA Triton kernels and torch.autograd functions.\n\n\nmonkeypatch.utils\nShared utils for the monkeypatches\n\n\nmonkeypatch.btlm_attn_hijack_flash\nFlash attention monkey patch for cerebras btlm model\n\n\nmonkeypatch.llama_patch_multipack\nPatched LlamaAttention to use torch.nn.functional.scaled_dot_product_attention\n\n\nmonkeypatch.stablelm_attn_hijack_flash\nPyTorch StableLM Epoch model.\n\n\nmonkeypatch.trainer_fsdp_optim\nfix for FSDP optimizer save in trainer w 4.47.0\n\n\nmonkeypatch.transformers_fa_utils\nsee https://github.com/huggingface/transformers/pull/35834\n\n\nmonkeypatch.unsloth_\nmodule for patching with unsloth optimizations\n\n\nmonkeypatch.attention.mllama\nMonkeypatch for Vision Llama for FA2 support\n\n\nmonkeypatch.data.batch_dataset_fetcher\nmonkey patches for the dataset fetcher to handle batches of packed indexes\n\n\nmonkeypatch.mixtral\nPatches to support multipack for mixtral\n\n\n\n\n\n\nUtility functions\n\n\n\nutils.models\nModule for models and model loading\n\n\nutils.tokenization\nModule for tokenization utilities\n\n\nutils.chat_templates\nThis module provides functionality for selecting chat templates based on user choices.\n\n\nutils.lora\nmodule to get the state dict of a merged lora model\n\n\nutils.lora_embeddings\nhelpers for lora embeddings\n\n\nutils.model_shard_quant\nmodule to handle loading model on cpu/meta device for FSDP\n\n\nutils.bench\nBenchmarking and measurement utilities\n\n\nutils.freeze\nmodule to freeze/unfreeze parameters by name\n\n\nutils.trainer\nModule containing the Trainer class and related functions\n\n\nutils.schedulers\nModule for custom LRScheduler class\n\n\nutils.distributed\nutility helpers for distributed checks\n\n\nutils.dict\nModule containing the DictDefault class\n\n\nutils.optimizers.adopt\nCopied from https://github.com/iShohei220/adopt\n\n\nutils.data.pretraining\ndata handling specific to pretraining\n\n\nutils.data.sft\ndata handling specific to SFT\n\n\nutils.gradient_checkpointing.offload_cpu\nCPU offloaded checkpointing\n\n\nutils.gradient_checkpointing.offload_disk\nDISCO - DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\n\n\n\n\nPydantic data models for Axolotl config\n\n\n\nutils.schemas.config\nModule with Pydantic models for configuration.\n\n\nutils.schemas.model\nPydantic models for model input / output, etc. configuration\n\n\nutils.schemas.training\nPydantic models for training hyperparameters\n\n\nutils.schemas.datasets\nPydantic models for datasets-related configuration\n\n\nutils.schemas.peft\nPydantic models for PEFT-related configuration\n\n\nutils.schemas.trl\nPydantic models for TRL trainer configuration\n\n\nutils.schemas.multimodal\nPydantic models for multimodal-related configuration\n\n\nutils.schemas.integrations\nPydantic models for Axolotl integrations\n\n\nutils.schemas.enums\nEnums for Axolotl input config\n\n\nutils.schemas.utils\nUtilities for Axolotl Pydantic models\n\n\n\n\n\n\nThird-party integrations and extensions\n\n\n\nintegrations.base\nBase class for all plugins.\n\n\nintegrations.cut_cross_entropy.args\nModule for handling Cut Cross Entropy input arguments.\n\n\nintegrations.grokfast.optimizer\n\n\n\nintegrations.kd.trainer\nKD trainer\n\n\nintegrations.liger.args\nModule for handling LIGER input arguments.\n\n\nintegrations.lm_eval.args\nModule for handling lm eval harness input arguments.\n\n\nintegrations.spectrum.args\nModule for handling Spectrum input arguments.\n\n\n\n\n\n\nCommon utilities and shared functionality\n\n\n\ncommon.architectures\nCommon architecture specific constants\n\n\ncommon.const\nVarious shared constants\n\n\ncommon.datasets\nDataset loading utilities.\n\n\n\n\n\n\nCustom model implementations\n\n\n\nmodels.mamba.modeling_mamba\n\n\n\n\n\n\n\nData processing utilities\n\n\n\nutils.collators.core\nbasic shared collator constants\n\n\nutils.collators.batching\nData collators for axolotl to pad labels and position_ids for packed sequences\n\n\nutils.collators.mamba\ncollators for Mamba\n\n\nutils.collators.mm_chat\nCollators for multi-modal chat messages and packing\n\n\nutils.samplers.multipack\nMultipack Batch Sampler - An efficient batch sampler for packing variable-length sequences\n\n\n\n\n\n\nTraining callbacks\n\n\n\nutils.callbacks.perplexity\ncallback to calculate perplexity as an evaluation metric.\n\n\nutils.callbacks.profiler\nHF Trainer callback for creating pytorch profiling snapshots\n\n\nutils.callbacks.lisa\nmodule for LISA\n\n\nutils.callbacks.mlflow_\nMLFlow module for trainer callbacks\n\n\nutils.callbacks.comet_\nComet module for trainer callbacks" }, { - "objectID": "docs/api/prompt_strategies.dpo.llama3.html", - "href": "docs/api/prompt_strategies.dpo.llama3.html", - "title": "prompt_strategies.dpo.llama3", + "objectID": "docs/api/index.html#core", + "href": "docs/api/index.html#core", + "title": "API Reference", "section": "", - "text": "prompt_strategies.dpo.llama3\nDPO strategies for llama-3 chat template\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.llama3.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" + "text": "Core functionality for training\n\n\n\ntrain\nPrepare and train a model on a dataset. Can also infer from a model or merge lora\n\n\nevaluate\nModule for evaluating models.\n\n\ndatasets\nModule containing Dataset functionality\n\n\nconvert\nModule containing File Reader, File Writer, Json Parser, and Jsonl Serializer classes\n\n\nprompt_tokenizers\nModule containing PromptTokenizingStrategy and Prompter classes\n\n\nlogging_config\nCommon logging module for axolotl\n\n\ncore.trainer_builder\nBuilder for the training args and trainer\n\n\ncore.training_args\nextra axolotl specific training args\n\n\ncore.chat.messages\ninternal message representations of chat messages\n\n\ncore.chat.format.chatml\nChatML transformation functions for MessageContents\n\n\ncore.chat.format.llama3x\nLlama 3.x chat formatting functions for MessageContents\n\n\ncore.chat.format.shared\nshared functions for format transforms\n\n\ncore.datasets.chat\nchat dataset module\n\n\ncore.datasets.transforms.chat_builder\nThis module contains a function that builds a transform that takes a row from the dataset and converts it to a Chat." }, { - "objectID": "docs/api/prompt_strategies.dpo.llama3.html#functions", - "href": "docs/api/prompt_strategies.dpo.llama3.html#functions", - "title": "prompt_strategies.dpo.llama3", + "objectID": "docs/api/index.html#cli", + "href": "docs/api/index.html#cli", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.llama3.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" + "text": "Command-line interface\n\n\n\ncli.main\nClick CLI definitions for various axolotl commands.\n\n\ncli.train\nCLI to run training on a model.\n\n\ncli.evaluate\nCLI to run evaluation on a model.\n\n\ncli.args\nModule for axolotl CLI command arguments.\n\n\ncli.checks\nVarious checks for Axolotl CLI.\n\n\ncli.config\nConfiguration loading and processing.\n\n\ncli.inference\nCLI to run inference on a trained model.\n\n\ncli.merge_lora\nCLI to merge a trained LoRA into a base model.\n\n\ncli.merge_sharded_fsdp_weights\nCLI to merge sharded FSDP model checkpoints into a single combined checkpoint.\n\n\ncli.preprocess\nCLI to run preprocessing of a dataset.\n\n\ncli.sweeps\nUtilities for handling sweeps over configs for axolotl train CLI command\n\n\ncli.utils\nUtility methods for axolotl CLI.\n\n\ncli.vllm_serve\nCLI to start the vllm server for online RL\n\n\ncli.cloud.base\nbase class for cloud platforms from cli\n\n\ncli.cloud.modal_\nModal Cloud support from CLI" }, { - "objectID": "docs/api/prompt_strategies.metharme.html", - "href": "docs/api/prompt_strategies.metharme.html", - "title": "prompt_strategies.metharme", + "objectID": "docs/api/index.html#trainers", + "href": "docs/api/index.html#trainers", + "title": "API Reference", "section": "", - "text": "prompt_strategies.metharme\nModule containing the MetharmenPromptTokenizingStrategy and MetharmePrompter class\n\n\n\n\n\nName\nDescription\n\n\n\n\nMetharmePromptTokenizingStrategy\nTokenizing strategy for the Metharme models\n\n\nMetharmePrompter\nPrompter for the Metharme models.\n\n\n\n\n\nprompt_strategies.metharme.MetharmePromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for the Metharme models\n\n\n\nprompt_strategies.metharme.MetharmePrompter(self, *args, **kwargs)\nPrompter for the Metharme models." + "text": "Training implementations\n\n\n\ncore.trainers.base\nModule for customized trainers\n\n\ncore.trainers.trl\nModule for TRL PPO trainer\n\n\ncore.trainers.mamba\nModule for mamba trainer\n\n\ncore.trainers.relora\nModule for ReLoRA trainer\n\n\ncore.trainers.dpo.trainer\nDPO trainer for axolotl\n\n\ncore.trainers.grpo.trainer\nAxolotl GRPO trainers (with and without sequence parallelism handling)\n\n\ncore.trainers.grpo.sampler\nRepeat random sampler (similar to the one implemented in\n\n\ncore.trainers.utils\nUtils for Axolotl trainers" }, { - "objectID": "docs/api/prompt_strategies.metharme.html#classes", - "href": "docs/api/prompt_strategies.metharme.html#classes", - "title": "prompt_strategies.metharme", + "objectID": "docs/api/index.html#mixins", + "href": "docs/api/index.html#mixins", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nMetharmePromptTokenizingStrategy\nTokenizing strategy for the Metharme models\n\n\nMetharmePrompter\nPrompter for the Metharme models.\n\n\n\n\n\nprompt_strategies.metharme.MetharmePromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for the Metharme models\n\n\n\nprompt_strategies.metharme.MetharmePrompter(self, *args, **kwargs)\nPrompter for the Metharme models." + "text": "Mixin classes for augmenting trainers\n\n\n\ncore.trainers.mixins.optimizer\nModule for Axolotl trainer optimizer mixin\n\n\ncore.trainers.mixins.rng_state_loader\nTemporary fix/override for bug in resume from checkpoint\n\n\ncore.trainers.mixins.scheduler\nModule for Axolotl trainer scheduler mixin" }, { - "objectID": "docs/api/kernels.swiglu.html", - "href": "docs/api/kernels.swiglu.html", - "title": "kernels.swiglu", + "objectID": "docs/api/index.html#context-managers", + "href": "docs/api/index.html#context-managers", + "title": "API Reference", "section": "", - "text": "kernels.swiglu\nModule for definition of SwiGLU Triton kernels.\nSee “GLU Variants Improve Transformer” (https://arxiv.org/abs/2002.05202).\nCredit to unsloth (https://unsloth.ai/) for inspiration for this implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nswiglu_backward\nSwiGLU backward pass using in-place operations.\n\n\nswiglu_forward\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\n\n\n\n\n\nkernels.swiglu.swiglu_backward(grad_output, gate, up)\nSwiGLU backward pass using in-place operations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to output, shape [batch, seq_len, hidden_dim].\nrequired\n\n\ngate\ntorch.Tensor\nGate tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple containing: - Forward pass output (h) - Gradient with respect to gate (df) - Gradient with respect to up-projection (de)\n\n\n\n\n\n\n\nkernels.swiglu.swiglu_forward(gate, up)\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\nx is the gate tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngate\ntorch.Tensor\nInput gate tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor of shape [batch, seq_len, hidden_dim]." + "text": "Context managers for altering trainer behaviors\n\n\n\nutils.ctx_managers.sequence_parallel\nModule for Axolotl trainer sequence parallelism manager and utilities" }, { - "objectID": "docs/api/kernels.swiglu.html#functions", - "href": "docs/api/kernels.swiglu.html#functions", - "title": "kernels.swiglu", + "objectID": "docs/api/index.html#prompt-strategies", + "href": "docs/api/index.html#prompt-strategies", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nswiglu_backward\nSwiGLU backward pass using in-place operations.\n\n\nswiglu_forward\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\n\n\n\n\n\nkernels.swiglu.swiglu_backward(grad_output, gate, up)\nSwiGLU backward pass using in-place operations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to output, shape [batch, seq_len, hidden_dim].\nrequired\n\n\ngate\ntorch.Tensor\nGate tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple containing: - Forward pass output (h) - Gradient with respect to gate (df) - Gradient with respect to up-projection (de)\n\n\n\n\n\n\n\nkernels.swiglu.swiglu_forward(gate, up)\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\nx is the gate tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngate\ntorch.Tensor\nInput gate tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor of shape [batch, seq_len, hidden_dim]." + "text": "Prompt formatting strategies\n\n\n\nprompt_strategies.base\nmodule for base dataset transform strategies\n\n\nprompt_strategies.chat_template\nHF Chat Templates prompt strategy\n\n\nprompt_strategies.alpaca_chat\nModule for Alpaca prompt strategy classes\n\n\nprompt_strategies.alpaca_instruct\nModule loading the AlpacaInstructPromptTokenizingStrategy class\n\n\nprompt_strategies.alpaca_w_system\nPrompt strategies loader for alpaca instruction datasets with system prompts\n\n\nprompt_strategies.user_defined\nUser Defined prompts with configuration from the YML config\n\n\nprompt_strategies.llama2_chat\nPrompt Strategy for finetuning Llama2 chat models\n\n\nprompt_strategies.completion\nBasic completion text\n\n\nprompt_strategies.input_output\nModule for plain input/output prompt pairs\n\n\nprompt_strategies.stepwise_supervised\nModule for stepwise datasets, typically including a prompt and reasoning traces,\n\n\nprompt_strategies.metharme\nModule containing the MetharmenPromptTokenizingStrategy and MetharmePrompter class\n\n\nprompt_strategies.orcamini\nPrompt Strategy for finetuning Orca Mini (v2) models\n\n\nprompt_strategies.pygmalion\nModule containing the PygmalionPromptTokenizingStrategy and PygmalionPrompter class\n\n\nprompt_strategies.messages.chat\nChat dataset wrapping strategy for new internal messages representations\n\n\nprompt_strategies.dpo.chat_template\nDPO prompt strategies for using tokenizer chat templates.\n\n\nprompt_strategies.dpo.llama3\nDPO strategies for llama-3 chat template\n\n\nprompt_strategies.dpo.chatml\nDPO strategies for chatml\n\n\nprompt_strategies.dpo.zephyr\nDPO strategies for zephyr\n\n\nprompt_strategies.dpo.user_defined\nUser-defined DPO strategies\n\n\nprompt_strategies.dpo.passthrough\nDPO prompt strategies passthrough/zero-processing strategy\n\n\nprompt_strategies.kto.llama3\nKTO strategies for llama-3 chat template\n\n\nprompt_strategies.kto.chatml\nKTO strategies for chatml\n\n\nprompt_strategies.kto.user_defined\nUser-defined KTO strategies\n\n\nprompt_strategies.orpo.chat_template\nchatml prompt tokenization strategy for ORPO\n\n\nprompt_strategies.bradley_terry.llama3\nchatml transforms for datasets with system, input, chosen, rejected to match llama3 chat template" }, { - "objectID": "docs/api/core.trainers.base.html", - "href": "docs/api/core.trainers.base.html", - "title": "core.trainers.base", + "objectID": "docs/api/index.html#kernels", + "href": "docs/api/index.html#kernels", + "title": "API Reference", "section": "", - "text": "core.trainers.base\nModule for customized trainers\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlTrainer\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_eval_dataloader\nGet dataloader for evaluation\n\n\nget_train_dataloader\nGet dataloader for training\n\n\nlog\nLog logs on the various objects watching training, including stored metrics.\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.get_eval_dataloader(eval_dataset=None)\nGet dataloader for evaluation\n\n\n\ncore.trainers.base.AxolotlTrainer.get_train_dataloader()\nGet dataloader for training\n\n\n\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\nLog logs on the various objects watching training, including stored metrics.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nlogs\ndict[str, float]\nThe values to log.\nrequired\n\n\nstart_time\nfloat | None\nThe start of training.\nNone\n\n\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\nmodel on the Hub. Please refer to ~transformers.Trainer.push_to_hub for more details." + "text": "Low-level performance optimizations\n\n\n\nkernels.lora\nModule for definition of Low-Rank Adaptation (LoRA) Triton kernels.\n\n\nkernels.geglu\nModule for definition of GEGLU Triton kernels.\n\n\nkernels.swiglu\nModule for definition of SwiGLU Triton kernels.\n\n\nkernels.quantize\nDequantization utilities for bitsandbytes integration.\n\n\nkernels.utils\nUtilities for axolotl.kernels submodules." }, { - "objectID": "docs/api/core.trainers.base.html#classes", - "href": "docs/api/core.trainers.base.html#classes", - "title": "core.trainers.base", + "objectID": "docs/api/index.html#monkey-patches", + "href": "docs/api/index.html#monkey-patches", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nAxolotlTrainer\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_eval_dataloader\nGet dataloader for evaluation\n\n\nget_train_dataloader\nGet dataloader for training\n\n\nlog\nLog logs on the various objects watching training, including stored metrics.\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.get_eval_dataloader(eval_dataset=None)\nGet dataloader for evaluation\n\n\n\ncore.trainers.base.AxolotlTrainer.get_train_dataloader()\nGet dataloader for training\n\n\n\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\nLog logs on the various objects watching training, including stored metrics.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nlogs\ndict[str, float]\nThe values to log.\nrequired\n\n\nstart_time\nfloat | None\nThe start of training.\nNone\n\n\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\nmodel on the Hub. Please refer to ~transformers.Trainer.push_to_hub for more details." + "text": "Runtime patches for model optimizations\n\n\n\nmonkeypatch.llama_attn_hijack_flash\nFlash attention monkey patch for llama model\n\n\nmonkeypatch.llama_attn_hijack_xformers\nDirectly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments\n\n\nmonkeypatch.mistral_attn_hijack_flash\nFlash attention monkey patch for mistral model\n\n\nmonkeypatch.multipack\nmultipack patching for v2 of sample packing\n\n\nmonkeypatch.relora\nImplements the ReLoRA training procedure from https://arxiv.org/abs/2307.05695, minus the initial full fine-tune.\n\n\nmonkeypatch.llama_expand_mask\nexpands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf\n\n\nmonkeypatch.lora_kernels\nModule for patching custom LoRA Triton kernels and torch.autograd functions.\n\n\nmonkeypatch.utils\nShared utils for the monkeypatches\n\n\nmonkeypatch.btlm_attn_hijack_flash\nFlash attention monkey patch for cerebras btlm model\n\n\nmonkeypatch.llama_patch_multipack\nPatched LlamaAttention to use torch.nn.functional.scaled_dot_product_attention\n\n\nmonkeypatch.stablelm_attn_hijack_flash\nPyTorch StableLM Epoch model.\n\n\nmonkeypatch.trainer_fsdp_optim\nfix for FSDP optimizer save in trainer w 4.47.0\n\n\nmonkeypatch.transformers_fa_utils\nsee https://github.com/huggingface/transformers/pull/35834\n\n\nmonkeypatch.unsloth_\nmodule for patching with unsloth optimizations\n\n\nmonkeypatch.attention.mllama\nMonkeypatch for Vision Llama for FA2 support\n\n\nmonkeypatch.data.batch_dataset_fetcher\nmonkey patches for the dataset fetcher to handle batches of packed indexes\n\n\nmonkeypatch.mixtral\nPatches to support multipack for mixtral" }, { - "objectID": "docs/api/monkeypatch.relora.html", - "href": "docs/api/monkeypatch.relora.html", - "title": "monkeypatch.relora", + "objectID": "docs/api/index.html#utils", + "href": "docs/api/index.html#utils", + "title": "API Reference", "section": "", - "text": "monkeypatch.relora\nImplements the ReLoRA training procedure from https://arxiv.org/abs/2307.05695, minus the initial full fine-tune.\n\n\n\n\n\nName\nDescription\n\n\n\n\nReLoRACallback\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\nReLoRAScheduler\nWraps another scheduler to apply per-lora-restart learning rate warmups.\n\n\n\n\n\nmonkeypatch.relora.ReLoRACallback(self, cfg)\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\n\nmonkeypatch.relora.ReLoRAScheduler(\n self,\n optimizer,\n inner_schedule,\n relora_steps,\n warmup_steps,\n anneal_steps=1,\n min_lr_scale=0.001,\n)\nWraps another scheduler to apply per-lora-restart learning rate warmups." + "text": "Utility functions\n\n\n\nutils.models\nModule for models and model loading\n\n\nutils.tokenization\nModule for tokenization utilities\n\n\nutils.chat_templates\nThis module provides functionality for selecting chat templates based on user choices.\n\n\nutils.lora\nmodule to get the state dict of a merged lora model\n\n\nutils.lora_embeddings\nhelpers for lora embeddings\n\n\nutils.model_shard_quant\nmodule to handle loading model on cpu/meta device for FSDP\n\n\nutils.bench\nBenchmarking and measurement utilities\n\n\nutils.freeze\nmodule to freeze/unfreeze parameters by name\n\n\nutils.trainer\nModule containing the Trainer class and related functions\n\n\nutils.schedulers\nModule for custom LRScheduler class\n\n\nutils.distributed\nutility helpers for distributed checks\n\n\nutils.dict\nModule containing the DictDefault class\n\n\nutils.optimizers.adopt\nCopied from https://github.com/iShohei220/adopt\n\n\nutils.data.pretraining\ndata handling specific to pretraining\n\n\nutils.data.sft\ndata handling specific to SFT\n\n\nutils.gradient_checkpointing.offload_cpu\nCPU offloaded checkpointing\n\n\nutils.gradient_checkpointing.offload_disk\nDISCO - DIsk-based Storage and Checkpointing with Optimized prefetching" }, { - "objectID": "docs/api/monkeypatch.relora.html#classes", - "href": "docs/api/monkeypatch.relora.html#classes", - "title": "monkeypatch.relora", + "objectID": "docs/api/index.html#schemas", + "href": "docs/api/index.html#schemas", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nReLoRACallback\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\nReLoRAScheduler\nWraps another scheduler to apply per-lora-restart learning rate warmups.\n\n\n\n\n\nmonkeypatch.relora.ReLoRACallback(self, cfg)\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\n\nmonkeypatch.relora.ReLoRAScheduler(\n self,\n optimizer,\n inner_schedule,\n relora_steps,\n warmup_steps,\n anneal_steps=1,\n min_lr_scale=0.001,\n)\nWraps another scheduler to apply per-lora-restart learning rate warmups." + "text": "Pydantic data models for Axolotl config\n\n\n\nutils.schemas.config\nModule with Pydantic models for configuration.\n\n\nutils.schemas.model\nPydantic models for model input / output, etc. configuration\n\n\nutils.schemas.training\nPydantic models for training hyperparameters\n\n\nutils.schemas.datasets\nPydantic models for datasets-related configuration\n\n\nutils.schemas.peft\nPydantic models for PEFT-related configuration\n\n\nutils.schemas.trl\nPydantic models for TRL trainer configuration\n\n\nutils.schemas.multimodal\nPydantic models for multimodal-related configuration\n\n\nutils.schemas.integrations\nPydantic models for Axolotl integrations\n\n\nutils.schemas.enums\nEnums for Axolotl input config\n\n\nutils.schemas.utils\nUtilities for Axolotl Pydantic models" }, { - "objectID": "docs/api/cli.cloud.modal_.html", - "href": "docs/api/cli.cloud.modal_.html", - "title": "cli.cloud.modal_", + "objectID": "docs/api/index.html#integrations", + "href": "docs/api/index.html#integrations", + "title": "API Reference", "section": "", - "text": "cli.cloud.modal_\nModal Cloud support from CLI\n\n\n\n\n\nName\nDescription\n\n\n\n\nModalCloud\nModal Cloud implementation.\n\n\n\n\n\ncli.cloud.modal_.ModalCloud(self, config, app=None)\nModal Cloud implementation.\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nrun_cmd\nRun a command inside a folder, with Modal Volume reloading before and commit on success.\n\n\n\n\n\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\nRun a command inside a folder, with Modal Volume reloading before and commit on success." + "text": "Third-party integrations and extensions\n\n\n\nintegrations.base\nBase class for all plugins.\n\n\nintegrations.cut_cross_entropy.args\nModule for handling Cut Cross Entropy input arguments.\n\n\nintegrations.grokfast.optimizer\n\n\n\nintegrations.kd.trainer\nKD trainer\n\n\nintegrations.liger.args\nModule for handling LIGER input arguments.\n\n\nintegrations.lm_eval.args\nModule for handling lm eval harness input arguments.\n\n\nintegrations.spectrum.args\nModule for handling Spectrum input arguments." }, { - "objectID": "docs/api/cli.cloud.modal_.html#classes", - "href": "docs/api/cli.cloud.modal_.html#classes", - "title": "cli.cloud.modal_", + "objectID": "docs/api/index.html#common", + "href": "docs/api/index.html#common", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nModalCloud\nModal Cloud implementation.\n\n\n\n\n\ncli.cloud.modal_.ModalCloud(self, config, app=None)\nModal Cloud implementation." + "text": "Common utilities and shared functionality\n\n\n\ncommon.architectures\nCommon architecture specific constants\n\n\ncommon.const\nVarious shared constants\n\n\ncommon.datasets\nDataset loading utilities." }, { - "objectID": "docs/api/cli.cloud.modal_.html#functions", - "href": "docs/api/cli.cloud.modal_.html#functions", - "title": "cli.cloud.modal_", + "objectID": "docs/api/index.html#models", + "href": "docs/api/index.html#models", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nrun_cmd\nRun a command inside a folder, with Modal Volume reloading before and commit on success.\n\n\n\n\n\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\nRun a command inside a folder, with Modal Volume reloading before and commit on success." + "text": "Custom model implementations\n\n\n\nmodels.mamba.modeling_mamba" }, { - "objectID": "docs/api/core.training_args.html", - "href": "docs/api/core.training_args.html", - "title": "core.training_args", + "objectID": "docs/api/index.html#data-processing", + "href": "docs/api/index.html#data-processing", + "title": "API Reference", "section": "", - "text": "core.training_args\nextra axolotl specific training args\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlCPOConfig\nCPO config for CPO training\n\n\nAxolotlKTOConfig\nKTO config for KTO training\n\n\nAxolotlORPOConfig\nORPO config for ORPO training\n\n\nAxolotlPRMConfig\nPRM config for PRM training\n\n\nAxolotlRewardConfig\nReward config for Reward training\n\n\nAxolotlTrainingArguments\nTraining arguments for Causal trainer\n\n\nAxolotlTrainingMixins\nMixin class for the Axolotl training args.\n\n\n\n\n\ncore.training_args.AxolotlCPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n simpo_gamma=None,\n)\nCPO config for CPO training\n\n\n\ncore.training_args.AxolotlKTOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nKTO config for KTO training\n\n\n\ncore.training_args.AxolotlORPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nORPO config for ORPO training\n\n\n\ncore.training_args.AxolotlPRMConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nPRM config for PRM training\n\n\n\ncore.training_args.AxolotlRewardConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nReward config for Reward training\n\n\n\ncore.training_args.AxolotlTrainingArguments(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nTraining arguments for Causal trainer\nThis code is duplicated due to HF TrainingArguments not setting output_dir with a\ndefault value so it can’t be used as a mixin.\n\n\n\ncore.training_args.AxolotlTrainingMixins(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nMixin class for the Axolotl training args." + "text": "Data processing utilities\n\n\n\nutils.collators.core\nbasic shared collator constants\n\n\nutils.collators.batching\nData collators for axolotl to pad labels and position_ids for packed sequences\n\n\nutils.collators.mamba\ncollators for Mamba\n\n\nutils.collators.mm_chat\nCollators for multi-modal chat messages and packing\n\n\nutils.samplers.multipack\nMultipack Batch Sampler - An efficient batch sampler for packing variable-length sequences" }, { - "objectID": "docs/api/core.training_args.html#classes", - "href": "docs/api/core.training_args.html#classes", - "title": "core.training_args", + "objectID": "docs/api/index.html#callbacks", + "href": "docs/api/index.html#callbacks", + "title": "API Reference", "section": "", - "text": "Name\nDescription\n\n\n\n\nAxolotlCPOConfig\nCPO config for CPO training\n\n\nAxolotlKTOConfig\nKTO config for KTO training\n\n\nAxolotlORPOConfig\nORPO config for ORPO training\n\n\nAxolotlPRMConfig\nPRM config for PRM training\n\n\nAxolotlRewardConfig\nReward config for Reward training\n\n\nAxolotlTrainingArguments\nTraining arguments for Causal trainer\n\n\nAxolotlTrainingMixins\nMixin class for the Axolotl training args.\n\n\n\n\n\ncore.training_args.AxolotlCPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n simpo_gamma=None,\n)\nCPO config for CPO training\n\n\n\ncore.training_args.AxolotlKTOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nKTO config for KTO training\n\n\n\ncore.training_args.AxolotlORPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nORPO config for ORPO training\n\n\n\ncore.training_args.AxolotlPRMConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nPRM config for PRM training\n\n\n\ncore.training_args.AxolotlRewardConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nReward config for Reward training\n\n\n\ncore.training_args.AxolotlTrainingArguments(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nTraining arguments for Causal trainer\nThis code is duplicated due to HF TrainingArguments not setting output_dir with a\ndefault value so it can’t be used as a mixin.\n\n\n\ncore.training_args.AxolotlTrainingMixins(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n sequence_parallel_degree=1,\n ring_attn_func=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nMixin class for the Axolotl training args." + "text": "Training callbacks\n\n\n\nutils.callbacks.perplexity\ncallback to calculate perplexity as an evaluation metric.\n\n\nutils.callbacks.profiler\nHF Trainer callback for creating pytorch profiling snapshots\n\n\nutils.callbacks.lisa\nmodule for LISA\n\n\nutils.callbacks.mlflow_\nMLFlow module for trainer callbacks\n\n\nutils.callbacks.comet_\nComet module for trainer callbacks" }, { - "objectID": "docs/api/utils.callbacks.comet_.html", - "href": "docs/api/utils.callbacks.comet_.html", - "title": "utils.callbacks.comet_", + "objectID": "docs/api/monkeypatch.llama_patch_multipack.html", + "href": "docs/api/monkeypatch.llama_patch_multipack.html", + "title": "monkeypatch.llama_patch_multipack", "section": "", - "text": "utils.callbacks.comet_\nComet module for trainer callbacks\n\n\n\n\n\nName\nDescription\n\n\n\n\nSaveAxolotlConfigtoCometCallback\nCallback to save axolotl config to comet\n\n\n\n\n\nutils.callbacks.comet_.SaveAxolotlConfigtoCometCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to comet" + "text": "monkeypatch.llama_patch_multipack\nmonkeypatch.llama_patch_multipack\nPatched LlamaAttention to use torch.nn.functional.scaled_dot_product_attention" }, { - "objectID": "docs/api/utils.callbacks.comet_.html#classes", - "href": "docs/api/utils.callbacks.comet_.html#classes", - "title": "utils.callbacks.comet_", + "objectID": "docs/api/prompt_strategies.messages.chat.html", + "href": "docs/api/prompt_strategies.messages.chat.html", + "title": "prompt_strategies.messages.chat", "section": "", - "text": "Name\nDescription\n\n\n\n\nSaveAxolotlConfigtoCometCallback\nCallback to save axolotl config to comet\n\n\n\n\n\nutils.callbacks.comet_.SaveAxolotlConfigtoCometCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to comet" + "text": "prompt_strategies.messages.chat\nChat dataset wrapping strategy for new internal messages representations\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatMessageDatasetWrappingStrategy\nChat dataset wrapping strategy for new internal messages representations\n\n\n\n\n\nprompt_strategies.messages.chat.ChatMessageDatasetWrappingStrategy(\n self,\n processor,\n message_transform=None,\n formatter=None,\n **kwargs,\n)\nChat dataset wrapping strategy for new internal messages representations" }, { - "objectID": "docs/api/core.chat.format.shared.html", - "href": "docs/api/core.chat.format.shared.html", - "title": "core.chat.format.shared", + "objectID": "docs/api/prompt_strategies.messages.chat.html#classes", + "href": "docs/api/prompt_strategies.messages.chat.html#classes", + "title": "prompt_strategies.messages.chat", "section": "", - "text": "core.chat.format.shared\ncore.chat.format.shared\nshared functions for format transforms" + "text": "Name\nDescription\n\n\n\n\nChatMessageDatasetWrappingStrategy\nChat dataset wrapping strategy for new internal messages representations\n\n\n\n\n\nprompt_strategies.messages.chat.ChatMessageDatasetWrappingStrategy(\n self,\n processor,\n message_transform=None,\n formatter=None,\n **kwargs,\n)\nChat dataset wrapping strategy for new internal messages representations" }, { - "objectID": "docs/api/monkeypatch.lora_kernels.html", - "href": "docs/api/monkeypatch.lora_kernels.html", - "title": "monkeypatch.lora_kernels", + "objectID": "docs/api/utils.gradient_checkpointing.offload_cpu.html", + "href": "docs/api/utils.gradient_checkpointing.offload_cpu.html", + "title": "utils.gradient_checkpointing.offload_cpu", "section": "", - "text": "monkeypatch.lora_kernels\nModule for patching custom LoRA Triton kernels and torch.autograd functions.\n\n\n\n\n\nName\nDescription\n\n\n\n\nFakeMLP\nplaceholder MLP for triton patching\n\n\n\n\n\nmonkeypatch.lora_kernels.FakeMLP(self, gate_proj, up_proj, down_proj)\nplaceholder MLP for triton patching\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\napply_lora_kernel_patches\nApplies optimized Triton kernel patches to a PEFT model.\n\n\nget_attention_cls_from_config\nGet the appropriate attention class by inspecting the model config.\n\n\noriginal_apply_o\nOriginal implementation of output projection without optimizations.\n\n\noriginal_apply_qkv\nOriginal implementation of QKV projection without optimizations.\n\n\npatch_self_attn_lora\nGiven an axolotl config, this method patches the inferred attention class forward\n\n\n\n\n\nmonkeypatch.lora_kernels.apply_lora_kernel_patches(model, cfg)\nApplies optimized Triton kernel patches to a PEFT model.\nPatches a PEFT model with optimized implementations for MLP and attention\ncomputations. The optimizations include custom Triton kernels for activation\nfunctions and specialized autograd functions for LoRA computations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\nPeftModelForCausalLM\nA PEFT model to be patched with optimized kernels.\nrequired\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nPeftModelForCausalLM\nPeftModelForCausalLM\nThe patched model with optimized kernels.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTypeError\nIf the provided model is not a PeftModelForCausalLM.\n\n\n\nNotImplementedError\nIf the model type is not supported.\n\n\n\nAssertionError\nIf multiple adapters are active (currently unsupported).\n\n\n\n\n\n\nThe optimizations require LoRA adapters with no dropout and no bias terms. The\nfunction will skip patching if these conditions aren’t met.\n\n\n\n\nmonkeypatch.lora_kernels.get_attention_cls_from_config(cfg)\nGet the appropriate attention class by inspecting the model config.\nUses dynamic import to support any model architecture that follows\nthe standard transformers naming convention.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nType[nn.Module]\nThe appropriate attention class for the model.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf base_model not specified or attention class cannot be imported\n\n\n\nImportError\nIf the model module or attention class doesn’t exist\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_o(self, hidden_states)\nOriginal implementation of output projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim]`.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nThe output projection result.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_qkv(self, hidden_states)\nOriginal implementation of QKV projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nA tuple (query_states, key_states, value_states) containing the projected states for query, key, and value.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.patch_self_attn_lora(cfg)\nGiven an axolotl config, this method patches the inferred attention class forward\npass with optimized LoRA implementations.\nIt modifies the attention class to use optimized QKV and output projections. The\noriginal implementation is preserved and can be restored if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf the required code blocks are not found in the attention implementation." + "text": "utils.gradient_checkpointing.offload_cpu\nCPU offloaded checkpointing\n\n\n\n\n\nName\nDescription\n\n\n\n\nCPU_Offloaded_Gradient_Checkpointer\nSaves VRAM by smartly offloading to RAM.\n\n\n\n\n\nutils.gradient_checkpointing.offload_cpu.CPU_Offloaded_Gradient_Checkpointer()\nSaves VRAM by smartly offloading to RAM.\nTiny hit to performance, since we mask the movement via non blocking calls." }, { - "objectID": "docs/api/monkeypatch.lora_kernels.html#classes", - "href": "docs/api/monkeypatch.lora_kernels.html#classes", - "title": "monkeypatch.lora_kernels", + "objectID": "docs/api/utils.gradient_checkpointing.offload_cpu.html#classes", + "href": "docs/api/utils.gradient_checkpointing.offload_cpu.html#classes", + "title": "utils.gradient_checkpointing.offload_cpu", "section": "", - "text": "Name\nDescription\n\n\n\n\nFakeMLP\nplaceholder MLP for triton patching\n\n\n\n\n\nmonkeypatch.lora_kernels.FakeMLP(self, gate_proj, up_proj, down_proj)\nplaceholder MLP for triton patching" + "text": "Name\nDescription\n\n\n\n\nCPU_Offloaded_Gradient_Checkpointer\nSaves VRAM by smartly offloading to RAM.\n\n\n\n\n\nutils.gradient_checkpointing.offload_cpu.CPU_Offloaded_Gradient_Checkpointer()\nSaves VRAM by smartly offloading to RAM.\nTiny hit to performance, since we mask the movement via non blocking calls." }, { - "objectID": "docs/api/monkeypatch.lora_kernels.html#functions", - "href": "docs/api/monkeypatch.lora_kernels.html#functions", - "title": "monkeypatch.lora_kernels", + "objectID": "docs/api/train.html", + "href": "docs/api/train.html", + "title": "train", "section": "", - "text": "Name\nDescription\n\n\n\n\napply_lora_kernel_patches\nApplies optimized Triton kernel patches to a PEFT model.\n\n\nget_attention_cls_from_config\nGet the appropriate attention class by inspecting the model config.\n\n\noriginal_apply_o\nOriginal implementation of output projection without optimizations.\n\n\noriginal_apply_qkv\nOriginal implementation of QKV projection without optimizations.\n\n\npatch_self_attn_lora\nGiven an axolotl config, this method patches the inferred attention class forward\n\n\n\n\n\nmonkeypatch.lora_kernels.apply_lora_kernel_patches(model, cfg)\nApplies optimized Triton kernel patches to a PEFT model.\nPatches a PEFT model with optimized implementations for MLP and attention\ncomputations. The optimizations include custom Triton kernels for activation\nfunctions and specialized autograd functions for LoRA computations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\nPeftModelForCausalLM\nA PEFT model to be patched with optimized kernels.\nrequired\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nPeftModelForCausalLM\nPeftModelForCausalLM\nThe patched model with optimized kernels.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTypeError\nIf the provided model is not a PeftModelForCausalLM.\n\n\n\nNotImplementedError\nIf the model type is not supported.\n\n\n\nAssertionError\nIf multiple adapters are active (currently unsupported).\n\n\n\n\n\n\nThe optimizations require LoRA adapters with no dropout and no bias terms. The\nfunction will skip patching if these conditions aren’t met.\n\n\n\n\nmonkeypatch.lora_kernels.get_attention_cls_from_config(cfg)\nGet the appropriate attention class by inspecting the model config.\nUses dynamic import to support any model architecture that follows\nthe standard transformers naming convention.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nType[nn.Module]\nThe appropriate attention class for the model.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf base_model not specified or attention class cannot be imported\n\n\n\nImportError\nIf the model module or attention class doesn’t exist\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_o(self, hidden_states)\nOriginal implementation of output projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim]`.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nThe output projection result.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_qkv(self, hidden_states)\nOriginal implementation of QKV projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nA tuple (query_states, key_states, value_states) containing the projected states for query, key, and value.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.patch_self_attn_lora(cfg)\nGiven an axolotl config, this method patches the inferred attention class forward\npass with optimized LoRA implementations.\nIt modifies the attention class to use optimized QKV and output projections. The\noriginal implementation is preserved and can be restored if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf the required code blocks are not found in the attention implementation." + "text": "train\nPrepare and train a model on a dataset. Can also infer from a model or merge lora\n\n\n\n\n\nName\nDescription\n\n\n\n\ncreate_model_card\nCreate a model card for the trained model if needed.\n\n\ndetermine_resume_checkpoint\nDetermine the checkpoint to resume from based on configuration.\n\n\nexecute_training\nExecute the training process with appropriate SDP kernel configurations.\n\n\nhandle_untrained_tokens_fix\nApply fixes for untrained tokens if configured.\n\n\nsave_initial_configs\nSave initial configurations before training.\n\n\nsave_trained_model\nSave the trained model according to configuration and training setup.\n\n\nsetup_model_and_tokenizer\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\nsetup_model_and_trainer\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\n\n\nsetup_model_card\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\nsetup_reference_model\nSet up the reference model for RL training if needed.\n\n\nsetup_signal_handler\nSet up signal handler for graceful termination.\n\n\ntrain\nTrain a model on the given dataset.\n\n\n\n\n\ntrain.create_model_card(cfg, trainer)\nCreate a model card for the trained model if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nTrainer\nThe trainer object with model card creation capabilities.\nrequired\n\n\n\n\n\n\n\ntrain.determine_resume_checkpoint(cfg)\nDetermine the checkpoint to resume from based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr | None\nPath to the checkpoint to resume from, or None if not resuming.\n\n\n\n\n\n\n\ntrain.execute_training(cfg, trainer, resume_from_checkpoint)\nExecute the training process with appropriate SDP kernel configurations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe configured trainer object.\nrequired\n\n\nresume_from_checkpoint\nstr | None\nPath to checkpoint to resume from, if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.handle_untrained_tokens_fix(\n cfg,\n model,\n tokenizer,\n train_dataset,\n safe_serialization,\n)\nApply fixes for untrained tokens if configured.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to apply fixes to.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer for token identification.\nrequired\n\n\ntrain_dataset\nDataset\nThe training dataset to use.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving.\nrequired\n\n\n\n\n\n\n\ntrain.save_initial_configs(cfg, tokenizer, model, peft_config, processor)\nSave initial configurations before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to save.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save configuration for.\nrequired\n\n\npeft_config\nPeftConfig | None\nThe PEFT configuration to save if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.save_trained_model(cfg, trainer, model, safe_serialization)\nSave the trained model according to configuration and training setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe trainer object.\nrequired\n\n\nmodel\nPreTrainedModel\nThe trained model to save.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization.\nrequired\n\n\n\n\n\n\n\ntrain.setup_model_and_tokenizer(cfg)\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple containing model, tokenizer, peft_config (if LoRA / QLoRA, else None), and processor (if multimodal, else None).\n\n\n\n\n\n\n\ntrain.setup_model_and_trainer(cfg, dataset_meta)\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\ntrainer setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[HFRLTrainerBuilder | HFCausalTrainerBuilder, PeftModel | PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple of: - Trainer (Causal or RLHF) - Model - Tokenizer - PEFT config - Processor\n\n\n\n\n\n\n\ntrain.setup_model_card(cfg)\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\ntrain.setup_reference_model(cfg, tokenizer)\nSet up the reference model for RL training if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to use for the reference model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nPreTrainedModel | None\nReference model if needed for RL training, None otherwise.\n\n\n\n\n\n\n\ntrain.setup_signal_handler(cfg, model, safe_serialization)\nSet up signal handler for graceful termination.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save on termination\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving\nrequired\n\n\n\n\n\n\n\ntrain.train(cfg, dataset_meta)\nTrain a model on the given dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PeftModel | PreTrainedModel, PreTrainedTokenizer, Trainer]\nTuple of (model, tokenizer) after training" }, { - "objectID": "docs/api/cli.merge_lora.html", - "href": "docs/api/cli.merge_lora.html", - "title": "cli.merge_lora", + "objectID": "docs/api/train.html#functions", + "href": "docs/api/train.html#functions", + "title": "train", "section": "", - "text": "cli.merge_lora\nCLI to merge a trained LoRA into a base model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\n\n\ndo_merge_lora\nCalls transformers’ merge_and_unload on the model given in the axolotl config\n\n\n\n\n\ncli.merge_lora.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\nconfig values will be overwritten to allow the LoRA merge logic to work as expected\n(load_in_8bit=False, load_in4bit=False, flash_attention=False, etc.).\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf target directory for LoRA merged model does not exist.\n\n\n\n\n\n\n\ncli.merge_lora.do_merge_lora(cfg)\nCalls transformers’ merge_and_unload on the model given in the axolotl config\nalong with the LoRA adapters to combine them into a single base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" + "text": "Name\nDescription\n\n\n\n\ncreate_model_card\nCreate a model card for the trained model if needed.\n\n\ndetermine_resume_checkpoint\nDetermine the checkpoint to resume from based on configuration.\n\n\nexecute_training\nExecute the training process with appropriate SDP kernel configurations.\n\n\nhandle_untrained_tokens_fix\nApply fixes for untrained tokens if configured.\n\n\nsave_initial_configs\nSave initial configurations before training.\n\n\nsave_trained_model\nSave the trained model according to configuration and training setup.\n\n\nsetup_model_and_tokenizer\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\nsetup_model_and_trainer\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\n\n\nsetup_model_card\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\nsetup_reference_model\nSet up the reference model for RL training if needed.\n\n\nsetup_signal_handler\nSet up signal handler for graceful termination.\n\n\ntrain\nTrain a model on the given dataset.\n\n\n\n\n\ntrain.create_model_card(cfg, trainer)\nCreate a model card for the trained model if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nTrainer\nThe trainer object with model card creation capabilities.\nrequired\n\n\n\n\n\n\n\ntrain.determine_resume_checkpoint(cfg)\nDetermine the checkpoint to resume from based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr | None\nPath to the checkpoint to resume from, or None if not resuming.\n\n\n\n\n\n\n\ntrain.execute_training(cfg, trainer, resume_from_checkpoint)\nExecute the training process with appropriate SDP kernel configurations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe configured trainer object.\nrequired\n\n\nresume_from_checkpoint\nstr | None\nPath to checkpoint to resume from, if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.handle_untrained_tokens_fix(\n cfg,\n model,\n tokenizer,\n train_dataset,\n safe_serialization,\n)\nApply fixes for untrained tokens if configured.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to apply fixes to.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer for token identification.\nrequired\n\n\ntrain_dataset\nDataset\nThe training dataset to use.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving.\nrequired\n\n\n\n\n\n\n\ntrain.save_initial_configs(cfg, tokenizer, model, peft_config, processor)\nSave initial configurations before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to save.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save configuration for.\nrequired\n\n\npeft_config\nPeftConfig | None\nThe PEFT configuration to save if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.save_trained_model(cfg, trainer, model, safe_serialization)\nSave the trained model according to configuration and training setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe trainer object.\nrequired\n\n\nmodel\nPreTrainedModel\nThe trained model to save.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization.\nrequired\n\n\n\n\n\n\n\ntrain.setup_model_and_tokenizer(cfg)\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple containing model, tokenizer, peft_config (if LoRA / QLoRA, else None), and processor (if multimodal, else None).\n\n\n\n\n\n\n\ntrain.setup_model_and_trainer(cfg, dataset_meta)\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\ntrainer setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[HFRLTrainerBuilder | HFCausalTrainerBuilder, PeftModel | PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple of: - Trainer (Causal or RLHF) - Model - Tokenizer - PEFT config - Processor\n\n\n\n\n\n\n\ntrain.setup_model_card(cfg)\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\ntrain.setup_reference_model(cfg, tokenizer)\nSet up the reference model for RL training if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to use for the reference model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nPreTrainedModel | None\nReference model if needed for RL training, None otherwise.\n\n\n\n\n\n\n\ntrain.setup_signal_handler(cfg, model, safe_serialization)\nSet up signal handler for graceful termination.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save on termination\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving\nrequired\n\n\n\n\n\n\n\ntrain.train(cfg, dataset_meta)\nTrain a model on the given dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PeftModel | PreTrainedModel, PreTrainedTokenizer, Trainer]\nTuple of (model, tokenizer) after training" }, { - "objectID": "docs/api/cli.merge_lora.html#functions", - "href": "docs/api/cli.merge_lora.html#functions", - "title": "cli.merge_lora", + "objectID": "docs/api/monkeypatch.llama_attn_hijack_xformers.html", + "href": "docs/api/monkeypatch.llama_attn_hijack_xformers.html", + "title": "monkeypatch.llama_attn_hijack_xformers", "section": "", - "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\n\n\ndo_merge_lora\nCalls transformers’ merge_and_unload on the model given in the axolotl config\n\n\n\n\n\ncli.merge_lora.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\nconfig values will be overwritten to allow the LoRA merge logic to work as expected\n(load_in_8bit=False, load_in4bit=False, flash_attention=False, etc.).\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf target directory for LoRA merged model does not exist.\n\n\n\n\n\n\n\ncli.merge_lora.do_merge_lora(cfg)\nCalls transformers’ merge_and_unload on the model given in the axolotl config\nalong with the LoRA adapters to combine them into a single base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" + "text": "monkeypatch.llama_attn_hijack_xformers\nmonkeypatch.llama_attn_hijack_xformers\nDirectly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments" }, { - "objectID": "docs/api/utils.trainer.html", - "href": "docs/api/utils.trainer.html", - "title": "utils.trainer", + "objectID": "docs/api/cli.args.html", + "href": "docs/api/cli.args.html", + "title": "cli.args", "section": "", - "text": "utils.trainer\nModule containing the Trainer class and related functions\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_pose_position_ids\nuse the PoSE technique to extend the context length by randomly skipping\n\n\nadd_position_ids\nHandle both single-example and batched data.\n\n\ndrop_long_seq\nDrop samples whose sequence length is either too long (> sequence_len)\n\n\nsetup_trainer\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\nutils.trainer.add_pose_position_ids(\n sample,\n max_context_len=32768,\n split_on_token_ids=None,\n chunks=2,\n)\nuse the PoSE technique to extend the context length by randomly skipping\npositions in the context. We only want to skip right before tokens in\nthe split_on_token_ids list. We should attempt to randomly distribute\nthe skips, but we don’t need the final position_ids to be the full\ncontext_len. There may be multiple turns in the context, so we want to\nmake sure we take into account the maximum possible number of skips\nremaining in each sample.\n\n\n\nutils.trainer.add_position_ids(sample)\nHandle both single-example and batched data.\n- single example: sample[‘input_ids’] is a list[int]\n- batched data: sample[‘input_ids’] is a list[list[int]]\n\n\n\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\nDrop samples whose sequence length is either too long (> sequence_len)\nor too short (< min_sequence_len).\nWorks for both single-example (list[int]) or batched (list[list[int]]).\n\n\n\nutils.trainer.setup_trainer(\n cfg,\n train_dataset,\n eval_dataset,\n model,\n tokenizer,\n processor,\n total_num_steps,\n model_ref=None,\n peft_config=None,\n)\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nAxolotl config object containing training parameters.\nrequired\n\n\ntrain_dataset\n\nDataset to use for training.\nrequired\n\n\neval_dataset\n\nDataset to use for evaluation.\nrequired\n\n\nmodel\n\nThe model to train.\nrequired\n\n\ntokenizer\n\nTokenizer for processing text input.\nrequired\n\n\nprocessor\n\nProcessor for data preparation.\nrequired\n\n\ntotal_num_steps\n\nThe total number of training steps.\nrequired\n\n\nmodel_ref\n\nOptional reference model for RLHF training. Default is None.\nNone\n\n\npeft_config\n\nOptional PEFT (Parameter-Efficient Fine-Tuning) configuration. Default is None.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nA trainer instance (either HFRLTrainer or HFCausalTrainer) configured based on the provided parameters." + "text": "cli.args\nModule for axolotl CLI command arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nEvaluateCliArgs\nDataclass with CLI arguments for axolotl evaluate command.\n\n\nInferenceCliArgs\nDataclass with CLI arguments for axolotl inference command.\n\n\nPreprocessCliArgs\nDataclass with CLI arguments for axolotl preprocess command.\n\n\nTrainerCliArgs\nDataclass with CLI arguments for axolotl train command.\n\n\nVllmServeCliArgs\nDataclass with CLI arguments for axolotl vllm-serve command.\n\n\n\n\n\ncli.args.EvaluateCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n)\nDataclass with CLI arguments for axolotl evaluate command.\n\n\n\ncli.args.InferenceCliArgs(self, prompter=None)\nDataclass with CLI arguments for axolotl inference command.\n\n\n\ncli.args.PreprocessCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=1,\n prompter=None,\n download=True,\n iterable=None,\n)\nDataclass with CLI arguments for axolotl preprocess command.\n\n\n\ncli.args.TrainerCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n merge_lora=False,\n prompter=None,\n shard=False,\n main_process_port=None,\n num_processes=None,\n)\nDataclass with CLI arguments for axolotl train command.\n\n\n\ncli.args.VllmServeCliArgs(\n self,\n tensor_parallel_size=None,\n host=None,\n port=None,\n gpu_memory_utilization=None,\n dtype=None,\n max_model_len=None,\n enable_prefix_caching=None,\n serve_module=None,\n)\nDataclass with CLI arguments for axolotl vllm-serve command." }, { - "objectID": "docs/api/utils.trainer.html#functions", - "href": "docs/api/utils.trainer.html#functions", - "title": "utils.trainer", + "objectID": "docs/api/cli.args.html#classes", + "href": "docs/api/cli.args.html#classes", + "title": "cli.args", "section": "", - "text": "Name\nDescription\n\n\n\n\nadd_pose_position_ids\nuse the PoSE technique to extend the context length by randomly skipping\n\n\nadd_position_ids\nHandle both single-example and batched data.\n\n\ndrop_long_seq\nDrop samples whose sequence length is either too long (> sequence_len)\n\n\nsetup_trainer\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\nutils.trainer.add_pose_position_ids(\n sample,\n max_context_len=32768,\n split_on_token_ids=None,\n chunks=2,\n)\nuse the PoSE technique to extend the context length by randomly skipping\npositions in the context. We only want to skip right before tokens in\nthe split_on_token_ids list. We should attempt to randomly distribute\nthe skips, but we don’t need the final position_ids to be the full\ncontext_len. There may be multiple turns in the context, so we want to\nmake sure we take into account the maximum possible number of skips\nremaining in each sample.\n\n\n\nutils.trainer.add_position_ids(sample)\nHandle both single-example and batched data.\n- single example: sample[‘input_ids’] is a list[int]\n- batched data: sample[‘input_ids’] is a list[list[int]]\n\n\n\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\nDrop samples whose sequence length is either too long (> sequence_len)\nor too short (< min_sequence_len).\nWorks for both single-example (list[int]) or batched (list[list[int]]).\n\n\n\nutils.trainer.setup_trainer(\n cfg,\n train_dataset,\n eval_dataset,\n model,\n tokenizer,\n processor,\n total_num_steps,\n model_ref=None,\n peft_config=None,\n)\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nAxolotl config object containing training parameters.\nrequired\n\n\ntrain_dataset\n\nDataset to use for training.\nrequired\n\n\neval_dataset\n\nDataset to use for evaluation.\nrequired\n\n\nmodel\n\nThe model to train.\nrequired\n\n\ntokenizer\n\nTokenizer for processing text input.\nrequired\n\n\nprocessor\n\nProcessor for data preparation.\nrequired\n\n\ntotal_num_steps\n\nThe total number of training steps.\nrequired\n\n\nmodel_ref\n\nOptional reference model for RLHF training. Default is None.\nNone\n\n\npeft_config\n\nOptional PEFT (Parameter-Efficient Fine-Tuning) configuration. Default is None.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nA trainer instance (either HFRLTrainer or HFCausalTrainer) configured based on the provided parameters." + "text": "Name\nDescription\n\n\n\n\nEvaluateCliArgs\nDataclass with CLI arguments for axolotl evaluate command.\n\n\nInferenceCliArgs\nDataclass with CLI arguments for axolotl inference command.\n\n\nPreprocessCliArgs\nDataclass with CLI arguments for axolotl preprocess command.\n\n\nTrainerCliArgs\nDataclass with CLI arguments for axolotl train command.\n\n\nVllmServeCliArgs\nDataclass with CLI arguments for axolotl vllm-serve command.\n\n\n\n\n\ncli.args.EvaluateCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n)\nDataclass with CLI arguments for axolotl evaluate command.\n\n\n\ncli.args.InferenceCliArgs(self, prompter=None)\nDataclass with CLI arguments for axolotl inference command.\n\n\n\ncli.args.PreprocessCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=1,\n prompter=None,\n download=True,\n iterable=None,\n)\nDataclass with CLI arguments for axolotl preprocess command.\n\n\n\ncli.args.TrainerCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n merge_lora=False,\n prompter=None,\n shard=False,\n main_process_port=None,\n num_processes=None,\n)\nDataclass with CLI arguments for axolotl train command.\n\n\n\ncli.args.VllmServeCliArgs(\n self,\n tensor_parallel_size=None,\n host=None,\n port=None,\n gpu_memory_utilization=None,\n dtype=None,\n max_model_len=None,\n enable_prefix_caching=None,\n serve_module=None,\n)\nDataclass with CLI arguments for axolotl vllm-serve command." }, { - "objectID": "docs/api/utils.dict.html", - "href": "docs/api/utils.dict.html", - "title": "utils.dict", + "objectID": "docs/api/utils.schemas.enums.html", + "href": "docs/api/utils.schemas.enums.html", + "title": "utils.schemas.enums", "section": "", - "text": "utils.dict\nModule containing the DictDefault class\n\n\n\n\n\nName\nDescription\n\n\n\n\nDictDefault\nA Dict that returns None instead of returning empty Dict for missing keys.\n\n\n\n\n\nutils.dict.DictDefault()\nA Dict that returns None instead of returning empty Dict for missing keys." + "text": "utils.schemas.enums\nEnums for Axolotl input config\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatTemplate\nChat templates configuration subset\n\n\nCustomSupportedOptimizers\nCustom supported optimizers\n\n\nRLType\nRL trainer type configuration subset\n\n\nRingAttnFunc\nEnum class for supported ring-flash-attn implementations\n\n\n\n\n\nutils.schemas.enums.ChatTemplate()\nChat templates configuration subset\n\n\n\nutils.schemas.enums.CustomSupportedOptimizers()\nCustom supported optimizers\n\n\n\nutils.schemas.enums.RLType()\nRL trainer type configuration subset\n\n\n\nutils.schemas.enums.RingAttnFunc()\nEnum class for supported ring-flash-attn implementations" }, { - "objectID": "docs/api/utils.dict.html#classes", - "href": "docs/api/utils.dict.html#classes", - "title": "utils.dict", + "objectID": "docs/api/utils.schemas.enums.html#classes", + "href": "docs/api/utils.schemas.enums.html#classes", + "title": "utils.schemas.enums", "section": "", - "text": "Name\nDescription\n\n\n\n\nDictDefault\nA Dict that returns None instead of returning empty Dict for missing keys.\n\n\n\n\n\nutils.dict.DictDefault()\nA Dict that returns None instead of returning empty Dict for missing keys." + "text": "Name\nDescription\n\n\n\n\nChatTemplate\nChat templates configuration subset\n\n\nCustomSupportedOptimizers\nCustom supported optimizers\n\n\nRLType\nRL trainer type configuration subset\n\n\nRingAttnFunc\nEnum class for supported ring-flash-attn implementations\n\n\n\n\n\nutils.schemas.enums.ChatTemplate()\nChat templates configuration subset\n\n\n\nutils.schemas.enums.CustomSupportedOptimizers()\nCustom supported optimizers\n\n\n\nutils.schemas.enums.RLType()\nRL trainer type configuration subset\n\n\n\nutils.schemas.enums.RingAttnFunc()\nEnum class for supported ring-flash-attn implementations" }, { - "objectID": "docs/api/kernels.quantize.html", - "href": "docs/api/kernels.quantize.html", - "title": "kernels.quantize", + "objectID": "docs/api/utils.schemas.datasets.html", + "href": "docs/api/utils.schemas.datasets.html", + "title": "utils.schemas.datasets", "section": "", - "text": "kernels.quantize\nDequantization utilities for bitsandbytes integration.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndequantize\nFast NF4 dequantization using bitsandbytes CUDA kernels.\n\n\n\n\n\nkernels.quantize.dequantize(W, quant_state=None, out=None)\nFast NF4 dequantization using bitsandbytes CUDA kernels.\nPerforms efficient dequantization of weights from NF4 format using bitsandbytes’\noptimized CUDA implementations. Supports both legacy list and new QuantState\nformats.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nW\ntorch.Tensor\nQuantized weight tensor to dequantize\nrequired\n\n\nquant_state\nQuantState | list | None\nQuantization state containing metadata needed for dequantization. Can be either a QuantState object or legacy list format. If None, returns W unchanged.\nNone\n\n\nout\ntorch.Tensor | None\nOptional output tensor for storing dequantized results. Must match expected shape and dtype if provided.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nDequantized tensor in the specified dtype (fp16 or bf16). Will be transposed if\n\n\n\ntorch.Tensor\ninput W was transposed.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf provided output tensor doesn’t match expected shape / dtype.\n\n\n\n\n\n\nUses CUDA streams for better performance when available in newer bitsandbytes\nversions (>0.43.3)." + "text": "utils.schemas.datasets\nPydantic models for datasets-related configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nDPODataset\nDPO configuration subset\n\n\nKTODataset\nKTO configuration subset\n\n\nPretrainingDataset\nPretraining dataset configuration subset\n\n\nSFTDataset\nSFT configuration subset\n\n\nStepwiseSupervisedDataset\nStepwise supervised dataset configuration subset\n\n\nUserDefinedDPOType\nUser defined typing for DPO\n\n\nUserDefinedKTOType\nUser defined typing for KTO\n\n\nUserDefinedPrompterType\nStructure for user defined prompt types\n\n\n\n\n\nutils.schemas.datasets.DPODataset()\nDPO configuration subset\n\n\n\nutils.schemas.datasets.KTODataset()\nKTO configuration subset\n\n\n\nutils.schemas.datasets.PretrainingDataset()\nPretraining dataset configuration subset\n\n\n\nutils.schemas.datasets.SFTDataset()\nSFT configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nhandle_legacy_message_fields\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.SFTDataset.handle_legacy_message_fields(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.StepwiseSupervisedDataset()\nStepwise supervised dataset configuration subset\n\n\n\nutils.schemas.datasets.UserDefinedDPOType()\nUser defined typing for DPO\n\n\n\nutils.schemas.datasets.UserDefinedKTOType()\nUser defined typing for KTO\n\n\n\nutils.schemas.datasets.UserDefinedPrompterType()\nStructure for user defined prompt types" }, { - "objectID": "docs/api/kernels.quantize.html#functions", - "href": "docs/api/kernels.quantize.html#functions", - "title": "kernels.quantize", + "objectID": "docs/api/utils.schemas.datasets.html#classes", + "href": "docs/api/utils.schemas.datasets.html#classes", + "title": "utils.schemas.datasets", "section": "", - "text": "Name\nDescription\n\n\n\n\ndequantize\nFast NF4 dequantization using bitsandbytes CUDA kernels.\n\n\n\n\n\nkernels.quantize.dequantize(W, quant_state=None, out=None)\nFast NF4 dequantization using bitsandbytes CUDA kernels.\nPerforms efficient dequantization of weights from NF4 format using bitsandbytes’\noptimized CUDA implementations. Supports both legacy list and new QuantState\nformats.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nW\ntorch.Tensor\nQuantized weight tensor to dequantize\nrequired\n\n\nquant_state\nQuantState | list | None\nQuantization state containing metadata needed for dequantization. Can be either a QuantState object or legacy list format. If None, returns W unchanged.\nNone\n\n\nout\ntorch.Tensor | None\nOptional output tensor for storing dequantized results. Must match expected shape and dtype if provided.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nDequantized tensor in the specified dtype (fp16 or bf16). Will be transposed if\n\n\n\ntorch.Tensor\ninput W was transposed.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf provided output tensor doesn’t match expected shape / dtype.\n\n\n\n\n\n\nUses CUDA streams for better performance when available in newer bitsandbytes\nversions (>0.43.3)." + "text": "Name\nDescription\n\n\n\n\nDPODataset\nDPO configuration subset\n\n\nKTODataset\nKTO configuration subset\n\n\nPretrainingDataset\nPretraining dataset configuration subset\n\n\nSFTDataset\nSFT configuration subset\n\n\nStepwiseSupervisedDataset\nStepwise supervised dataset configuration subset\n\n\nUserDefinedDPOType\nUser defined typing for DPO\n\n\nUserDefinedKTOType\nUser defined typing for KTO\n\n\nUserDefinedPrompterType\nStructure for user defined prompt types\n\n\n\n\n\nutils.schemas.datasets.DPODataset()\nDPO configuration subset\n\n\n\nutils.schemas.datasets.KTODataset()\nKTO configuration subset\n\n\n\nutils.schemas.datasets.PretrainingDataset()\nPretraining dataset configuration subset\n\n\n\nutils.schemas.datasets.SFTDataset()\nSFT configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nhandle_legacy_message_fields\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.SFTDataset.handle_legacy_message_fields(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.StepwiseSupervisedDataset()\nStepwise supervised dataset configuration subset\n\n\n\nutils.schemas.datasets.UserDefinedDPOType()\nUser defined typing for DPO\n\n\n\nutils.schemas.datasets.UserDefinedKTOType()\nUser defined typing for KTO\n\n\n\nutils.schemas.datasets.UserDefinedPrompterType()\nStructure for user defined prompt types" }, { - "objectID": "docs/api/core.trainers.utils.html", - "href": "docs/api/core.trainers.utils.html", - "title": "core.trainers.utils", + "objectID": "docs/api/convert.html", + "href": "docs/api/convert.html", + "title": "convert", "section": "", - "text": "core.trainers.utils\ncore.trainers.utils\nUtils for Axolotl trainers" + "text": "convert\nModule containing File Reader, File Writer, Json Parser, and Jsonl Serializer classes\n\n\n\n\n\nName\nDescription\n\n\n\n\nFileReader\nReads a file and returns its contents as a string\n\n\nFileWriter\nWrites a string to a file\n\n\nJsonParser\nParses a string as JSON and returns the result\n\n\nJsonToJsonlConverter\nConverts a JSON file to JSONL\n\n\nJsonlSerializer\nSerializes a list of JSON objects into a JSONL string\n\n\nStdoutWriter\nWrites a string to stdout\n\n\n\n\n\nconvert.FileReader()\nReads a file and returns its contents as a string\n\n\n\nconvert.FileWriter(self, file_path)\nWrites a string to a file\n\n\n\nconvert.JsonParser()\nParses a string as JSON and returns the result\n\n\n\nconvert.JsonToJsonlConverter(\n self,\n file_reader,\n file_writer,\n json_parser,\n jsonl_serializer,\n)\nConverts a JSON file to JSONL\n\n\n\nconvert.JsonlSerializer()\nSerializes a list of JSON objects into a JSONL string\n\n\n\nconvert.StdoutWriter()\nWrites a string to stdout" }, { - "objectID": "docs/api/monkeypatch.data.batch_dataset_fetcher.html", - "href": "docs/api/monkeypatch.data.batch_dataset_fetcher.html", - "title": "monkeypatch.data.batch_dataset_fetcher", + "objectID": "docs/api/convert.html#classes", + "href": "docs/api/convert.html#classes", + "title": "convert", "section": "", - "text": "monkeypatch.data.batch_dataset_fetcher\nmonkeypatch.data.batch_dataset_fetcher\nmonkey patches for the dataset fetcher to handle batches of packed indexes" + "text": "Name\nDescription\n\n\n\n\nFileReader\nReads a file and returns its contents as a string\n\n\nFileWriter\nWrites a string to a file\n\n\nJsonParser\nParses a string as JSON and returns the result\n\n\nJsonToJsonlConverter\nConverts a JSON file to JSONL\n\n\nJsonlSerializer\nSerializes a list of JSON objects into a JSONL string\n\n\nStdoutWriter\nWrites a string to stdout\n\n\n\n\n\nconvert.FileReader()\nReads a file and returns its contents as a string\n\n\n\nconvert.FileWriter(self, file_path)\nWrites a string to a file\n\n\n\nconvert.JsonParser()\nParses a string as JSON and returns the result\n\n\n\nconvert.JsonToJsonlConverter(\n self,\n file_reader,\n file_writer,\n json_parser,\n jsonl_serializer,\n)\nConverts a JSON file to JSONL\n\n\n\nconvert.JsonlSerializer()\nSerializes a list of JSON objects into a JSONL string\n\n\n\nconvert.StdoutWriter()\nWrites a string to stdout" }, { - "objectID": "docs/api/utils.ctx_managers.sequence_parallel.html", - "href": "docs/api/utils.ctx_managers.sequence_parallel.html", - "title": "utils.ctx_managers.sequence_parallel", + "objectID": "docs/api/prompt_strategies.llama2_chat.html", + "href": "docs/api/prompt_strategies.llama2_chat.html", + "title": "prompt_strategies.llama2_chat", "section": "", - "text": "utils.ctx_managers.sequence_parallel\nModule for Axolotl trainer sequence parallelism manager and utilities\n\n\n\n\n\nName\nDescription\n\n\n\n\nAllGatherWithGrad\nCustom autograd function for all-gather to preserve gradients.\n\n\nSequenceParallelContextManager\nContext manager for sequence parallelism operations.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad()\nCustom autograd function for all-gather to preserve gradients.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass for all-gather operation.\n\n\nforward\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.backward(\n ctx,\n grad_output,\n)\nBackward pass for all-gather operation.\nExtracts the gradient slice corresponding to this rank’s original input\nfrom the full gradient tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient from subsequent layers with respect to the concatenated output tensor.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None]\nTuple containing the gradient slice for this rank’s input tensor and None for the process group parameter which doesn’t require gradients.\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.forward(\n ctx,\n input_tensor,\n group,\n)\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ninput_tensor\ntorch.Tensor\nTensor from model output with sequence dimension.\nrequired\n\n\ngroup\ndist.ProcessGroup\ntorch.distributed process group.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTensor from gathering the input_tensor from across the process group and concatenating along the sequence dimension.\n\n\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager(\n self,\n models,\n sequence_parallel_degree,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nContext manager for sequence parallelism operations.\nThis class provides a context that will automatically apply sequence parallelism\nduring model forward passes using a pre-forward hook, and gather outputs from\nacross the sequence parallelism group using a post-forward hook.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodels\nlist[nn.Module]\nList of models to apply sequence parallelism to pre- and post- forward hooks.\nrequired\n\n\nsequence_parallel_degree\nint\nNumber of processes to split sequences over.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused.\nrequired\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ngather_outputs\nGather sharded outputs from all ranks and reconstruct the full tensor.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager.gather_outputs(\n output,\n)\nGather sharded outputs from all ranks and reconstruct the full tensor.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\napply_sequence_parallelism\nApply sequence parallelism slicing to a batch.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.apply_sequence_parallelism(\n batch,\n local_rank,\n local_world_size,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nApply sequence parallelism slicing to a batch.\nSpecial handling is implemented for integer logits_to_keep, which indicates\nto only keep the last N tokens in the sequence during generation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbatch\ndict[str, torch.Tensor]\nBatch dictionary (e.g., input_ids, attention_mask, etc.).\nrequired\n\n\nlocal_rank\nint\nLocal rank in the sequence parallel group.\nrequired\n\n\nlocal_world_size\nint\nWorld size of the sequence parallel group.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused, but related to above TODO.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[dict[str, torch.Tensor], int, int]\ntuple of: - Batch dictionary with sliced tensors. - The original sequence length before padding. - The number of padding tokens added." + "text": "prompt_strategies.llama2_chat\nPrompt Strategy for finetuning Llama2 chat models\nsee also https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L213 for ma reference implementation.\nThis implementation is based on the Vicuna PR and the fastchat repo, see also:\nhttps://github.com/lm-sys/FastChat/blob/cdd7730686cb1bf9ae2b768ee171bdf7d1ff04f3/fastchat/conversation.py#L847\nUse dataset type: “llama2_chat” in conig.yml to use this prompt style.\nE.g. in the config.yml:\ndatasets:\n - path: llama_finetune_train.jsonl\n type: llama2_chat\nThe dataset itself should look like this:\n{'conversations':[{\"from\": \"human\", \"value\": \"Who are you?\"}, {\"from\": \"gpt\", \"value\": \"I am Vicuna\"},...]}\nin a jsonl file. The first message should be from the human, the second from gpt.\nFor a custom system message, the first “from” can be “system” (followed by alternating “human” and “gpt” turns).\nImportant: Don’t use “special_tokens:” in your config.yml if you are not sure what you are doing!\n\n\n\n\n\nName\nDescription\n\n\n\n\nLLama2ChatTokenizingStrategy\nTokenizing strategy for Llama2 prompts.\n\n\nLlama2ChatConversation\nA class that manages prompt templates and keeps all conversation history.\n\n\nLlama2ChatPrompter\nA prompter that generates prompts for Llama2 models.\n\n\n\n\n\nprompt_strategies.llama2_chat.LLama2ChatTokenizingStrategy(\n self,\n *args,\n **kwargs,\n)\nTokenizing strategy for Llama2 prompts.\nadapted from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation(\n self,\n name='llama2',\n system=\"[INST] <<SYS>>\\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\\n<</SYS>>\\n\\n\",\n roles=('[INST]', '[/INST]'),\n messages=list(),\n offset=0,\n)\nA class that manages prompt templates and keeps all conversation history.\ncopied from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n\n\n\n\n\nName\nDescription\n\n\n\n\nappend_message\nAppend a new message.\n\n\nget_prompt\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.append_message(\n role,\n message,\n)\nAppend a new message.\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.get_prompt()\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatPrompter()\nA prompter that generates prompts for Llama2 models." }, { - "objectID": "docs/api/utils.ctx_managers.sequence_parallel.html#classes", - "href": "docs/api/utils.ctx_managers.sequence_parallel.html#classes", - "title": "utils.ctx_managers.sequence_parallel", + "objectID": "docs/api/prompt_strategies.llama2_chat.html#classes", + "href": "docs/api/prompt_strategies.llama2_chat.html#classes", + "title": "prompt_strategies.llama2_chat", "section": "", - "text": "Name\nDescription\n\n\n\n\nAllGatherWithGrad\nCustom autograd function for all-gather to preserve gradients.\n\n\nSequenceParallelContextManager\nContext manager for sequence parallelism operations.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad()\nCustom autograd function for all-gather to preserve gradients.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass for all-gather operation.\n\n\nforward\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.backward(\n ctx,\n grad_output,\n)\nBackward pass for all-gather operation.\nExtracts the gradient slice corresponding to this rank’s original input\nfrom the full gradient tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient from subsequent layers with respect to the concatenated output tensor.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None]\nTuple containing the gradient slice for this rank’s input tensor and None for the process group parameter which doesn’t require gradients.\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.forward(\n ctx,\n input_tensor,\n group,\n)\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ninput_tensor\ntorch.Tensor\nTensor from model output with sequence dimension.\nrequired\n\n\ngroup\ndist.ProcessGroup\ntorch.distributed process group.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTensor from gathering the input_tensor from across the process group and concatenating along the sequence dimension.\n\n\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager(\n self,\n models,\n sequence_parallel_degree,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nContext manager for sequence parallelism operations.\nThis class provides a context that will automatically apply sequence parallelism\nduring model forward passes using a pre-forward hook, and gather outputs from\nacross the sequence parallelism group using a post-forward hook.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodels\nlist[nn.Module]\nList of models to apply sequence parallelism to pre- and post- forward hooks.\nrequired\n\n\nsequence_parallel_degree\nint\nNumber of processes to split sequences over.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused.\nrequired\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ngather_outputs\nGather sharded outputs from all ranks and reconstruct the full tensor.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager.gather_outputs(\n output,\n)\nGather sharded outputs from all ranks and reconstruct the full tensor." + "text": "Name\nDescription\n\n\n\n\nLLama2ChatTokenizingStrategy\nTokenizing strategy for Llama2 prompts.\n\n\nLlama2ChatConversation\nA class that manages prompt templates and keeps all conversation history.\n\n\nLlama2ChatPrompter\nA prompter that generates prompts for Llama2 models.\n\n\n\n\n\nprompt_strategies.llama2_chat.LLama2ChatTokenizingStrategy(\n self,\n *args,\n **kwargs,\n)\nTokenizing strategy for Llama2 prompts.\nadapted from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation(\n self,\n name='llama2',\n system=\"[INST] <<SYS>>\\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\\n<</SYS>>\\n\\n\",\n roles=('[INST]', '[/INST]'),\n messages=list(),\n offset=0,\n)\nA class that manages prompt templates and keeps all conversation history.\ncopied from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n\n\n\n\n\nName\nDescription\n\n\n\n\nappend_message\nAppend a new message.\n\n\nget_prompt\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.append_message(\n role,\n message,\n)\nAppend a new message.\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.get_prompt()\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatPrompter()\nA prompter that generates prompts for Llama2 models." }, { - "objectID": "docs/api/utils.ctx_managers.sequence_parallel.html#functions", - "href": "docs/api/utils.ctx_managers.sequence_parallel.html#functions", - "title": "utils.ctx_managers.sequence_parallel", + "objectID": "docs/api/monkeypatch.transformers_fa_utils.html", + "href": "docs/api/monkeypatch.transformers_fa_utils.html", + "title": "monkeypatch.transformers_fa_utils", "section": "", - "text": "Name\nDescription\n\n\n\n\napply_sequence_parallelism\nApply sequence parallelism slicing to a batch.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.apply_sequence_parallelism(\n batch,\n local_rank,\n local_world_size,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nApply sequence parallelism slicing to a batch.\nSpecial handling is implemented for integer logits_to_keep, which indicates\nto only keep the last N tokens in the sequence during generation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbatch\ndict[str, torch.Tensor]\nBatch dictionary (e.g., input_ids, attention_mask, etc.).\nrequired\n\n\nlocal_rank\nint\nLocal rank in the sequence parallel group.\nrequired\n\n\nlocal_world_size\nint\nWorld size of the sequence parallel group.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused, but related to above TODO.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[dict[str, torch.Tensor], int, int]\ntuple of: - Batch dictionary with sliced tensors. - The original sequence length before padding. - The number of padding tokens added." + "text": "monkeypatch.transformers_fa_utils\nsee https://github.com/huggingface/transformers/pull/35834\n\n\n\n\n\nName\nDescription\n\n\n\n\nfixed_fa_peft_integration_check\nPEFT usually casts the layer norms in float32 for training stability reasons\n\n\n\n\n\nmonkeypatch.transformers_fa_utils.fixed_fa_peft_integration_check(\n query,\n key,\n value,\n target_dtype=None,\n preferred_dtype=None,\n)\nPEFT usually casts the layer norms in float32 for training stability reasons\ntherefore the input hidden states gets silently casted in float32. Hence, we need\ncast them back in float16 / bfloat16 just to be sure everything works as expected.\nThis might slowdown training & inference so it is recommended to not cast the LayerNorms!\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nquery\ntorch.Tensor\nInput query states to be passed to Flash Attention API\nrequired\n\n\nkey\ntorch.Tensor\nInput key states to be passed to Flash Attention API\nrequired\n\n\nvalue\ntorch.Tensor\nInput value states to be passed to Flash Attention API\nrequired\n\n\ntarget_dtype\ntorch.dtype, optional\nThe dtype to convert the attention tensors to. Conversion can be ignored by not providing the target dtype.\nNone\n\n\npreferred_dtype\ntorch.dtype, optional\nThe preferred dtype to convert the attention tensors to regardless of the target dtype.\nNone" }, { - "objectID": "docs/api/evaluate.html", - "href": "docs/api/evaluate.html", - "title": "evaluate", + "objectID": "docs/api/monkeypatch.transformers_fa_utils.html#functions", + "href": "docs/api/monkeypatch.transformers_fa_utils.html#functions", + "title": "monkeypatch.transformers_fa_utils", "section": "", - "text": "evaluate\nModule for evaluating models.\n\n\n\n\n\nName\nDescription\n\n\n\n\nevaluate\nEvaluate a model on training and validation datasets.\n\n\nevaluate_dataset\nHelper function to evaluate a single dataset.\n\n\n\n\n\nevaluate.evaluate(cfg, dataset_meta)\nEvaluate a model on training and validation datasets.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nDataset metadata containing training and evaluation datasets.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDict[str, float]\nDictionary mapping metric names to their values.\n\n\n\n\n\n\n\nevaluate.evaluate_dataset(trainer, dataset, dataset_type, flash_optimum=False)\nHelper function to evaluate a single dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrainer\nTrainer\nThe trainer instance.\nrequired\n\n\ndataset\nDataset\nDataset to evaluate.\nrequired\n\n\ndataset_type\nstr\nType of dataset (‘train’ or ‘eval’).\nrequired\n\n\nflash_optimum\nbool\nWhether to use flash optimum.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nOptional[Dict[str, float]]\nDictionary of metrics or None if dataset is None." + "text": "Name\nDescription\n\n\n\n\nfixed_fa_peft_integration_check\nPEFT usually casts the layer norms in float32 for training stability reasons\n\n\n\n\n\nmonkeypatch.transformers_fa_utils.fixed_fa_peft_integration_check(\n query,\n key,\n value,\n target_dtype=None,\n preferred_dtype=None,\n)\nPEFT usually casts the layer norms in float32 for training stability reasons\ntherefore the input hidden states gets silently casted in float32. Hence, we need\ncast them back in float16 / bfloat16 just to be sure everything works as expected.\nThis might slowdown training & inference so it is recommended to not cast the LayerNorms!\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nquery\ntorch.Tensor\nInput query states to be passed to Flash Attention API\nrequired\n\n\nkey\ntorch.Tensor\nInput key states to be passed to Flash Attention API\nrequired\n\n\nvalue\ntorch.Tensor\nInput value states to be passed to Flash Attention API\nrequired\n\n\ntarget_dtype\ntorch.dtype, optional\nThe dtype to convert the attention tensors to. Conversion can be ignored by not providing the target dtype.\nNone\n\n\npreferred_dtype\ntorch.dtype, optional\nThe preferred dtype to convert the attention tensors to regardless of the target dtype.\nNone" }, { - "objectID": "docs/api/evaluate.html#functions", - "href": "docs/api/evaluate.html#functions", - "title": "evaluate", + "objectID": "docs/api/cli.checks.html", + "href": "docs/api/cli.checks.html", + "title": "cli.checks", "section": "", - "text": "Name\nDescription\n\n\n\n\nevaluate\nEvaluate a model on training and validation datasets.\n\n\nevaluate_dataset\nHelper function to evaluate a single dataset.\n\n\n\n\n\nevaluate.evaluate(cfg, dataset_meta)\nEvaluate a model on training and validation datasets.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nDataset metadata containing training and evaluation datasets.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDict[str, float]\nDictionary mapping metric names to their values.\n\n\n\n\n\n\n\nevaluate.evaluate_dataset(trainer, dataset, dataset_type, flash_optimum=False)\nHelper function to evaluate a single dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrainer\nTrainer\nThe trainer instance.\nrequired\n\n\ndataset\nDataset\nDataset to evaluate.\nrequired\n\n\ndataset_type\nstr\nType of dataset (‘train’ or ‘eval’).\nrequired\n\n\nflash_optimum\nbool\nWhether to use flash optimum.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nOptional[Dict[str, float]]\nDictionary of metrics or None if dataset is None." + "text": "cli.checks\nVarious checks for Axolotl CLI.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncheck_accelerate_default_config\nLogs at warning level if no accelerate config file is found.\n\n\ncheck_user_token\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\ncli.checks.check_accelerate_default_config()\nLogs at warning level if no accelerate config file is found.\n\n\n\ncli.checks.check_user_token()\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nbool\nBoolean indicating successful check (i.e., HF_HUB_OFFLINE=1 or HF user info is retrieved).\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nLocalTokenNotFoundError\nIf HF user info can’t be retrieved." }, { - "objectID": "docs/api/prompt_strategies.completion.html", - "href": "docs/api/prompt_strategies.completion.html", - "title": "prompt_strategies.completion", + "objectID": "docs/api/cli.checks.html#functions", + "href": "docs/api/cli.checks.html#functions", + "title": "cli.checks", "section": "", - "text": "prompt_strategies.completion\nBasic completion text\n\n\n\n\n\nName\nDescription\n\n\n\n\nCompletionPromptTokenizingStrategy\nTokenizing strategy for Completion prompts.\n\n\nCompletionPrompter\nPrompter for completion\n\n\n\n\n\nprompt_strategies.completion.CompletionPromptTokenizingStrategy(\n self,\n *args,\n max_length=None,\n **kwargs,\n)\nTokenizing strategy for Completion prompts.\n\n\n\nprompt_strategies.completion.CompletionPrompter()\nPrompter for completion" + "text": "Name\nDescription\n\n\n\n\ncheck_accelerate_default_config\nLogs at warning level if no accelerate config file is found.\n\n\ncheck_user_token\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\ncli.checks.check_accelerate_default_config()\nLogs at warning level if no accelerate config file is found.\n\n\n\ncli.checks.check_user_token()\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nbool\nBoolean indicating successful check (i.e., HF_HUB_OFFLINE=1 or HF user info is retrieved).\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nLocalTokenNotFoundError\nIf HF user info can’t be retrieved." }, { - "objectID": "docs/api/prompt_strategies.completion.html#classes", - "href": "docs/api/prompt_strategies.completion.html#classes", - "title": "prompt_strategies.completion", + "objectID": "docs/api/core.chat.format.llama3x.html", + "href": "docs/api/core.chat.format.llama3x.html", + "title": "core.chat.format.llama3x", "section": "", - "text": "Name\nDescription\n\n\n\n\nCompletionPromptTokenizingStrategy\nTokenizing strategy for Completion prompts.\n\n\nCompletionPrompter\nPrompter for completion\n\n\n\n\n\nprompt_strategies.completion.CompletionPromptTokenizingStrategy(\n self,\n *args,\n max_length=None,\n **kwargs,\n)\nTokenizing strategy for Completion prompts.\n\n\n\nprompt_strategies.completion.CompletionPrompter()\nPrompter for completion" + "text": "core.chat.format.llama3x\ncore.chat.format.llama3x\nLlama 3.x chat formatting functions for MessageContents" }, { - "objectID": "docs/api/monkeypatch.llama_attn_hijack_flash.html", - "href": "docs/api/monkeypatch.llama_attn_hijack_flash.html", - "title": "monkeypatch.llama_attn_hijack_flash", + "objectID": "docs/api/monkeypatch.mistral_attn_hijack_flash.html", + "href": "docs/api/monkeypatch.mistral_attn_hijack_flash.html", + "title": "monkeypatch.mistral_attn_hijack_flash", "section": "", - "text": "monkeypatch.llama_attn_hijack_flash\nFlash attention monkey patch for llama model\n\n\n\n\n\nName\nDescription\n\n\n\n\nFusedAttention\nFused QKV Attention layer for incrementally improved training efficiency\n\n\nLlamaDecoderLayer\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.FusedAttention(self, config, q, k, v, o)\nFused QKV Attention layer for incrementally improved training efficiency\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer()\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nflashattn_forward\nInput shape: Batch x Time x Channel\n\n\nflashattn_forward_with_s2attn\nInput shape: Batch x Time x Channel\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nattention_mask: [bsz, q_len]\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward_with_s2attn(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nFrom: https://github.com/dvlab-research/LongLoRA/blob/main/llama_attn_replace.py\nattention_mask: [bsz, q_len]\ncu_seqlens will be ignored if provided\nmax_seqlen will be ignored if provided\n\n\n\nmonkeypatch.llama_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" + "text": "monkeypatch.mistral_attn_hijack_flash\nFlash attention monkey patch for mistral model\n\n\n\n\n\nName\nDescription\n\n\n\n\nMistralDecoderLayer\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer()\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" }, { - "objectID": "docs/api/monkeypatch.llama_attn_hijack_flash.html#classes", - "href": "docs/api/monkeypatch.llama_attn_hijack_flash.html#classes", - "title": "monkeypatch.llama_attn_hijack_flash", + "objectID": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#classes", + "href": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#classes", + "title": "monkeypatch.mistral_attn_hijack_flash", "section": "", - "text": "Name\nDescription\n\n\n\n\nFusedAttention\nFused QKV Attention layer for incrementally improved training efficiency\n\n\nLlamaDecoderLayer\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.FusedAttention(self, config, q, k, v, o)\nFused QKV Attention layer for incrementally improved training efficiency\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer()\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone" + "text": "Name\nDescription\n\n\n\n\nMistralDecoderLayer\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer()\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone" }, { - "objectID": "docs/api/monkeypatch.llama_attn_hijack_flash.html#functions", - "href": "docs/api/monkeypatch.llama_attn_hijack_flash.html#functions", - "title": "monkeypatch.llama_attn_hijack_flash", + "objectID": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#functions", + "href": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#functions", + "title": "monkeypatch.mistral_attn_hijack_flash", "section": "", - "text": "Name\nDescription\n\n\n\n\nflashattn_forward\nInput shape: Batch x Time x Channel\n\n\nflashattn_forward_with_s2attn\nInput shape: Batch x Time x Channel\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nattention_mask: [bsz, q_len]\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward_with_s2attn(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nFrom: https://github.com/dvlab-research/LongLoRA/blob/main/llama_attn_replace.py\nattention_mask: [bsz, q_len]\ncu_seqlens will be ignored if provided\nmax_seqlen will be ignored if provided\n\n\n\nmonkeypatch.llama_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" + "text": "Name\nDescription\n\n\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" }, { - "objectID": "docs/api/prompt_strategies.orpo.chat_template.html", - "href": "docs/api/prompt_strategies.orpo.chat_template.html", - "title": "prompt_strategies.orpo.chat_template", + "objectID": "docs/api/utils.callbacks.mlflow_.html", + "href": "docs/api/utils.callbacks.mlflow_.html", + "title": "utils.callbacks.mlflow_", "section": "", - "text": "prompt_strategies.orpo.chat_template\nchatml prompt tokenization strategy for ORPO\n\n\n\n\n\nName\nDescription\n\n\n\n\nMessage\nmessage/turn\n\n\nMessageList\nconversation\n\n\nORPODatasetParsingStrategy\nStrategy to parse chosen rejected dataset into messagelist\n\n\nORPOPrompter\nSingle Turn prompter for ORPO\n\n\nORPOTokenizingStrategy\nrejected_input_ids\n\n\n\n\n\nprompt_strategies.orpo.chat_template.Message()\nmessage/turn\n\n\n\nprompt_strategies.orpo.chat_template.MessageList()\nconversation\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy()\nStrategy to parse chosen rejected dataset into messagelist\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_chosen_conversation_thread\nDataset structure mappings\n\n\nget_prompt\nMap the data to extract everything up to the last turn\n\n\nget_rejected_conversation_thread\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_chosen_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_prompt(\n prompt,\n)\nMap the data to extract everything up to the last turn\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_rejected_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPOPrompter(\n self,\n chat_template,\n tokenizer,\n)\nSingle Turn prompter for ORPO\n\n\n\nprompt_strategies.orpo.chat_template.ORPOTokenizingStrategy(\n self,\n *args,\n dataset_parser=None,\n **kwargs,\n)\nrejected_input_ids\ninput_ids\nrejected_attention_mask\nattention_mask\nrejected_labels\nlabels\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nload\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.orpo.chat_template.load(tokenizer, cfg, ds_cfg=None, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected" + "text": "utils.callbacks.mlflow_\nMLFlow module for trainer callbacks\n\n\n\n\n\nName\nDescription\n\n\n\n\nSaveAxolotlConfigtoMlflowCallback\nCallback to save axolotl config to mlflow\n\n\n\n\n\nutils.callbacks.mlflow_.SaveAxolotlConfigtoMlflowCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to mlflow" }, { - "objectID": "docs/api/prompt_strategies.orpo.chat_template.html#classes", - "href": "docs/api/prompt_strategies.orpo.chat_template.html#classes", - "title": "prompt_strategies.orpo.chat_template", + "objectID": "docs/api/utils.callbacks.mlflow_.html#classes", + "href": "docs/api/utils.callbacks.mlflow_.html#classes", + "title": "utils.callbacks.mlflow_", "section": "", - "text": "Name\nDescription\n\n\n\n\nMessage\nmessage/turn\n\n\nMessageList\nconversation\n\n\nORPODatasetParsingStrategy\nStrategy to parse chosen rejected dataset into messagelist\n\n\nORPOPrompter\nSingle Turn prompter for ORPO\n\n\nORPOTokenizingStrategy\nrejected_input_ids\n\n\n\n\n\nprompt_strategies.orpo.chat_template.Message()\nmessage/turn\n\n\n\nprompt_strategies.orpo.chat_template.MessageList()\nconversation\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy()\nStrategy to parse chosen rejected dataset into messagelist\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_chosen_conversation_thread\nDataset structure mappings\n\n\nget_prompt\nMap the data to extract everything up to the last turn\n\n\nget_rejected_conversation_thread\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_chosen_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_prompt(\n prompt,\n)\nMap the data to extract everything up to the last turn\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_rejected_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPOPrompter(\n self,\n chat_template,\n tokenizer,\n)\nSingle Turn prompter for ORPO\n\n\n\nprompt_strategies.orpo.chat_template.ORPOTokenizingStrategy(\n self,\n *args,\n dataset_parser=None,\n **kwargs,\n)\nrejected_input_ids\ninput_ids\nrejected_attention_mask\nattention_mask\nrejected_labels\nlabels" + "text": "Name\nDescription\n\n\n\n\nSaveAxolotlConfigtoMlflowCallback\nCallback to save axolotl config to mlflow\n\n\n\n\n\nutils.callbacks.mlflow_.SaveAxolotlConfigtoMlflowCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to mlflow" }, { - "objectID": "docs/api/prompt_strategies.orpo.chat_template.html#functions", - "href": "docs/api/prompt_strategies.orpo.chat_template.html#functions", - "title": "prompt_strategies.orpo.chat_template", + "objectID": "docs/api/core.datasets.chat.html", + "href": "docs/api/core.datasets.chat.html", + "title": "core.datasets.chat", "section": "", - "text": "Name\nDescription\n\n\n\n\nload\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.orpo.chat_template.load(tokenizer, cfg, ds_cfg=None, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected" + "text": "core.datasets.chat\nchat dataset module\n\n\n\n\n\nName\nDescription\n\n\n\n\nTokenizedChatDataset\nTokenized chat dataset\n\n\n\n\n\ncore.datasets.chat.TokenizedChatDataset(\n self,\n data,\n model_transform,\n *args,\n message_transform=None,\n formatter=None,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nTokenized chat dataset" }, { - "objectID": "docs/api/core.trainers.mixins.optimizer.html", - "href": "docs/api/core.trainers.mixins.optimizer.html", - "title": "core.trainers.mixins.optimizer", + "objectID": "docs/api/core.datasets.chat.html#classes", + "href": "docs/api/core.datasets.chat.html#classes", + "title": "core.datasets.chat", "section": "", - "text": "core.trainers.mixins.optimizer\nModule for Axolotl trainer optimizer mixin\n\n\n\n\n\nName\nDescription\n\n\n\n\nOptimizerMixin\nMixin class for shared handling of building custom optimizers\n\n\n\n\n\ncore.trainers.mixins.optimizer.OptimizerMixin()\nMixin class for shared handling of building custom optimizers" + "text": "Name\nDescription\n\n\n\n\nTokenizedChatDataset\nTokenized chat dataset\n\n\n\n\n\ncore.datasets.chat.TokenizedChatDataset(\n self,\n data,\n model_transform,\n *args,\n message_transform=None,\n formatter=None,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nTokenized chat dataset" }, { - "objectID": "docs/api/core.trainers.mixins.optimizer.html#classes", - "href": "docs/api/core.trainers.mixins.optimizer.html#classes", - "title": "core.trainers.mixins.optimizer", + "objectID": "docs/api/core.trainers.mixins.scheduler.html", + "href": "docs/api/core.trainers.mixins.scheduler.html", + "title": "core.trainers.mixins.scheduler", "section": "", - "text": "Name\nDescription\n\n\n\n\nOptimizerMixin\nMixin class for shared handling of building custom optimizers\n\n\n\n\n\ncore.trainers.mixins.optimizer.OptimizerMixin()\nMixin class for shared handling of building custom optimizers" + "text": "core.trainers.mixins.scheduler\nModule for Axolotl trainer scheduler mixin\n\n\n\n\n\nName\nDescription\n\n\n\n\nSchedulerMixin\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin()\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncreate_scheduler\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin.create_scheduler(\n num_training_steps,\n optimizer=None,\n)\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\npassed as an argument.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nnum_training_steps\nint\nThe number of training steps to do.\nrequired\n\n\noptimizer\ntorch.optim.Optimizer\nThe training optimizer\nNone" }, { - "objectID": "docs/api/cli.utils.html", - "href": "docs/api/cli.utils.html", - "title": "cli.utils", + "objectID": "docs/api/core.trainers.mixins.scheduler.html#classes", + "href": "docs/api/core.trainers.mixins.scheduler.html#classes", + "title": "core.trainers.mixins.scheduler", "section": "", - "text": "cli.utils\nUtility methods for axolotl CLI.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_options_from_config\nCreate Click options from the fields of a Pydantic model.\n\n\nadd_options_from_dataclass\nCreate Click options from the fields of a dataclass.\n\n\nbuild_command\nBuild command list from base command and options.\n\n\ndownload_file\nDownload a single file and return its processing status.\n\n\nfetch_from_github\nSync files from a specific directory in the GitHub repository.\n\n\nfilter_none_kwargs\nWraps function to remove None-valued kwargs.\n\n\nload_model_and_tokenizer\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\n\n\nstrip_optional_type\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\ncli.utils.add_options_from_config(config_class)\nCreate Click options from the fields of a Pydantic model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[BaseModel]\nPyDantic model with fields to parse from the CLI\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.add_options_from_dataclass(config_class)\nCreate Click options from the fields of a dataclass.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[Any]\nDataclass with fields to parse from the CLI.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.build_command(base_cmd, options)\nBuild command list from base command and options.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_cmd\nlist[str]\nCommand without options.\nrequired\n\n\noptions\ndict[str, Any]\nOptions to parse and append to base command.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nlist[str]\nList of strings giving shell command.\n\n\n\n\n\n\n\ncli.utils.download_file(file_info, raw_base_url, dest_path, dir_prefix)\nDownload a single file and return its processing status.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfile_info\ntuple\nTuple of (file_path, remote_sha).\nrequired\n\n\nraw_base_url\nstr\nBase URL for raw GitHub content.\nrequired\n\n\ndest_path\nPath\nLocal destination directory.\nrequired\n\n\ndir_prefix\nstr\nDirectory prefix to filter files.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[str, str]\nTuple of (file_path, status) where status is ‘new’, ‘updated’, or ‘unchanged’.\n\n\n\n\n\n\n\ncli.utils.fetch_from_github(dir_prefix, dest_dir=None, max_workers=5)\nSync files from a specific directory in the GitHub repository.\nOnly downloads files that don’t exist locally or have changed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndir_prefix\nstr\nDirectory prefix to filter files (e.g., ‘examples/’, ‘deepspeed_configs/’).\nrequired\n\n\ndest_dir\nstr | None\nLocal destination directory.\nNone\n\n\nmax_workers\nint\nMaximum number of concurrent downloads.\n5\n\n\n\n\n\n\n\ncli.utils.filter_none_kwargs(func)\nWraps function to remove None-valued kwargs.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfunc\nCallable\nFunction to wrap.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nWrapped function.\n\n\n\n\n\n\n\ncli.utils.load_model_and_tokenizer(cfg, inference=False)\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\nconfig.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ninference\nbool\nBoolean denoting inference mode.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer | PreTrainedTokenizerFast | Any, ProcessorMixin | None]\nTuple of (PreTrainedModel, PreTrainedTokenizer, ProcessorMixin).\n\n\n\n\n\n\n\ncli.utils.strip_optional_type(field_type)\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfield_type\ntype | str | None\nType of field for Axolotl CLI command.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nIf the input type is Union[T, None] or Optional[T], returns T. Otherwise returns the input type unchanged." + "text": "Name\nDescription\n\n\n\n\nSchedulerMixin\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin()\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncreate_scheduler\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin.create_scheduler(\n num_training_steps,\n optimizer=None,\n)\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\npassed as an argument.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nnum_training_steps\nint\nThe number of training steps to do.\nrequired\n\n\noptimizer\ntorch.optim.Optimizer\nThe training optimizer\nNone" }, { - "objectID": "docs/api/cli.utils.html#functions", - "href": "docs/api/cli.utils.html#functions", - "title": "cli.utils", + "objectID": "docs/api/utils.schedulers.html", + "href": "docs/api/utils.schedulers.html", + "title": "utils.schedulers", "section": "", - "text": "Name\nDescription\n\n\n\n\nadd_options_from_config\nCreate Click options from the fields of a Pydantic model.\n\n\nadd_options_from_dataclass\nCreate Click options from the fields of a dataclass.\n\n\nbuild_command\nBuild command list from base command and options.\n\n\ndownload_file\nDownload a single file and return its processing status.\n\n\nfetch_from_github\nSync files from a specific directory in the GitHub repository.\n\n\nfilter_none_kwargs\nWraps function to remove None-valued kwargs.\n\n\nload_model_and_tokenizer\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\n\n\nstrip_optional_type\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\ncli.utils.add_options_from_config(config_class)\nCreate Click options from the fields of a Pydantic model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[BaseModel]\nPyDantic model with fields to parse from the CLI\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.add_options_from_dataclass(config_class)\nCreate Click options from the fields of a dataclass.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[Any]\nDataclass with fields to parse from the CLI.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.build_command(base_cmd, options)\nBuild command list from base command and options.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_cmd\nlist[str]\nCommand without options.\nrequired\n\n\noptions\ndict[str, Any]\nOptions to parse and append to base command.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nlist[str]\nList of strings giving shell command.\n\n\n\n\n\n\n\ncli.utils.download_file(file_info, raw_base_url, dest_path, dir_prefix)\nDownload a single file and return its processing status.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfile_info\ntuple\nTuple of (file_path, remote_sha).\nrequired\n\n\nraw_base_url\nstr\nBase URL for raw GitHub content.\nrequired\n\n\ndest_path\nPath\nLocal destination directory.\nrequired\n\n\ndir_prefix\nstr\nDirectory prefix to filter files.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[str, str]\nTuple of (file_path, status) where status is ‘new’, ‘updated’, or ‘unchanged’.\n\n\n\n\n\n\n\ncli.utils.fetch_from_github(dir_prefix, dest_dir=None, max_workers=5)\nSync files from a specific directory in the GitHub repository.\nOnly downloads files that don’t exist locally or have changed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndir_prefix\nstr\nDirectory prefix to filter files (e.g., ‘examples/’, ‘deepspeed_configs/’).\nrequired\n\n\ndest_dir\nstr | None\nLocal destination directory.\nNone\n\n\nmax_workers\nint\nMaximum number of concurrent downloads.\n5\n\n\n\n\n\n\n\ncli.utils.filter_none_kwargs(func)\nWraps function to remove None-valued kwargs.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfunc\nCallable\nFunction to wrap.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nWrapped function.\n\n\n\n\n\n\n\ncli.utils.load_model_and_tokenizer(cfg, inference=False)\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\nconfig.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ninference\nbool\nBoolean denoting inference mode.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer | PreTrainedTokenizerFast | Any, ProcessorMixin | None]\nTuple of (PreTrainedModel, PreTrainedTokenizer, ProcessorMixin).\n\n\n\n\n\n\n\ncli.utils.strip_optional_type(field_type)\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfield_type\ntype | str | None\nType of field for Axolotl CLI command.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nIf the input type is Union[T, None] or Optional[T], returns T. Otherwise returns the input type unchanged." + "text": "utils.schedulers\nModule for custom LRScheduler class\n\n\n\n\n\nName\nDescription\n\n\n\n\nInterpolatingLogScheduler\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\nRexLR\nReflected Exponential (REX) learning rate scheduler.\n\n\n\n\n\nutils.schedulers.InterpolatingLogScheduler(\n self,\n optimizer,\n num_steps,\n min_lr,\n max_lr,\n last_epoch=-1,\n)\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\n\nutils.schedulers.RexLR(\n self,\n optimizer,\n max_lr,\n min_lr,\n total_steps=0,\n num_warmup_steps=0,\n last_step=0,\n)\nReflected Exponential (REX) learning rate scheduler.\n\nOriginal implementation: https://github.com/IvanVassi/REX_LR\nOriginal license: Apache 2.0\nBased on: https://arxiv.org/abs/2107.04197\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\ntorch.optim.Optimizer\nThe optimizer to schedule the learning rate for.\nrequired\n\n\nmax_lr\nfloat\nThe maximum learning rate.\nrequired\n\n\nmin_lr\nfloat\nThe minimum learning rate.\nrequired\n\n\ntotal_steps\nint\nThe total number of training steps.\n0\n\n\nnum_warmup_steps\nint\nThe number of warmup steps.\n0\n\n\nlast_step\nint\nThe index of last step.\n0\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_cosine_schedule_with_min_lr\n\n\n\nget_cosine_schedule_with_quadratic_warmup\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\n\n\nget_cosine_schedule_with_warmup_decay_constant\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_min_lr(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n min_lr_ratio=0.0,\n)\n\n\n\nlinear warmup from 0 -> max_lr over num_warmup_steps\ncosine learning rate annealing from max_lr -> min_lr over num_training_steps\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_quadratic_warmup(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n num_cycles=0.5,\n last_epoch=-1,\n)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the\ninitial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nnum_cycles\nfloat, optional, defaults to 0.5\nThe number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine).\n0.5\n\n\nlast_epoch\nint, optional, defaults to -1\nThe index of the last epoch when resuming training.\n-1\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule.\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_warmup_decay_constant(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n constant_lr_ratio,\n min_lr_ratio,\n num_cycles=0.5,\n last_epoch=-1,\n)\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to min_lr_ratio until num_training_steps * constant_lr_ratio, after constant_rate returns constant value of min_rate\n, after a warmup period during which it increases linearly between 0 and the initial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nconstant_lr_ratio\nfloat\n(float): The ratio of num_training_steps to decrease by cosine function.\nrequired\n\n\nmin_lr_ratio\nfloat\n(float): The ratio of maximum learning rate for cosine function to decay to minimum learning rate. | _required_ | | num_cycles |float, *optional*, defaults to 0.5 | The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine). |0.5| | last_epoch |int, *optional*, defaults to -1 | The index of the last epoch when resuming training. |-1`\n\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule." }, { - "objectID": "src/axolotl/integrations/LICENSE.html", - "href": "src/axolotl/integrations/LICENSE.html", + "objectID": "docs/api/utils.schedulers.html#classes", + "href": "docs/api/utils.schedulers.html#classes", + "title": "utils.schedulers", + "section": "", + "text": "Name\nDescription\n\n\n\n\nInterpolatingLogScheduler\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\nRexLR\nReflected Exponential (REX) learning rate scheduler.\n\n\n\n\n\nutils.schedulers.InterpolatingLogScheduler(\n self,\n optimizer,\n num_steps,\n min_lr,\n max_lr,\n last_epoch=-1,\n)\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\n\nutils.schedulers.RexLR(\n self,\n optimizer,\n max_lr,\n min_lr,\n total_steps=0,\n num_warmup_steps=0,\n last_step=0,\n)\nReflected Exponential (REX) learning rate scheduler.\n\nOriginal implementation: https://github.com/IvanVassi/REX_LR\nOriginal license: Apache 2.0\nBased on: https://arxiv.org/abs/2107.04197\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\ntorch.optim.Optimizer\nThe optimizer to schedule the learning rate for.\nrequired\n\n\nmax_lr\nfloat\nThe maximum learning rate.\nrequired\n\n\nmin_lr\nfloat\nThe minimum learning rate.\nrequired\n\n\ntotal_steps\nint\nThe total number of training steps.\n0\n\n\nnum_warmup_steps\nint\nThe number of warmup steps.\n0\n\n\nlast_step\nint\nThe index of last step.\n0" + }, + { + "objectID": "docs/api/utils.schedulers.html#functions", + "href": "docs/api/utils.schedulers.html#functions", + "title": "utils.schedulers", + "section": "", + "text": "Name\nDescription\n\n\n\n\nget_cosine_schedule_with_min_lr\n\n\n\nget_cosine_schedule_with_quadratic_warmup\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\n\n\nget_cosine_schedule_with_warmup_decay_constant\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_min_lr(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n min_lr_ratio=0.0,\n)\n\n\n\nlinear warmup from 0 -> max_lr over num_warmup_steps\ncosine learning rate annealing from max_lr -> min_lr over num_training_steps\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_quadratic_warmup(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n num_cycles=0.5,\n last_epoch=-1,\n)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the\ninitial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nnum_cycles\nfloat, optional, defaults to 0.5\nThe number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine).\n0.5\n\n\nlast_epoch\nint, optional, defaults to -1\nThe index of the last epoch when resuming training.\n-1\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule.\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_warmup_decay_constant(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n constant_lr_ratio,\n min_lr_ratio,\n num_cycles=0.5,\n last_epoch=-1,\n)\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to min_lr_ratio until num_training_steps * constant_lr_ratio, after constant_rate returns constant value of min_rate\n, after a warmup period during which it increases linearly between 0 and the initial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nconstant_lr_ratio\nfloat\n(float): The ratio of num_training_steps to decrease by cosine function.\nrequired\n\n\nmin_lr_ratio\nfloat\n(float): The ratio of maximum learning rate for cosine function to decay to minimum learning rate. | _required_ | | num_cycles |float, *optional*, defaults to 0.5 | The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine). |0.5| | last_epoch |int, *optional*, defaults to -1 | The index of the last epoch when resuming training. |-1`\n\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule." + }, + { + "objectID": "docs/api/utils.schemas.integrations.html", + "href": "docs/api/utils.schemas.integrations.html", + "title": "utils.schemas.integrations", + "section": "", + "text": "utils.schemas.integrations\nPydantic models for Axolotl integrations\n\n\n\n\n\nName\nDescription\n\n\n\n\nCometConfig\nComet configuration subset\n\n\nGradioConfig\nGradio configuration subset\n\n\nLISAConfig\nLISA configuration subset\n\n\nMLFlowConfig\nMLFlow configuration subset\n\n\nRayConfig\nRay launcher configuration subset\n\n\nWandbConfig\nWandb configuration subset\n\n\n\n\n\nutils.schemas.integrations.CometConfig()\nComet configuration subset\n\n\n\nutils.schemas.integrations.GradioConfig()\nGradio configuration subset\n\n\n\nutils.schemas.integrations.LISAConfig()\nLISA configuration subset\n\n\n\nutils.schemas.integrations.MLFlowConfig()\nMLFlow configuration subset\n\n\n\nutils.schemas.integrations.RayConfig()\nRay launcher configuration subset\n\n\n\nutils.schemas.integrations.WandbConfig()\nWandb configuration subset" + }, + { + "objectID": "docs/api/utils.schemas.integrations.html#classes", + "href": "docs/api/utils.schemas.integrations.html#classes", + "title": "utils.schemas.integrations", + "section": "", + "text": "Name\nDescription\n\n\n\n\nCometConfig\nComet configuration subset\n\n\nGradioConfig\nGradio configuration subset\n\n\nLISAConfig\nLISA configuration subset\n\n\nMLFlowConfig\nMLFlow configuration subset\n\n\nRayConfig\nRay launcher configuration subset\n\n\nWandbConfig\nWandb configuration subset\n\n\n\n\n\nutils.schemas.integrations.CometConfig()\nComet configuration subset\n\n\n\nutils.schemas.integrations.GradioConfig()\nGradio configuration subset\n\n\n\nutils.schemas.integrations.LISAConfig()\nLISA configuration subset\n\n\n\nutils.schemas.integrations.MLFlowConfig()\nMLFlow configuration subset\n\n\n\nutils.schemas.integrations.RayConfig()\nRay launcher configuration subset\n\n\n\nutils.schemas.integrations.WandbConfig()\nWandb configuration subset" + }, + { + "objectID": "docs/api/utils.tokenization.html", + "href": "docs/api/utils.tokenization.html", + "title": "utils.tokenization", + "section": "", + "text": "utils.tokenization\nModule for tokenization utilities\n\n\n\n\n\nName\nDescription\n\n\n\n\ncolor_token_for_rl_debug\nHelper function to color tokens based on their type.\n\n\nprocess_tokens_for_rl_debug\nHelper function to process and color tokens.\n\n\n\n\n\nutils.tokenization.color_token_for_rl_debug(\n decoded_token,\n encoded_token,\n color,\n text_only,\n)\nHelper function to color tokens based on their type.\n\n\n\nutils.tokenization.process_tokens_for_rl_debug(\n tokens,\n color,\n tokenizer,\n text_only,\n)\nHelper function to process and color tokens." + }, + { + "objectID": "docs/api/utils.tokenization.html#functions", + "href": "docs/api/utils.tokenization.html#functions", + "title": "utils.tokenization", + "section": "", + "text": "Name\nDescription\n\n\n\n\ncolor_token_for_rl_debug\nHelper function to color tokens based on their type.\n\n\nprocess_tokens_for_rl_debug\nHelper function to process and color tokens.\n\n\n\n\n\nutils.tokenization.color_token_for_rl_debug(\n decoded_token,\n encoded_token,\n color,\n text_only,\n)\nHelper function to color tokens based on their type.\n\n\n\nutils.tokenization.process_tokens_for_rl_debug(\n tokens,\n color,\n tokenizer,\n text_only,\n)\nHelper function to process and color tokens." + }, + { + "objectID": "docs/api/utils.distributed.html", + "href": "docs/api/utils.distributed.html", + "title": "utils.distributed", + "section": "", + "text": "utils.distributed\nutility helpers for distributed checks\n\n\n\n\n\nName\nDescription\n\n\n\n\nbarrier\nActs as a barrier to wait for all processes. This ensures that all processes\n\n\ncleanup_distributed\nDestroy process group if torch distributed is initialized. Called in training early\n\n\ncompute_and_broadcast\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\n\n\ngather_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\ngather_scalar_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\nis_distributed\nCheck if distributed training is initialized.\n\n\nis_main_process\nCheck if the current process is the main process. If not in distributed mode,\n\n\nreduce_and_broadcast\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\n\n\nzero_first\nruns the wrapped context so that rank 0 runs first before other ranks\n\n\n\n\n\nutils.distributed.barrier()\nActs as a barrier to wait for all processes. This ensures that all processes\nreach the barrier before proceeding further.\n\n\n\nutils.distributed.cleanup_distributed()\nDestroy process group if torch distributed is initialized. Called in training early\ntermination or when training successfully completes.\n\n\n\nutils.distributed.compute_and_broadcast(fn)\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\nThe value is then broadcasted to all other ranks.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that computes the value. Default is 0.\nReturns:\n- The computed value (int or float).\n\n\n\nutils.distributed.gather_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.gather_scalar_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.is_distributed()\nCheck if distributed training is initialized.\n\n\n\nutils.distributed.is_main_process(use_environ=False)\nCheck if the current process is the main process. If not in distributed mode,\nalways return True.\nArgs:\n- use_environ (bool, optional): Use environment variable to determine main process.\nReturns:\n- bool: True if the current process is the main process, False otherwise.\n\n\n\nutils.distributed.reduce_and_broadcast(fn1, fn2)\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\nand then broadcast the reduced result to all ranks.\nArgs:\n- fn1 (callable): A function that computes the value on each rank.\n- fn2 (callable): A reduction function that takes a list of values and returns a single value.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- The reduced and broadcasted value.\n\n\n\nutils.distributed.zero_first(is_main)\nruns the wrapped context so that rank 0 runs first before other ranks" + }, + { + "objectID": "docs/api/utils.distributed.html#functions", + "href": "docs/api/utils.distributed.html#functions", + "title": "utils.distributed", + "section": "", + "text": "Name\nDescription\n\n\n\n\nbarrier\nActs as a barrier to wait for all processes. This ensures that all processes\n\n\ncleanup_distributed\nDestroy process group if torch distributed is initialized. Called in training early\n\n\ncompute_and_broadcast\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\n\n\ngather_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\ngather_scalar_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\nis_distributed\nCheck if distributed training is initialized.\n\n\nis_main_process\nCheck if the current process is the main process. If not in distributed mode,\n\n\nreduce_and_broadcast\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\n\n\nzero_first\nruns the wrapped context so that rank 0 runs first before other ranks\n\n\n\n\n\nutils.distributed.barrier()\nActs as a barrier to wait for all processes. This ensures that all processes\nreach the barrier before proceeding further.\n\n\n\nutils.distributed.cleanup_distributed()\nDestroy process group if torch distributed is initialized. Called in training early\ntermination or when training successfully completes.\n\n\n\nutils.distributed.compute_and_broadcast(fn)\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\nThe value is then broadcasted to all other ranks.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that computes the value. Default is 0.\nReturns:\n- The computed value (int or float).\n\n\n\nutils.distributed.gather_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.gather_scalar_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.is_distributed()\nCheck if distributed training is initialized.\n\n\n\nutils.distributed.is_main_process(use_environ=False)\nCheck if the current process is the main process. If not in distributed mode,\nalways return True.\nArgs:\n- use_environ (bool, optional): Use environment variable to determine main process.\nReturns:\n- bool: True if the current process is the main process, False otherwise.\n\n\n\nutils.distributed.reduce_and_broadcast(fn1, fn2)\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\nand then broadcast the reduced result to all ranks.\nArgs:\n- fn1 (callable): A function that computes the value on each rank.\n- fn2 (callable): A reduction function that takes a list of values and returns a single value.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- The reduced and broadcasted value.\n\n\n\nutils.distributed.zero_first(is_main)\nruns the wrapped context so that rank 0 runs first before other ranks" + }, + { + "objectID": "docs/api/prompt_strategies.bradley_terry.llama3.html", + "href": "docs/api/prompt_strategies.bradley_terry.llama3.html", + "title": "prompt_strategies.bradley_terry.llama3", + "section": "", + "text": "prompt_strategies.bradley_terry.llama3\nchatml transforms for datasets with system, input, chosen, rejected to match llama3 chat template\n\n\n\n\n\nName\nDescription\n\n\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.bradley_terry.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs" + }, + { + "objectID": "docs/api/prompt_strategies.bradley_terry.llama3.html#functions", + "href": "docs/api/prompt_strategies.bradley_terry.llama3.html#functions", + "title": "prompt_strategies.bradley_terry.llama3", + "section": "", + "text": "Name\nDescription\n\n\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.bradley_terry.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs" + }, + { + "objectID": "docs/api/common.const.html", + "href": "docs/api/common.const.html", + "title": "common.const", + "section": "", + "text": "common.const\ncommon.const\nVarious shared constants" + }, + { + "objectID": "docs/api/core.trainers.grpo.sampler.html", + "href": "docs/api/core.trainers.grpo.sampler.html", + "title": "core.trainers.grpo.sampler", + "section": "", + "text": "core.trainers.grpo.sampler\nRepeat random sampler (similar to the one implemented in\nhttps://github.com/huggingface/trl/blob/main/trl/trainer/grpo_trainer.py) that adds\nsequence parallelism functionality; i.e., duplicating data across ranks in the same\nsequence parallel group.\n\n\n\n\n\nName\nDescription\n\n\n\n\nSequenceParallelRepeatRandomSampler\nSampler for GRPO training with sequence parallelism.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler(\n self,\n dataset,\n mini_repeat_count,\n world_size,\n rank,\n batch_size=1,\n repeat_count=1,\n sequence_parallel_degree=1,\n shuffle=True,\n seed=0,\n drop_last=False,\n)\nSampler for GRPO training with sequence parallelism.\nThis sampler ensures:\n- Ranks in the same sequence parallel (SP) group receive identical data.\n- Each index is repeated multiple times for sampling different completions.\n- Entire batches are repeated for reuse in multiple updates.\n- Data is properly distributed across SP groups.\nIn the table below, the values represent dataset indices. Each SP group has\nsequence_parallel_degree = 2 GPUs working together on the same data. There are 2\nSP groups (SP0 and SP1), with world_size = 4 total GPUs.\n Sequence Parallel Groups\n | SP0 | SP1 |\n | GPU 0 | GPU 1 | GPU 2 | GPU 3 |\n global_step step <---> mini_repeat_count=3\n <----------> batch_size=2 per SP group\ngrad_accum=2 ▲ ▲ 0 0 [0 0 0 1 1 1] [2 2 2 3 3 3] <- SP groups get different data\n▼ | 0 1 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Same data for each SP group GPU\n|\n| 1 2 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Repeat same indices for iterations\nnum_iterations=2 ▼ 1 3 [0 0 0 1 1 1] [2 2 2 3 3 3] <- When using gradient accumulation\n 2 4 [4 4 4 5 5 5] [6 6 6 7 7 7] <- New batch of data indices\n 2 5 [4 4 4 5 5 5] [6 6 6 7 7 7]\n ...\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nSized\nDataset to sample from.\nrequired\n\n\nmini_repeat_count\nint\nHow many times to repeat each sample immediately.\nrequired\n\n\nworld_size\nint\nTotal number of processes.\nrequired\n\n\nrank\nint\nRank of current process.\nrequired\n\n\nbatch_size\nint\nNumber of samples per batch.\n1\n\n\nrepeat_count\nint\nHow many times to repeat the full sampling process.\n1\n\n\nsequence_parallel_degree\nint\nNumber of ranks in a sequence parallel group.\n1\n\n\nshuffle\nbool\nWhether to shuffle the dataset.\nTrue\n\n\nseed\nint\nRandom seed for shuffling.\n0\n\n\ndrop_last\nbool\nWhether to drop the last incomplete batch.\nFalse\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nset_epoch\nSets the epoch for this sampler.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler.set_epoch(epoch)\nSets the epoch for this sampler.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nepoch\nint\nEpoch number to use for shuffling.\nrequired" + }, + { + "objectID": "docs/api/core.trainers.grpo.sampler.html#classes", + "href": "docs/api/core.trainers.grpo.sampler.html#classes", + "title": "core.trainers.grpo.sampler", + "section": "", + "text": "Name\nDescription\n\n\n\n\nSequenceParallelRepeatRandomSampler\nSampler for GRPO training with sequence parallelism.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler(\n self,\n dataset,\n mini_repeat_count,\n world_size,\n rank,\n batch_size=1,\n repeat_count=1,\n sequence_parallel_degree=1,\n shuffle=True,\n seed=0,\n drop_last=False,\n)\nSampler for GRPO training with sequence parallelism.\nThis sampler ensures:\n- Ranks in the same sequence parallel (SP) group receive identical data.\n- Each index is repeated multiple times for sampling different completions.\n- Entire batches are repeated for reuse in multiple updates.\n- Data is properly distributed across SP groups.\nIn the table below, the values represent dataset indices. Each SP group has\nsequence_parallel_degree = 2 GPUs working together on the same data. There are 2\nSP groups (SP0 and SP1), with world_size = 4 total GPUs.\n Sequence Parallel Groups\n | SP0 | SP1 |\n | GPU 0 | GPU 1 | GPU 2 | GPU 3 |\n global_step step <---> mini_repeat_count=3\n <----------> batch_size=2 per SP group\ngrad_accum=2 ▲ ▲ 0 0 [0 0 0 1 1 1] [2 2 2 3 3 3] <- SP groups get different data\n▼ | 0 1 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Same data for each SP group GPU\n|\n| 1 2 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Repeat same indices for iterations\nnum_iterations=2 ▼ 1 3 [0 0 0 1 1 1] [2 2 2 3 3 3] <- When using gradient accumulation\n 2 4 [4 4 4 5 5 5] [6 6 6 7 7 7] <- New batch of data indices\n 2 5 [4 4 4 5 5 5] [6 6 6 7 7 7]\n ...\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nSized\nDataset to sample from.\nrequired\n\n\nmini_repeat_count\nint\nHow many times to repeat each sample immediately.\nrequired\n\n\nworld_size\nint\nTotal number of processes.\nrequired\n\n\nrank\nint\nRank of current process.\nrequired\n\n\nbatch_size\nint\nNumber of samples per batch.\n1\n\n\nrepeat_count\nint\nHow many times to repeat the full sampling process.\n1\n\n\nsequence_parallel_degree\nint\nNumber of ranks in a sequence parallel group.\n1\n\n\nshuffle\nbool\nWhether to shuffle the dataset.\nTrue\n\n\nseed\nint\nRandom seed for shuffling.\n0\n\n\ndrop_last\nbool\nWhether to drop the last incomplete batch.\nFalse\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nset_epoch\nSets the epoch for this sampler.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler.set_epoch(epoch)\nSets the epoch for this sampler.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nepoch\nint\nEpoch number to use for shuffling.\nrequired" + }, + { + "objectID": "docs/api/prompt_strategies.user_defined.html", + "href": "docs/api/prompt_strategies.user_defined.html", + "title": "prompt_strategies.user_defined", + "section": "", + "text": "prompt_strategies.user_defined\nUser Defined prompts with configuration from the YML config\n\n\n\n\n\nName\nDescription\n\n\n\n\nUserDefinedDatasetConfig\ndataclass configuration representing a userdefined dataset type\n\n\nUserDefinedPromptTokenizationStrategy\nPrompt Tokenization Strategy for user defined prompts\n\n\n\n\n\nprompt_strategies.user_defined.UserDefinedDatasetConfig(\n self,\n system_prompt='',\n field_system='system',\n field_instruction='instruction',\n field_input='input',\n field_output='output',\n format='{instruction} {input} ',\n no_input_format='{instruction} ',\n system_format='{system}',\n)\ndataclass configuration representing a userdefined dataset type\n\n\n\nprompt_strategies.user_defined.UserDefinedPromptTokenizationStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nPrompt Tokenization Strategy for user defined prompts" + }, + { + "objectID": "docs/api/prompt_strategies.user_defined.html#classes", + "href": "docs/api/prompt_strategies.user_defined.html#classes", + "title": "prompt_strategies.user_defined", + "section": "", + "text": "Name\nDescription\n\n\n\n\nUserDefinedDatasetConfig\ndataclass configuration representing a userdefined dataset type\n\n\nUserDefinedPromptTokenizationStrategy\nPrompt Tokenization Strategy for user defined prompts\n\n\n\n\n\nprompt_strategies.user_defined.UserDefinedDatasetConfig(\n self,\n system_prompt='',\n field_system='system',\n field_instruction='instruction',\n field_input='input',\n field_output='output',\n format='{instruction} {input} ',\n no_input_format='{instruction} ',\n system_format='{system}',\n)\ndataclass configuration representing a userdefined dataset type\n\n\n\nprompt_strategies.user_defined.UserDefinedPromptTokenizationStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nPrompt Tokenization Strategy for user defined prompts" + }, + { + "objectID": "docs/api/utils.models.html", + "href": "docs/api/utils.models.html", + "title": "utils.models", + "section": "", + "text": "utils.models\nModule for models and model loading\n\n\n\n\n\nName\nDescription\n\n\n\n\nModelLoader\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nutils.models.ModelLoader(\n self,\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nName\nDescription\n\n\n\n\nhas_flash_attn\nCheck if flash attention is installed\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\npatch_llama_derived_model\nModify all llama derived models in one block\n\n\npatch_loss_llama\nPatch loss functions and other optimizations\n\n\nset_attention_config\nsample packing uses custom FA2 patch\n\n\nset_auto_model_loader\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n\n\n\n\n\nutils.models.ModelLoader.patch_llama_derived_model()\nModify all llama derived models in one block\n\n\n\nutils.models.ModelLoader.patch_loss_llama()\nPatch loss functions and other optimizations\n\n\n\nutils.models.ModelLoader.set_attention_config()\nsample packing uses custom FA2 patch\n\n\n\nutils.models.ModelLoader.set_auto_model_loader()\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n(set at __init__). When using a multimodal model, self.auto_model_loader\nshould be set according to the type of the model.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_module_class_from_name\nGets a class from a module by its name.\n\n\nload_model\nLoad a model for a given configuration and tokenizer.\n\n\nload_tokenizer\nLoad and configure the tokenizer based on the provided config.\n\n\nmodify_tokenizer_files\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\n\n\nsetup_quantized_meta_for_peft\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\nsetup_quantized_peft_meta_for_training\nReplaces dummy quant_state.to method with the original function to allow training to continue\n\n\n\n\n\nutils.models.get_module_class_from_name(module, name)\nGets a class from a module by its name.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodule\ntorch.nn.Module\nThe module to get the class from.\nrequired\n\n\nname\nstr\nThe name of the class.\nrequired\n\n\n\n\n\n\n\nutils.models.load_model(\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nLoad a model for a given configuration and tokenizer.\n\n\n\nutils.models.load_tokenizer(cfg)\nLoad and configure the tokenizer based on the provided config.\n\n\n\nutils.models.modify_tokenizer_files(tokenizer_path, token_mappings, output_dir)\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\nThis only works with reserved tokens that were added to the tokenizer, not tokens already part of the vocab.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer_path\nstr\nPath or name of the original tokenizer\nrequired\n\n\ntoken_mappings\nDict[int, str]\nDict mapping {token_id (int): new_token_string}\nrequired\n\n\noutput_dir\nstr\nDirectory to save the modified tokenizer\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to the modified tokenizer directory\n\n\n\nRef: https://github.com/huggingface/transformers/issues/27974#issuecomment-1854188941\n\n\n\n\nutils.models.setup_quantized_meta_for_peft(model)\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\n\nutils.models.setup_quantized_peft_meta_for_training(model)\nReplaces dummy quant_state.to method with the original function to allow training to continue" + }, + { + "objectID": "docs/api/utils.models.html#classes", + "href": "docs/api/utils.models.html#classes", + "title": "utils.models", + "section": "", + "text": "Name\nDescription\n\n\n\n\nModelLoader\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nutils.models.ModelLoader(\n self,\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nName\nDescription\n\n\n\n\nhas_flash_attn\nCheck if flash attention is installed\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\npatch_llama_derived_model\nModify all llama derived models in one block\n\n\npatch_loss_llama\nPatch loss functions and other optimizations\n\n\nset_attention_config\nsample packing uses custom FA2 patch\n\n\nset_auto_model_loader\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n\n\n\n\n\nutils.models.ModelLoader.patch_llama_derived_model()\nModify all llama derived models in one block\n\n\n\nutils.models.ModelLoader.patch_loss_llama()\nPatch loss functions and other optimizations\n\n\n\nutils.models.ModelLoader.set_attention_config()\nsample packing uses custom FA2 patch\n\n\n\nutils.models.ModelLoader.set_auto_model_loader()\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n(set at __init__). When using a multimodal model, self.auto_model_loader\nshould be set according to the type of the model." + }, + { + "objectID": "docs/api/utils.models.html#functions", + "href": "docs/api/utils.models.html#functions", + "title": "utils.models", + "section": "", + "text": "Name\nDescription\n\n\n\n\nget_module_class_from_name\nGets a class from a module by its name.\n\n\nload_model\nLoad a model for a given configuration and tokenizer.\n\n\nload_tokenizer\nLoad and configure the tokenizer based on the provided config.\n\n\nmodify_tokenizer_files\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\n\n\nsetup_quantized_meta_for_peft\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\nsetup_quantized_peft_meta_for_training\nReplaces dummy quant_state.to method with the original function to allow training to continue\n\n\n\n\n\nutils.models.get_module_class_from_name(module, name)\nGets a class from a module by its name.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodule\ntorch.nn.Module\nThe module to get the class from.\nrequired\n\n\nname\nstr\nThe name of the class.\nrequired\n\n\n\n\n\n\n\nutils.models.load_model(\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nLoad a model for a given configuration and tokenizer.\n\n\n\nutils.models.load_tokenizer(cfg)\nLoad and configure the tokenizer based on the provided config.\n\n\n\nutils.models.modify_tokenizer_files(tokenizer_path, token_mappings, output_dir)\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\nThis only works with reserved tokens that were added to the tokenizer, not tokens already part of the vocab.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer_path\nstr\nPath or name of the original tokenizer\nrequired\n\n\ntoken_mappings\nDict[int, str]\nDict mapping {token_id (int): new_token_string}\nrequired\n\n\noutput_dir\nstr\nDirectory to save the modified tokenizer\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to the modified tokenizer directory\n\n\n\nRef: https://github.com/huggingface/transformers/issues/27974#issuecomment-1854188941\n\n\n\n\nutils.models.setup_quantized_meta_for_peft(model)\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\n\nutils.models.setup_quantized_peft_meta_for_training(model)\nReplaces dummy quant_state.to method with the original function to allow training to continue" + }, + { + "objectID": "docs/api/utils.lora_embeddings.html", + "href": "docs/api/utils.lora_embeddings.html", + "title": "utils.lora_embeddings", + "section": "", + "text": "utils.lora_embeddings\nhelpers for lora embeddings\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_linear_embedding_layers\nreturns the linear embedding layers needed for loras, dependent on the model arch\n\n\n\n\n\nutils.lora_embeddings.get_linear_embedding_layers(model_type)\nreturns the linear embedding layers needed for loras, dependent on the model arch" + }, + { + "objectID": "docs/api/utils.lora_embeddings.html#functions", + "href": "docs/api/utils.lora_embeddings.html#functions", + "title": "utils.lora_embeddings", + "section": "", + "text": "Name\nDescription\n\n\n\n\nget_linear_embedding_layers\nreturns the linear embedding layers needed for loras, dependent on the model arch\n\n\n\n\n\nutils.lora_embeddings.get_linear_embedding_layers(model_type)\nreturns the linear embedding layers needed for loras, dependent on the model arch" + }, + { + "objectID": "docs/api/cli.train.html", + "href": "docs/api/cli.train.html", + "title": "cli.train", + "section": "", + "text": "cli.train\nCLI to run training on a model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_train.\n\n\ndo_train\nTrains a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.train.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_train.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.train.do_train(cfg, cli_args)\nTrains a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.train.train. Also runs the plugin\nmanager’s post_train_unload once training completes.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nTraining-specific CLI arguments.\nrequired" + }, + { + "objectID": "docs/api/cli.train.html#functions", + "href": "docs/api/cli.train.html#functions", + "title": "cli.train", + "section": "", + "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_train.\n\n\ndo_train\nTrains a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.train.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_train.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.train.do_train(cfg, cli_args)\nTrains a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.train.train. Also runs the plugin\nmanager’s post_train_unload once training completes.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nTraining-specific CLI arguments.\nrequired" + }, + { + "objectID": "docs/api/datasets.html", + "href": "docs/api/datasets.html", + "title": "datasets", + "section": "", + "text": "datasets\nModule containing Dataset functionality\n\n\n\n\n\nName\nDescription\n\n\n\n\nConstantLengthDataset\nIterable dataset that returns constant length chunks of tokens from stream of text files.\n\n\nTokenizedPromptDataset\nDataset that returns tokenized prompts from a stream of text files.\n\n\n\n\n\ndatasets.ConstantLengthDataset(self, tokenizer, datasets, seq_length=2048)\nIterable dataset that returns constant length chunks of tokens from stream of text files.\nArgs:\ntokenizer (Tokenizer): The processor used for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nseq_length (int): Length of token sequences to return.\n\n\n\ndatasets.TokenizedPromptDataset(\n self,\n prompt_tokenizer,\n dataset,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nDataset that returns tokenized prompts from a stream of text files.\nArgs:\nprompt_tokenizer (PromptTokenizingStrategy): The prompt tokenizing method for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nprocess_count (int): Number of processes to use for tokenizing.\nkeep_in_memory (bool): Whether to keep the tokenized dataset in memory." + }, + { + "objectID": "docs/api/datasets.html#classes", + "href": "docs/api/datasets.html#classes", + "title": "datasets", + "section": "", + "text": "Name\nDescription\n\n\n\n\nConstantLengthDataset\nIterable dataset that returns constant length chunks of tokens from stream of text files.\n\n\nTokenizedPromptDataset\nDataset that returns tokenized prompts from a stream of text files.\n\n\n\n\n\ndatasets.ConstantLengthDataset(self, tokenizer, datasets, seq_length=2048)\nIterable dataset that returns constant length chunks of tokens from stream of text files.\nArgs:\ntokenizer (Tokenizer): The processor used for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nseq_length (int): Length of token sequences to return.\n\n\n\ndatasets.TokenizedPromptDataset(\n self,\n prompt_tokenizer,\n dataset,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nDataset that returns tokenized prompts from a stream of text files.\nArgs:\nprompt_tokenizer (PromptTokenizingStrategy): The prompt tokenizing method for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nprocess_count (int): Number of processes to use for tokenizing.\nkeep_in_memory (bool): Whether to keep the tokenized dataset in memory." + }, + { + "objectID": "src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html", + "href": "src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html", "title": "Axolotl", "section": "", - "text": "AXOLOTL COMMUNITY LICENSE AGREEMENT\nThis Axolotl Community License Agreement (“Agreement”) is entered into by and between Axolotl AI Corp. (“Axolotl”) and\nany individual or entity (“Licensee”) who wishes to use the Software (as defined below) in accordance with the terms\nand conditions set forth in this Agreement.\n\nDefinitions\n1.1 “Licensee” refers to any individual or entity who has obtained a copy of the Software under this Agreement.\n1.2 “Plugin Integration” means independent integration software modules which may or may not be offered by Axolotl,\nwhich may be licensed separately by their respective authors and/or licensors.\n1.3 “Software” refers to the specific sub-directory of the Axolotl, Inc. software located at\nhttps://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations and its subdirectories which\npermits Plugin Integrations to integrate with the Axolotl service.\nGrant of License\n2.1 Axolotl hereby grants Licensee a worldwide, non-exclusive, royalty-free, license to use, copy, modify, merge,\npublish, distribute, sublicense, and/or otherwise exploit the Software, subject to the following conditions:\n- Licensee must comply with all the terms and conditions of this Agreement.\n- Licensee must include the original copyright notice and disclaimer of warranty in all copies or substantial\nportions of the Software.\n2.2 Licensee may use the Software for any lawful purpose, except as restricted in Section 3.\nRestrictions\n3.1 Licensee shall not use the Software for any activity that constitutes a commercial activity of offering for\nfree or for sale any services, platform, or equivalent to third parties for the purposes of allowing such\nthird parties to fine-tune artificial intelligence models.\n3.2 Licensee shall not:\n- Use the Software for any illegal or unauthorized purpose.\n- Reverse engineer, decompile, or disassemble the Software.\n- Remove or modify any copyright, trademark, or other proprietary notices contained in the Software.\n- Use the Software in a way that could damage, disable, overburden, or impair the functionality of the\nSoftware or interfere with any third-party use of the Software.\n3.3 Axolotl reserves the right to restrict certain Plugin Integrations for use with the Software. To the extent Licensee integrates a permitted, applicable Plugin Integration with the Software, Licensee shall comply with any additional terms and conditions imposed by the licensors of such Plugin Integration for use of such Plugin Integrations. Licensee shall contact Axolotl if it has questions about whether its use of the Software falls beyond the scope of this Agreement.\nIntellectual Property Rights\n4.1 Axolotl and its contributors retain all intellectual property rights in and to the Software. Licensee\nacknowledges that this Agreement does not transfer any ownership rights or intellectual property rights to\nLicensee.\nDisclaimer of Warranty\n5.1 THE SOFTWARE IS PROVIDED “AS IS,” WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED\nTO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. IN NO EVENT SHALL\nTHE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN AN ACTION OF\nCONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF, OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER\nDEALINGS IN THE SOFTWARE.\nTermination\n6.1 Axolotl may terminate this Agreement at any time if Licensee fails to comply with any of the terms and\nconditions set forth herein. Upon termination, Licensee shall cease all use of the Software and destroy any\ncopies in its possession.\nGoverning Law\n7.1 This Agreement shall be governed by and construed in accordance with the laws of the State of California,\nwithout regards to conflicts of laws provisions thereof.\nEntire Agreement\n8.1 This Agreement constitutes the entire agreement between Axolotl and Licensee with respect to the subject matter\nhereof and supersedes all prior or contemporaneous understandings or agreements between the parties concerning\nthe Software, whether written or oral. Axolotl may update the terms of this Agreement from time to time, and\nLicensee’s continued use of the Software after any such updates shall constitute acceptance of updated terms\non a go-forward basis. Axolotl will use commercially reasonable efforts to provide Licensee notice of any\nmaterial updates. By using the Software, Licensee acknowledges that it has read, understood, and agrees to be\nbound by the terms and conditions of this Agreement.\n\nThis Agreement was last updated on August 23, 2024." - }, - { - "objectID": "FAQS.html", - "href": "FAQS.html", - "title": "FAQs", - "section": "", - "text": "FAQs\n\nCan you train StableLM with this? Yes, but only with a single GPU atm. Multi GPU support is coming soon! Just waiting on this PR\nWill this work with Deepspeed? That’s still a WIP, but setting export ACCELERATE_USE_DEEPSPEED=true should work in some cases\nError invalid argument at line 359 in file /workspace/bitsandbytes/csrc/pythonInterface.c\n/arrow/cpp/src/arrow/filesystem/s3fs.cc:2598: arrow::fs::FinalizeS3 was not called even though S3 was initialized.\nThis could lead to a segmentation fault at exit. Try reinstalling bitsandbytes and transformers from source." - }, - { - "objectID": "examples/colab-notebooks/colab-axolotl-example.html", - "href": "examples/colab-notebooks/colab-axolotl-example.html", - "title": "Setting up", - "section": "", - "text": "import torch\n# Check so there is a gpu available, a T4(free tier) is enough to run this notebook\nassert (torch.cuda.is_available()==True)\n!pip install --no-build-isolation axolotl[deepspeed]" - }, - { - "objectID": "examples/colab-notebooks/colab-axolotl-example.html#hugging-face-login-optional", - "href": "examples/colab-notebooks/colab-axolotl-example.html#hugging-face-login-optional", - "title": "Setting up", - "section": "Hugging Face login (optional)", - "text": "Hugging Face login (optional)\n\nfrom huggingface_hub import notebook_login\nnotebook_login()" - }, - { - "objectID": "examples/colab-notebooks/colab-axolotl-example.html#example-configuration", - "href": "examples/colab-notebooks/colab-axolotl-example.html#example-configuration", - "title": "Setting up", - "section": "Example configuration", - "text": "Example configuration\n\nimport yaml\n\nyaml_string = \"\"\"\nbase_model: NousResearch/Meta-Llama-3.1-8B\n\nload_in_8bit: false\nload_in_4bit: true\nstrict: false\n\ndatasets:\n - path: tatsu-lab/alpaca\n type: alpaca\ndataset_prepared_path: last_run_prepared\nval_set_size: 0.05\noutput_dir: ./outputs/lora-out\n\nsequence_len: 2048\nsample_packing: true\neval_sample_packing: true\npad_to_sequence_len: true\n\nadapter: qlora\nlora_model_dir:\nlora_r: 32\nlora_alpha: 16\nlora_dropout: 0.05\nlora_target_linear: true\nlora_fan_in_fan_out:\nlora_modules_to_save:\n - embed_tokens\n - lm_head\n\nwandb_project:\nwandb_entity:\nwandb_watch:\nwandb_name:\nwandb_log_model:\n\ngradient_accumulation_steps: 2\nmicro_batch_size: 1\nnum_epochs: 1\noptimizer: paged_adamw_8bit\nlr_scheduler: cosine\nlearning_rate: 2e-5\n\ntrain_on_inputs: false\ngroup_by_length: false\nbf16: auto\nfp16:\ntf32: false\n\ngradient_checkpointing: true\nearly_stopping_patience:\nresume_from_checkpoint:\nlogging_steps: 1\nxformers_attention:\nflash_attention: false\nsdp_attention: true\n\nwarmup_steps: 1\nmax_steps: 25\nevals_per_epoch: 1\neval_table_size:\nsaves_per_epoch: 1\ndebug:\ndeepspeed:\nweight_decay: 0.0\nfsdp:\nfsdp_config:\nspecial_tokens:\n pad_token: <|end_of_text|>\n\"\"\"\n\n\n# Convert the YAML string to a Python dictionary\nyaml_dict = yaml.safe_load(yaml_string)\n\n# Specify your file path\nfile_path = 'test_axolotl.yaml'\n\n# Write the YAML file\nwith open(file_path, 'w') as file:\n yaml.dump(yaml_dict, file)\n\nAbove we have a configuration file with base LLM model and datasets specified, among many other things. Axolotl can automatically detect whether the specified datasets are on HuggingFace repo or local machine.\nThe Axolotl configuration options encompass model and dataset selection, data pre-processing, and training. Let’s go through them line by line:\n\n“base model”: String value, specifies the underlying pre-trained LLM that will be used for finetuning\n\nNext we have options for model weights quantization. Quantization allows for reduction in occupied memory on GPUs.\n\n“load_in_8bit”: Boolean value, whether to quantize the model weights into 8-bit integer.\n“load_in_4bit”: Boolean value, whether to quantize the model weights into 4-bit integer.\n“strict”: Boolean value. If false, it allows for overriding established configuration options in the yaml file when executing in command-line interface.\n“datasets”: a list of dicts that contain path and type of data sets as well as other optional configurations where datasets are concerned. Supports multiple datasets.\n“val_set_size”: Either a float value less than one or an integer less than the total size of dataset. Sets the size of validation set from the whole dataset. If float, sets the proportion of the dataset assigned for validation. If integer, sets the direct size of validation set.\n“output_dir”: String value. Path of trained model.\n\nFor data preprocessing:\n\n“sequence_len”: Integer. Specifies the maximum sequence length of the input. Typically 2048 or less.\n“pad_to_sequence_len”: Boolean. Padding input to maximum sequence length.\n“sample_packing”: Boolean. Specifies whether to use multi-packing with block diagonal attention.\n“special_tokens”: Python dict, optional. Allows users to specify the additional special tokens to be ignored by the tokenizer.\n\nFor LoRA configuration and its hyperparamters:\n\n“adapter”: String. Either “lora” or “qlora”, depending on user’s choice.\n“lora_model_dir”: String, Optional. Path to directory that contains LoRA model, if there is already a trained LoRA model the user would like to use.\n“lora_r”: Integer. Refers to the rank of LoRA decomposition matrices. Higher value will reduce LoRA efficiency. Recommended to be set to 8.\n“lora_alpha”: Integer. Scale the weight matrices by \\(\\frac{\\text{lora_alpha}}{\\text{lora_r}}\\)Recommended to be fixed at 16.\n“lora_dropout”: Float that is 1 or less. The dropout probability of a lora layer.\n“lora_target_linear”: Boolean. If true, lora will target all linear modules in the transformers architecture.\n“lora_modules_to_save”: If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens.\n\nSee LoRA for detailed explanation of LoRA implementation.\nFor the training configurations:\n\n“gradient_accumulation_steps”: Integer. The number of steps over which to accumulate gradient for batch training. E.g. if 2, backprop is performed every two steps.\n“micro_batch_size”: Integer. Batch size per gpu / gradient_accumulation_steps\n“num_epochs”: Integer. Number of epochs. One epoch is when training has looped over every batch in the whole data set once.\n“optimizer”: The optimizer to use for the training.\n“learning_rate”: The learning rate.\n“lr_scheduler”: The learning rate scheduler to use for adjusting learning rate during training.\n“train_on_inputs”: Boolean. Whether to ignore or include the user’s prompt from the training labels.\n“group_by_length”: Boolean. Whether to group similarly sized data to minimize padding.\n“bf16”: Either “auto”, “true”, or “false”. Whether to use CUDA bf16 floating point format. If set to “auto”, will automatically apply bf16 should the gpu supports it.\n“fp16”: Optional. Specifies whether to use CUDA fp16. Automatically set to true if “bf16” is set to true. Otherwise false.\n“tf32”: Boolean. Whether to use CUDA tf32. Will override bf16.\n“gradient_checkpointing”: Boolean. Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing\n“gradient_checkpointing_kwargs”: Python Dict. Fed into the trainer.\n“logging_steps”: Integer. Log training information over every specified number of steps.\n“flash_attention”: Boolean. Whether to use the flash attention mechanism.\n“sdp_attention”: Boolean. Whether to use the Scaled Dot Product attention mechanism (the attention mechanism in the original implementation of transformers.)\n“warmup_steps”: Integer. The number of pre-training steps where a very low learning rate is used.\n“evals_per_epoch”: Integer. Number of evaluations to be performed within one training epoch.\n“saves_per_epoch”: Integer. Number of times the model is saved in one training epoch.\n“weight_decay”: Positive Float. Sets the “strength” of weight decay (i.e. setting the coefficient of L2 regularization)\n\nThe above is but a snippet aiming to get users familiarized with the types of streamlined configuration options axolotl provides. For a full list of configuration options, see here\nTrain the model\n\n!accelerate launch -m axolotl.cli.train /content/test_axolotl.yaml\n\nPredict with trained model\n\n!accelerate launch -m axolotl.cli.inference /content/test_axolotl.yaml \\\n --lora_model_dir=\"./outputs/lora-out\" --gradio" - }, - { - "objectID": "examples/colab-notebooks/colab-axolotl-example.html#deeper-dive", - "href": "examples/colab-notebooks/colab-axolotl-example.html#deeper-dive", - "title": "Setting up", - "section": "Deeper Dive", - "text": "Deeper Dive\nIt is also helpful to gain some familiarity over some of the core inner workings of axolotl" - }, - { - "objectID": "examples/colab-notebooks/colab-axolotl-example.html#configuration-normalization", - "href": "examples/colab-notebooks/colab-axolotl-example.html#configuration-normalization", - "title": "Setting up", - "section": "Configuration Normalization", - "text": "Configuration Normalization\nAxolotl uses a custom Dict class, called DictDefault\nto store configurations specified in the yaml configuration file (into a Python variable named cfg). The definition for this custom Dict can be found in the utils/dict.py\nDictDefault is amended such that calling a missing key from it will result in a None return type. This is important because if some configuration options aren’t specified by the user, the None type allows Axolotl to perform boolean operations to determine the default settings for missing configurations. For more examples on how this is done, check out utils/config/init.py" - }, - { - "objectID": "examples/colab-notebooks/colab-axolotl-example.html#loading-models-tokenizers-and-trainer", - "href": "examples/colab-notebooks/colab-axolotl-example.html#loading-models-tokenizers-and-trainer", - "title": "Setting up", - "section": "Loading Models, Tokenizers, and Trainer", - "text": "Loading Models, Tokenizers, and Trainer\nIf we inspect cli.train.py, we will find that most of the heavy lifting were done by the function train() which is itself imported from src/axolotl/train.py.\ntrain() takes care of loading the appropriate tokenizer and pre-trained model through load_model() and load_tokenizer() from src/axolotl/utils/models.py respectively.\nload_tokenizer() loads in the appropriate tokenizer given the desired model, as well as chat templates.\nModelLoader class follows after tokenizer has been selected. It will automatically discern the base model type, load in the desired model, as well as applying model-appropriate attention mechanism modifications (e.g. flash attention). Depending on which base model the user chooses in the configuration, ModelLoader will utilize the corresponding “attention hijacking” script. For example, if the user specified the base model to be NousResearch/Meta-Llama-3.1-8B, which is of llama type, and set flash_attn to True, ModelLoader will load in llama_attn_hijack_flash.py. For a list of supported attention hijacking, please refer to the directory /src/axolotl/monkeypatch/\nAnother important operation encompassed in train() is setting up the training that takes into account of user-specified traning configurations (e.g. num_epochs, optimizer) through the use of setup_trainer() from /src/axolotl/utils/trainer.py, which in turn relies on modules from /src/axolotl/core/trainer_builder.py.\ntrainer_builder.py provides a list of trainer object options bespoke for the task type (Causal or Reinforcement learning (‘dpo’, ‘ipo’, ‘kto’) )" - }, - { - "objectID": "examples/colab-notebooks/colab-axolotl-example.html#monkey-patch", - "href": "examples/colab-notebooks/colab-axolotl-example.html#monkey-patch", - "title": "Setting up", - "section": "Monkey patch", - "text": "Monkey patch\nThe Monkey patch directory is where model architecture/optimization patching scripts are stored (these are modifications that are not implemented in the official releases, hence the name monkey patch). It includes attention jacking, ReLoRA, and unsloth optimization." + "text": "Acknowledgements\nPortions of this Cut Cross Entropy Software may utilize the following copyrighted\nmaterial, the use of which is hereby acknowledged.\n\nPyTorch\nFrom PyTorch:\n\nCopyright (c) 2016- Facebook, Inc (Adam Paszke)\nCopyright (c) 2014- Facebook, Inc (Soumith Chintala)\nCopyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)\nCopyright (c) 2012-2014 Deepmind Technologies (Koray Kavukcuoglu)\nCopyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)\nCopyright (c) 2011-2013 NYU (Clement Farabet)\nCopyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)\nCopyright (c) 2006 Idiap Research Institute (Samy Bengio)\nCopyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)\n\nFrom Caffe2:\n\nCopyright (c) 2016-present, Facebook Inc. All rights reserved.\n\nAll contributions by Facebook:\nCopyright (c) 2016 Facebook Inc.\n\nAll contributions by Google:\nCopyright (c) 2015 Google Inc.\nAll rights reserved.\n\nAll contributions by Yangqing Jia:\nCopyright (c) 2015 Yangqing Jia\nAll rights reserved.\n\nAll contributions by Kakao Brain:\nCopyright 2019-2020 Kakao Brain\n\nAll contributions by Cruise LLC:\nCopyright (c) 2022 Cruise LLC.\nAll rights reserved.\n\nAll contributions by Arm:\nCopyright (c) 2021, 2023-2024 Arm Limited and/or its affiliates\n\nAll contributions from Caffe:\nCopyright(c) 2013, 2014, 2015, the respective contributors\nAll rights reserved.\n\nAll other contributions:\nCopyright(c) 2015, 2016 the respective contributors\nAll rights reserved.\n\nCaffe2 uses a copyright model similar to Caffe: each contributor holds\ncopyright over their contributions to Caffe2. The project versioning records\nall such contribution and copyright details. If a contributor wants to further\nmark their specific copyright on a particular contribution, they should\nindicate their copyright solely in the commit message of the change when it is\ncommitted.\n\nAll rights reserved.\n\nRedistribution and use in source and binary forms, with or without\nmodification, are permitted provided that the following conditions are met:\n\n1. Redistributions of source code must retain the above copyright\nnotice, this list of conditions and the following disclaimer.\n\n2. Redistributions in binary form must reproduce the above copyright\nnotice, this list of conditions and the following disclaimer in the\ndocumentation and/or other materials provided with the distribution.\n\n3. Neither the names of Facebook, Deepmind Technologies, NYU, NEC Laboratories America\nand IDIAP Research Institute nor the names of its contributors may be\nused to endorse or promote products derived from this software without\nspecific prior written permission.\n\nTHIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\"\nAND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE\nIMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE\nARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE\nLIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR\nCONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF\nSUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS\nINTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN\nCONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)\nARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE\nPOSSIBILITY OF SUCH DAMAGE.\nTriton\n/*\n* Copyright 2018-2020 Philippe Tillet\n* Copyright 2020-2022 OpenAI\n*\n* Permission is hereby granted, free of charge, to any person obtaining\n* a copy of this software and associated documentation files\n* (the \"Software\"), to deal in the Software without restriction,\n* including without limitation the rights to use, copy, modify, merge,\n* publish, distribute, sublicense, and/or sell copies of the Software,\n* and to permit persons to whom the Software is furnished to do so,\n* subject to the following conditions:\n*\n* The above copyright notice and this permission notice shall be\n* included in all copies or substantial portions of the Software.\n*\n* THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND,\n* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF\n* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.\n* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY\n* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,\n* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE\n* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n*/\nTransformers\nCopyright 2018- The Hugging Face team. All rights reserved.\n\n Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n\nTERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n1. Definitions.\n\n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n\n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n\n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n\n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n\n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n\n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n\n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n\n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n\n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n\n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n\n2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n\n3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n\n4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n\n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n\n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n\n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n\n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n\n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n\n5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n\n6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n\n7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n\n8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n\n9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n\nEND OF TERMS AND CONDITIONS\n\nAPPENDIX: How to apply the Apache License to your work.\n\n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n\nCopyright [yyyy] [name of copyright owner]\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License." }, { "objectID": "index.html", @@ -1962,1019 +2074,893 @@ ] }, { - "objectID": "src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html", - "href": "src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html", + "objectID": "examples/colab-notebooks/colab-axolotl-example.html", + "href": "examples/colab-notebooks/colab-axolotl-example.html", + "title": "Setting up", + "section": "", + "text": "import torch\n# Check so there is a gpu available, a T4(free tier) is enough to run this notebook\nassert (torch.cuda.is_available()==True)\n!pip install --no-build-isolation axolotl[deepspeed]" + }, + { + "objectID": "examples/colab-notebooks/colab-axolotl-example.html#hugging-face-login-optional", + "href": "examples/colab-notebooks/colab-axolotl-example.html#hugging-face-login-optional", + "title": "Setting up", + "section": "Hugging Face login (optional)", + "text": "Hugging Face login (optional)\n\nfrom huggingface_hub import notebook_login\nnotebook_login()" + }, + { + "objectID": "examples/colab-notebooks/colab-axolotl-example.html#example-configuration", + "href": "examples/colab-notebooks/colab-axolotl-example.html#example-configuration", + "title": "Setting up", + "section": "Example configuration", + "text": "Example configuration\n\nimport yaml\n\nyaml_string = \"\"\"\nbase_model: NousResearch/Meta-Llama-3.1-8B\n\nload_in_8bit: false\nload_in_4bit: true\nstrict: false\n\ndatasets:\n - path: tatsu-lab/alpaca\n type: alpaca\ndataset_prepared_path: last_run_prepared\nval_set_size: 0.05\noutput_dir: ./outputs/lora-out\n\nsequence_len: 2048\nsample_packing: true\neval_sample_packing: true\npad_to_sequence_len: true\n\nadapter: qlora\nlora_model_dir:\nlora_r: 32\nlora_alpha: 16\nlora_dropout: 0.05\nlora_target_linear: true\nlora_fan_in_fan_out:\nlora_modules_to_save:\n - embed_tokens\n - lm_head\n\nwandb_project:\nwandb_entity:\nwandb_watch:\nwandb_name:\nwandb_log_model:\n\ngradient_accumulation_steps: 2\nmicro_batch_size: 1\nnum_epochs: 1\noptimizer: paged_adamw_8bit\nlr_scheduler: cosine\nlearning_rate: 2e-5\n\ntrain_on_inputs: false\ngroup_by_length: false\nbf16: auto\nfp16:\ntf32: false\n\ngradient_checkpointing: true\nearly_stopping_patience:\nresume_from_checkpoint:\nlogging_steps: 1\nxformers_attention:\nflash_attention: false\nsdp_attention: true\n\nwarmup_steps: 1\nmax_steps: 25\nevals_per_epoch: 1\neval_table_size:\nsaves_per_epoch: 1\ndebug:\ndeepspeed:\nweight_decay: 0.0\nfsdp:\nfsdp_config:\nspecial_tokens:\n pad_token: <|end_of_text|>\n\"\"\"\n\n\n# Convert the YAML string to a Python dictionary\nyaml_dict = yaml.safe_load(yaml_string)\n\n# Specify your file path\nfile_path = 'test_axolotl.yaml'\n\n# Write the YAML file\nwith open(file_path, 'w') as file:\n yaml.dump(yaml_dict, file)\n\nAbove we have a configuration file with base LLM model and datasets specified, among many other things. Axolotl can automatically detect whether the specified datasets are on HuggingFace repo or local machine.\nThe Axolotl configuration options encompass model and dataset selection, data pre-processing, and training. Let’s go through them line by line:\n\n“base model”: String value, specifies the underlying pre-trained LLM that will be used for finetuning\n\nNext we have options for model weights quantization. Quantization allows for reduction in occupied memory on GPUs.\n\n“load_in_8bit”: Boolean value, whether to quantize the model weights into 8-bit integer.\n“load_in_4bit”: Boolean value, whether to quantize the model weights into 4-bit integer.\n“strict”: Boolean value. If false, it allows for overriding established configuration options in the yaml file when executing in command-line interface.\n“datasets”: a list of dicts that contain path and type of data sets as well as other optional configurations where datasets are concerned. Supports multiple datasets.\n“val_set_size”: Either a float value less than one or an integer less than the total size of dataset. Sets the size of validation set from the whole dataset. If float, sets the proportion of the dataset assigned for validation. If integer, sets the direct size of validation set.\n“output_dir”: String value. Path of trained model.\n\nFor data preprocessing:\n\n“sequence_len”: Integer. Specifies the maximum sequence length of the input. Typically 2048 or less.\n“pad_to_sequence_len”: Boolean. Padding input to maximum sequence length.\n“sample_packing”: Boolean. Specifies whether to use multi-packing with block diagonal attention.\n“special_tokens”: Python dict, optional. Allows users to specify the additional special tokens to be ignored by the tokenizer.\n\nFor LoRA configuration and its hyperparamters:\n\n“adapter”: String. Either “lora” or “qlora”, depending on user’s choice.\n“lora_model_dir”: String, Optional. Path to directory that contains LoRA model, if there is already a trained LoRA model the user would like to use.\n“lora_r”: Integer. Refers to the rank of LoRA decomposition matrices. Higher value will reduce LoRA efficiency. Recommended to be set to 8.\n“lora_alpha”: Integer. Scale the weight matrices by \\(\\frac{\\text{lora_alpha}}{\\text{lora_r}}\\)Recommended to be fixed at 16.\n“lora_dropout”: Float that is 1 or less. The dropout probability of a lora layer.\n“lora_target_linear”: Boolean. If true, lora will target all linear modules in the transformers architecture.\n“lora_modules_to_save”: If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens.\n\nSee LoRA for detailed explanation of LoRA implementation.\nFor the training configurations:\n\n“gradient_accumulation_steps”: Integer. The number of steps over which to accumulate gradient for batch training. E.g. if 2, backprop is performed every two steps.\n“micro_batch_size”: Integer. Batch size per gpu / gradient_accumulation_steps\n“num_epochs”: Integer. Number of epochs. One epoch is when training has looped over every batch in the whole data set once.\n“optimizer”: The optimizer to use for the training.\n“learning_rate”: The learning rate.\n“lr_scheduler”: The learning rate scheduler to use for adjusting learning rate during training.\n“train_on_inputs”: Boolean. Whether to ignore or include the user’s prompt from the training labels.\n“group_by_length”: Boolean. Whether to group similarly sized data to minimize padding.\n“bf16”: Either “auto”, “true”, or “false”. Whether to use CUDA bf16 floating point format. If set to “auto”, will automatically apply bf16 should the gpu supports it.\n“fp16”: Optional. Specifies whether to use CUDA fp16. Automatically set to true if “bf16” is set to true. Otherwise false.\n“tf32”: Boolean. Whether to use CUDA tf32. Will override bf16.\n“gradient_checkpointing”: Boolean. Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing\n“gradient_checkpointing_kwargs”: Python Dict. Fed into the trainer.\n“logging_steps”: Integer. Log training information over every specified number of steps.\n“flash_attention”: Boolean. Whether to use the flash attention mechanism.\n“sdp_attention”: Boolean. Whether to use the Scaled Dot Product attention mechanism (the attention mechanism in the original implementation of transformers.)\n“warmup_steps”: Integer. The number of pre-training steps where a very low learning rate is used.\n“evals_per_epoch”: Integer. Number of evaluations to be performed within one training epoch.\n“saves_per_epoch”: Integer. Number of times the model is saved in one training epoch.\n“weight_decay”: Positive Float. Sets the “strength” of weight decay (i.e. setting the coefficient of L2 regularization)\n\nThe above is but a snippet aiming to get users familiarized with the types of streamlined configuration options axolotl provides. For a full list of configuration options, see here\nTrain the model\n\n!accelerate launch -m axolotl.cli.train /content/test_axolotl.yaml\n\nPredict with trained model\n\n!accelerate launch -m axolotl.cli.inference /content/test_axolotl.yaml \\\n --lora_model_dir=\"./outputs/lora-out\" --gradio" + }, + { + "objectID": "examples/colab-notebooks/colab-axolotl-example.html#deeper-dive", + "href": "examples/colab-notebooks/colab-axolotl-example.html#deeper-dive", + "title": "Setting up", + "section": "Deeper Dive", + "text": "Deeper Dive\nIt is also helpful to gain some familiarity over some of the core inner workings of axolotl" + }, + { + "objectID": "examples/colab-notebooks/colab-axolotl-example.html#configuration-normalization", + "href": "examples/colab-notebooks/colab-axolotl-example.html#configuration-normalization", + "title": "Setting up", + "section": "Configuration Normalization", + "text": "Configuration Normalization\nAxolotl uses a custom Dict class, called DictDefault\nto store configurations specified in the yaml configuration file (into a Python variable named cfg). The definition for this custom Dict can be found in the utils/dict.py\nDictDefault is amended such that calling a missing key from it will result in a None return type. This is important because if some configuration options aren’t specified by the user, the None type allows Axolotl to perform boolean operations to determine the default settings for missing configurations. For more examples on how this is done, check out utils/config/init.py" + }, + { + "objectID": "examples/colab-notebooks/colab-axolotl-example.html#loading-models-tokenizers-and-trainer", + "href": "examples/colab-notebooks/colab-axolotl-example.html#loading-models-tokenizers-and-trainer", + "title": "Setting up", + "section": "Loading Models, Tokenizers, and Trainer", + "text": "Loading Models, Tokenizers, and Trainer\nIf we inspect cli.train.py, we will find that most of the heavy lifting were done by the function train() which is itself imported from src/axolotl/train.py.\ntrain() takes care of loading the appropriate tokenizer and pre-trained model through load_model() and load_tokenizer() from src/axolotl/utils/models.py respectively.\nload_tokenizer() loads in the appropriate tokenizer given the desired model, as well as chat templates.\nModelLoader class follows after tokenizer has been selected. It will automatically discern the base model type, load in the desired model, as well as applying model-appropriate attention mechanism modifications (e.g. flash attention). Depending on which base model the user chooses in the configuration, ModelLoader will utilize the corresponding “attention hijacking” script. For example, if the user specified the base model to be NousResearch/Meta-Llama-3.1-8B, which is of llama type, and set flash_attn to True, ModelLoader will load in llama_attn_hijack_flash.py. For a list of supported attention hijacking, please refer to the directory /src/axolotl/monkeypatch/\nAnother important operation encompassed in train() is setting up the training that takes into account of user-specified traning configurations (e.g. num_epochs, optimizer) through the use of setup_trainer() from /src/axolotl/utils/trainer.py, which in turn relies on modules from /src/axolotl/core/trainer_builder.py.\ntrainer_builder.py provides a list of trainer object options bespoke for the task type (Causal or Reinforcement learning (‘dpo’, ‘ipo’, ‘kto’) )" + }, + { + "objectID": "examples/colab-notebooks/colab-axolotl-example.html#monkey-patch", + "href": "examples/colab-notebooks/colab-axolotl-example.html#monkey-patch", + "title": "Setting up", + "section": "Monkey patch", + "text": "Monkey patch\nThe Monkey patch directory is where model architecture/optimization patching scripts are stored (these are modifications that are not implemented in the official releases, hence the name monkey patch). It includes attention jacking, ReLoRA, and unsloth optimization." + }, + { + "objectID": "FAQS.html", + "href": "FAQS.html", + "title": "FAQs", + "section": "", + "text": "FAQs\n\nCan you train StableLM with this? Yes, but only with a single GPU atm. Multi GPU support is coming soon! Just waiting on this PR\nWill this work with Deepspeed? That’s still a WIP, but setting export ACCELERATE_USE_DEEPSPEED=true should work in some cases\nError invalid argument at line 359 in file /workspace/bitsandbytes/csrc/pythonInterface.c\n/arrow/cpp/src/arrow/filesystem/s3fs.cc:2598: arrow::fs::FinalizeS3 was not called even though S3 was initialized.\nThis could lead to a segmentation fault at exit. Try reinstalling bitsandbytes and transformers from source." + }, + { + "objectID": "src/axolotl/integrations/LICENSE.html", + "href": "src/axolotl/integrations/LICENSE.html", "title": "Axolotl", "section": "", - "text": "Acknowledgements\nPortions of this Cut Cross Entropy Software may utilize the following copyrighted\nmaterial, the use of which is hereby acknowledged.\n\nPyTorch\nFrom PyTorch:\n\nCopyright (c) 2016- Facebook, Inc (Adam Paszke)\nCopyright (c) 2014- Facebook, Inc (Soumith Chintala)\nCopyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)\nCopyright (c) 2012-2014 Deepmind Technologies (Koray Kavukcuoglu)\nCopyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)\nCopyright (c) 2011-2013 NYU (Clement Farabet)\nCopyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)\nCopyright (c) 2006 Idiap Research Institute (Samy Bengio)\nCopyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)\n\nFrom Caffe2:\n\nCopyright (c) 2016-present, Facebook Inc. All rights reserved.\n\nAll contributions by Facebook:\nCopyright (c) 2016 Facebook Inc.\n\nAll contributions by Google:\nCopyright (c) 2015 Google Inc.\nAll rights reserved.\n\nAll contributions by Yangqing Jia:\nCopyright (c) 2015 Yangqing Jia\nAll rights reserved.\n\nAll contributions by Kakao Brain:\nCopyright 2019-2020 Kakao Brain\n\nAll contributions by Cruise LLC:\nCopyright (c) 2022 Cruise LLC.\nAll rights reserved.\n\nAll contributions by Arm:\nCopyright (c) 2021, 2023-2024 Arm Limited and/or its affiliates\n\nAll contributions from Caffe:\nCopyright(c) 2013, 2014, 2015, the respective contributors\nAll rights reserved.\n\nAll other contributions:\nCopyright(c) 2015, 2016 the respective contributors\nAll rights reserved.\n\nCaffe2 uses a copyright model similar to Caffe: each contributor holds\ncopyright over their contributions to Caffe2. The project versioning records\nall such contribution and copyright details. If a contributor wants to further\nmark their specific copyright on a particular contribution, they should\nindicate their copyright solely in the commit message of the change when it is\ncommitted.\n\nAll rights reserved.\n\nRedistribution and use in source and binary forms, with or without\nmodification, are permitted provided that the following conditions are met:\n\n1. Redistributions of source code must retain the above copyright\nnotice, this list of conditions and the following disclaimer.\n\n2. Redistributions in binary form must reproduce the above copyright\nnotice, this list of conditions and the following disclaimer in the\ndocumentation and/or other materials provided with the distribution.\n\n3. Neither the names of Facebook, Deepmind Technologies, NYU, NEC Laboratories America\nand IDIAP Research Institute nor the names of its contributors may be\nused to endorse or promote products derived from this software without\nspecific prior written permission.\n\nTHIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\"\nAND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE\nIMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE\nARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE\nLIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR\nCONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF\nSUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS\nINTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN\nCONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)\nARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE\nPOSSIBILITY OF SUCH DAMAGE.\nTriton\n/*\n* Copyright 2018-2020 Philippe Tillet\n* Copyright 2020-2022 OpenAI\n*\n* Permission is hereby granted, free of charge, to any person obtaining\n* a copy of this software and associated documentation files\n* (the \"Software\"), to deal in the Software without restriction,\n* including without limitation the rights to use, copy, modify, merge,\n* publish, distribute, sublicense, and/or sell copies of the Software,\n* and to permit persons to whom the Software is furnished to do so,\n* subject to the following conditions:\n*\n* The above copyright notice and this permission notice shall be\n* included in all copies or substantial portions of the Software.\n*\n* THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND,\n* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF\n* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.\n* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY\n* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,\n* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE\n* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n*/\nTransformers\nCopyright 2018- The Hugging Face team. All rights reserved.\n\n Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n\nTERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n1. Definitions.\n\n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n\n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n\n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n\n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n\n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n\n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n\n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n\n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n\n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n\n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n\n2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n\n3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n\n4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n\n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n\n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n\n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n\n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n\n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n\n5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n\n6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n\n7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n\n8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n\n9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n\nEND OF TERMS AND CONDITIONS\n\nAPPENDIX: How to apply the Apache License to your work.\n\n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n\nCopyright [yyyy] [name of copyright owner]\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License." + "text": "AXOLOTL COMMUNITY LICENSE AGREEMENT\nThis Axolotl Community License Agreement (“Agreement”) is entered into by and between Axolotl AI Corp. (“Axolotl”) and\nany individual or entity (“Licensee”) who wishes to use the Software (as defined below) in accordance with the terms\nand conditions set forth in this Agreement.\n\nDefinitions\n1.1 “Licensee” refers to any individual or entity who has obtained a copy of the Software under this Agreement.\n1.2 “Plugin Integration” means independent integration software modules which may or may not be offered by Axolotl,\nwhich may be licensed separately by their respective authors and/or licensors.\n1.3 “Software” refers to the specific sub-directory of the Axolotl, Inc. software located at\nhttps://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations and its subdirectories which\npermits Plugin Integrations to integrate with the Axolotl service.\nGrant of License\n2.1 Axolotl hereby grants Licensee a worldwide, non-exclusive, royalty-free, license to use, copy, modify, merge,\npublish, distribute, sublicense, and/or otherwise exploit the Software, subject to the following conditions:\n- Licensee must comply with all the terms and conditions of this Agreement.\n- Licensee must include the original copyright notice and disclaimer of warranty in all copies or substantial\nportions of the Software.\n2.2 Licensee may use the Software for any lawful purpose, except as restricted in Section 3.\nRestrictions\n3.1 Licensee shall not use the Software for any activity that constitutes a commercial activity of offering for\nfree or for sale any services, platform, or equivalent to third parties for the purposes of allowing such\nthird parties to fine-tune artificial intelligence models.\n3.2 Licensee shall not:\n- Use the Software for any illegal or unauthorized purpose.\n- Reverse engineer, decompile, or disassemble the Software.\n- Remove or modify any copyright, trademark, or other proprietary notices contained in the Software.\n- Use the Software in a way that could damage, disable, overburden, or impair the functionality of the\nSoftware or interfere with any third-party use of the Software.\n3.3 Axolotl reserves the right to restrict certain Plugin Integrations for use with the Software. To the extent Licensee integrates a permitted, applicable Plugin Integration with the Software, Licensee shall comply with any additional terms and conditions imposed by the licensors of such Plugin Integration for use of such Plugin Integrations. Licensee shall contact Axolotl if it has questions about whether its use of the Software falls beyond the scope of this Agreement.\nIntellectual Property Rights\n4.1 Axolotl and its contributors retain all intellectual property rights in and to the Software. Licensee\nacknowledges that this Agreement does not transfer any ownership rights or intellectual property rights to\nLicensee.\nDisclaimer of Warranty\n5.1 THE SOFTWARE IS PROVIDED “AS IS,” WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED\nTO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. IN NO EVENT SHALL\nTHE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN AN ACTION OF\nCONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF, OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER\nDEALINGS IN THE SOFTWARE.\nTermination\n6.1 Axolotl may terminate this Agreement at any time if Licensee fails to comply with any of the terms and\nconditions set forth herein. Upon termination, Licensee shall cease all use of the Software and destroy any\ncopies in its possession.\nGoverning Law\n7.1 This Agreement shall be governed by and construed in accordance with the laws of the State of California,\nwithout regards to conflicts of laws provisions thereof.\nEntire Agreement\n8.1 This Agreement constitutes the entire agreement between Axolotl and Licensee with respect to the subject matter\nhereof and supersedes all prior or contemporaneous understandings or agreements between the parties concerning\nthe Software, whether written or oral. Axolotl may update the terms of this Agreement from time to time, and\nLicensee’s continued use of the Software after any such updates shall constitute acceptance of updated terms\non a go-forward basis. Axolotl will use commercially reasonable efforts to provide Licensee notice of any\nmaterial updates. By using the Software, Licensee acknowledges that it has read, understood, and agrees to be\nbound by the terms and conditions of this Agreement.\n\nThis Agreement was last updated on August 23, 2024." }, { - "objectID": "docs/api/datasets.html", - "href": "docs/api/datasets.html", - "title": "datasets", + "objectID": "docs/api/cli.utils.html", + "href": "docs/api/cli.utils.html", + "title": "cli.utils", "section": "", - "text": "datasets\nModule containing Dataset functionality\n\n\n\n\n\nName\nDescription\n\n\n\n\nConstantLengthDataset\nIterable dataset that returns constant length chunks of tokens from stream of text files.\n\n\nTokenizedPromptDataset\nDataset that returns tokenized prompts from a stream of text files.\n\n\n\n\n\ndatasets.ConstantLengthDataset(self, tokenizer, datasets, seq_length=2048)\nIterable dataset that returns constant length chunks of tokens from stream of text files.\nArgs:\ntokenizer (Tokenizer): The processor used for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nseq_length (int): Length of token sequences to return.\n\n\n\ndatasets.TokenizedPromptDataset(\n self,\n prompt_tokenizer,\n dataset,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nDataset that returns tokenized prompts from a stream of text files.\nArgs:\nprompt_tokenizer (PromptTokenizingStrategy): The prompt tokenizing method for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nprocess_count (int): Number of processes to use for tokenizing.\nkeep_in_memory (bool): Whether to keep the tokenized dataset in memory." + "text": "cli.utils\nUtility methods for axolotl CLI.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_options_from_config\nCreate Click options from the fields of a Pydantic model.\n\n\nadd_options_from_dataclass\nCreate Click options from the fields of a dataclass.\n\n\nbuild_command\nBuild command list from base command and options.\n\n\ndownload_file\nDownload a single file and return its processing status.\n\n\nfetch_from_github\nSync files from a specific directory in the GitHub repository.\n\n\nfilter_none_kwargs\nWraps function to remove None-valued kwargs.\n\n\nload_model_and_tokenizer\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\n\n\nstrip_optional_type\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\ncli.utils.add_options_from_config(config_class)\nCreate Click options from the fields of a Pydantic model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[BaseModel]\nPyDantic model with fields to parse from the CLI\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.add_options_from_dataclass(config_class)\nCreate Click options from the fields of a dataclass.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[Any]\nDataclass with fields to parse from the CLI.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.build_command(base_cmd, options)\nBuild command list from base command and options.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_cmd\nlist[str]\nCommand without options.\nrequired\n\n\noptions\ndict[str, Any]\nOptions to parse and append to base command.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nlist[str]\nList of strings giving shell command.\n\n\n\n\n\n\n\ncli.utils.download_file(file_info, raw_base_url, dest_path, dir_prefix)\nDownload a single file and return its processing status.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfile_info\ntuple\nTuple of (file_path, remote_sha).\nrequired\n\n\nraw_base_url\nstr\nBase URL for raw GitHub content.\nrequired\n\n\ndest_path\nPath\nLocal destination directory.\nrequired\n\n\ndir_prefix\nstr\nDirectory prefix to filter files.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[str, str]\nTuple of (file_path, status) where status is ‘new’, ‘updated’, or ‘unchanged’.\n\n\n\n\n\n\n\ncli.utils.fetch_from_github(dir_prefix, dest_dir=None, max_workers=5)\nSync files from a specific directory in the GitHub repository.\nOnly downloads files that don’t exist locally or have changed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndir_prefix\nstr\nDirectory prefix to filter files (e.g., ‘examples/’, ‘deepspeed_configs/’).\nrequired\n\n\ndest_dir\nstr | None\nLocal destination directory.\nNone\n\n\nmax_workers\nint\nMaximum number of concurrent downloads.\n5\n\n\n\n\n\n\n\ncli.utils.filter_none_kwargs(func)\nWraps function to remove None-valued kwargs.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfunc\nCallable\nFunction to wrap.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nWrapped function.\n\n\n\n\n\n\n\ncli.utils.load_model_and_tokenizer(cfg, inference=False)\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\nconfig.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ninference\nbool\nBoolean denoting inference mode.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer | PreTrainedTokenizerFast | Any, ProcessorMixin | None]\nTuple of (PreTrainedModel, PreTrainedTokenizer, ProcessorMixin).\n\n\n\n\n\n\n\ncli.utils.strip_optional_type(field_type)\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfield_type\ntype | str | None\nType of field for Axolotl CLI command.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nIf the input type is Union[T, None] or Optional[T], returns T. Otherwise returns the input type unchanged." }, { - "objectID": "docs/api/datasets.html#classes", - "href": "docs/api/datasets.html#classes", - "title": "datasets", + "objectID": "docs/api/cli.utils.html#functions", + "href": "docs/api/cli.utils.html#functions", + "title": "cli.utils", "section": "", - "text": "Name\nDescription\n\n\n\n\nConstantLengthDataset\nIterable dataset that returns constant length chunks of tokens from stream of text files.\n\n\nTokenizedPromptDataset\nDataset that returns tokenized prompts from a stream of text files.\n\n\n\n\n\ndatasets.ConstantLengthDataset(self, tokenizer, datasets, seq_length=2048)\nIterable dataset that returns constant length chunks of tokens from stream of text files.\nArgs:\ntokenizer (Tokenizer): The processor used for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nseq_length (int): Length of token sequences to return.\n\n\n\ndatasets.TokenizedPromptDataset(\n self,\n prompt_tokenizer,\n dataset,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nDataset that returns tokenized prompts from a stream of text files.\nArgs:\nprompt_tokenizer (PromptTokenizingStrategy): The prompt tokenizing method for processing the data.\ndataset (dataset.Dataset): Dataset with text files.\nprocess_count (int): Number of processes to use for tokenizing.\nkeep_in_memory (bool): Whether to keep the tokenized dataset in memory." + "text": "Name\nDescription\n\n\n\n\nadd_options_from_config\nCreate Click options from the fields of a Pydantic model.\n\n\nadd_options_from_dataclass\nCreate Click options from the fields of a dataclass.\n\n\nbuild_command\nBuild command list from base command and options.\n\n\ndownload_file\nDownload a single file and return its processing status.\n\n\nfetch_from_github\nSync files from a specific directory in the GitHub repository.\n\n\nfilter_none_kwargs\nWraps function to remove None-valued kwargs.\n\n\nload_model_and_tokenizer\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\n\n\nstrip_optional_type\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\ncli.utils.add_options_from_config(config_class)\nCreate Click options from the fields of a Pydantic model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[BaseModel]\nPyDantic model with fields to parse from the CLI\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.add_options_from_dataclass(config_class)\nCreate Click options from the fields of a dataclass.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig_class\nType[Any]\nDataclass with fields to parse from the CLI.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nFunction decorator for Axolotl CLI command.\n\n\n\n\n\n\n\ncli.utils.build_command(base_cmd, options)\nBuild command list from base command and options.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_cmd\nlist[str]\nCommand without options.\nrequired\n\n\noptions\ndict[str, Any]\nOptions to parse and append to base command.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nlist[str]\nList of strings giving shell command.\n\n\n\n\n\n\n\ncli.utils.download_file(file_info, raw_base_url, dest_path, dir_prefix)\nDownload a single file and return its processing status.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfile_info\ntuple\nTuple of (file_path, remote_sha).\nrequired\n\n\nraw_base_url\nstr\nBase URL for raw GitHub content.\nrequired\n\n\ndest_path\nPath\nLocal destination directory.\nrequired\n\n\ndir_prefix\nstr\nDirectory prefix to filter files.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[str, str]\nTuple of (file_path, status) where status is ‘new’, ‘updated’, or ‘unchanged’.\n\n\n\n\n\n\n\ncli.utils.fetch_from_github(dir_prefix, dest_dir=None, max_workers=5)\nSync files from a specific directory in the GitHub repository.\nOnly downloads files that don’t exist locally or have changed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndir_prefix\nstr\nDirectory prefix to filter files (e.g., ‘examples/’, ‘deepspeed_configs/’).\nrequired\n\n\ndest_dir\nstr | None\nLocal destination directory.\nNone\n\n\nmax_workers\nint\nMaximum number of concurrent downloads.\n5\n\n\n\n\n\n\n\ncli.utils.filter_none_kwargs(func)\nWraps function to remove None-valued kwargs.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfunc\nCallable\nFunction to wrap.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nCallable\nWrapped function.\n\n\n\n\n\n\n\ncli.utils.load_model_and_tokenizer(cfg, inference=False)\nHelper function for loading a model, tokenizer, and processor specified in the given axolotl\nconfig.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ninference\nbool\nBoolean denoting inference mode.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer | PreTrainedTokenizerFast | Any, ProcessorMixin | None]\nTuple of (PreTrainedModel, PreTrainedTokenizer, ProcessorMixin).\n\n\n\n\n\n\n\ncli.utils.strip_optional_type(field_type)\nExtracts the non-None type from an Optional / Union type.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nfield_type\ntype | str | None\nType of field for Axolotl CLI command.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nIf the input type is Union[T, None] or Optional[T], returns T. Otherwise returns the input type unchanged." }, { - "objectID": "docs/api/cli.train.html", - "href": "docs/api/cli.train.html", - "title": "cli.train", + "objectID": "docs/api/core.trainers.mixins.optimizer.html", + "href": "docs/api/core.trainers.mixins.optimizer.html", + "title": "core.trainers.mixins.optimizer", "section": "", - "text": "cli.train\nCLI to run training on a model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_train.\n\n\ndo_train\nTrains a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.train.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_train.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.train.do_train(cfg, cli_args)\nTrains a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.train.train. Also runs the plugin\nmanager’s post_train_unload once training completes.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nTraining-specific CLI arguments.\nrequired" + "text": "core.trainers.mixins.optimizer\nModule for Axolotl trainer optimizer mixin\n\n\n\n\n\nName\nDescription\n\n\n\n\nOptimizerMixin\nMixin class for shared handling of building custom optimizers\n\n\n\n\n\ncore.trainers.mixins.optimizer.OptimizerMixin()\nMixin class for shared handling of building custom optimizers" }, { - "objectID": "docs/api/cli.train.html#functions", - "href": "docs/api/cli.train.html#functions", - "title": "cli.train", + "objectID": "docs/api/core.trainers.mixins.optimizer.html#classes", + "href": "docs/api/core.trainers.mixins.optimizer.html#classes", + "title": "core.trainers.mixins.optimizer", "section": "", - "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_train.\n\n\ndo_train\nTrains a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.train.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_train.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.train.do_train(cfg, cli_args)\nTrains a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.train.train. Also runs the plugin\nmanager’s post_train_unload once training completes.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nTraining-specific CLI arguments.\nrequired" + "text": "Name\nDescription\n\n\n\n\nOptimizerMixin\nMixin class for shared handling of building custom optimizers\n\n\n\n\n\ncore.trainers.mixins.optimizer.OptimizerMixin()\nMixin class for shared handling of building custom optimizers" }, { - "objectID": "docs/api/utils.lora_embeddings.html", - "href": "docs/api/utils.lora_embeddings.html", - "title": "utils.lora_embeddings", + "objectID": "docs/api/prompt_strategies.orpo.chat_template.html", + "href": "docs/api/prompt_strategies.orpo.chat_template.html", + "title": "prompt_strategies.orpo.chat_template", "section": "", - "text": "utils.lora_embeddings\nhelpers for lora embeddings\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_linear_embedding_layers\nreturns the linear embedding layers needed for loras, dependent on the model arch\n\n\n\n\n\nutils.lora_embeddings.get_linear_embedding_layers(model_type)\nreturns the linear embedding layers needed for loras, dependent on the model arch" + "text": "prompt_strategies.orpo.chat_template\nchatml prompt tokenization strategy for ORPO\n\n\n\n\n\nName\nDescription\n\n\n\n\nMessage\nmessage/turn\n\n\nMessageList\nconversation\n\n\nORPODatasetParsingStrategy\nStrategy to parse chosen rejected dataset into messagelist\n\n\nORPOPrompter\nSingle Turn prompter for ORPO\n\n\nORPOTokenizingStrategy\nrejected_input_ids\n\n\n\n\n\nprompt_strategies.orpo.chat_template.Message()\nmessage/turn\n\n\n\nprompt_strategies.orpo.chat_template.MessageList()\nconversation\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy()\nStrategy to parse chosen rejected dataset into messagelist\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_chosen_conversation_thread\nDataset structure mappings\n\n\nget_prompt\nMap the data to extract everything up to the last turn\n\n\nget_rejected_conversation_thread\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_chosen_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_prompt(\n prompt,\n)\nMap the data to extract everything up to the last turn\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_rejected_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPOPrompter(\n self,\n chat_template,\n tokenizer,\n)\nSingle Turn prompter for ORPO\n\n\n\nprompt_strategies.orpo.chat_template.ORPOTokenizingStrategy(\n self,\n *args,\n dataset_parser=None,\n **kwargs,\n)\nrejected_input_ids\ninput_ids\nrejected_attention_mask\nattention_mask\nrejected_labels\nlabels\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nload\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.orpo.chat_template.load(tokenizer, cfg, ds_cfg=None, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected" }, { - "objectID": "docs/api/utils.lora_embeddings.html#functions", - "href": "docs/api/utils.lora_embeddings.html#functions", - "title": "utils.lora_embeddings", + "objectID": "docs/api/prompt_strategies.orpo.chat_template.html#classes", + "href": "docs/api/prompt_strategies.orpo.chat_template.html#classes", + "title": "prompt_strategies.orpo.chat_template", "section": "", - "text": "Name\nDescription\n\n\n\n\nget_linear_embedding_layers\nreturns the linear embedding layers needed for loras, dependent on the model arch\n\n\n\n\n\nutils.lora_embeddings.get_linear_embedding_layers(model_type)\nreturns the linear embedding layers needed for loras, dependent on the model arch" + "text": "Name\nDescription\n\n\n\n\nMessage\nmessage/turn\n\n\nMessageList\nconversation\n\n\nORPODatasetParsingStrategy\nStrategy to parse chosen rejected dataset into messagelist\n\n\nORPOPrompter\nSingle Turn prompter for ORPO\n\n\nORPOTokenizingStrategy\nrejected_input_ids\n\n\n\n\n\nprompt_strategies.orpo.chat_template.Message()\nmessage/turn\n\n\n\nprompt_strategies.orpo.chat_template.MessageList()\nconversation\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy()\nStrategy to parse chosen rejected dataset into messagelist\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_chosen_conversation_thread\nDataset structure mappings\n\n\nget_prompt\nMap the data to extract everything up to the last turn\n\n\nget_rejected_conversation_thread\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_chosen_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_prompt(\n prompt,\n)\nMap the data to extract everything up to the last turn\n\n\n\nprompt_strategies.orpo.chat_template.ORPODatasetParsingStrategy.get_rejected_conversation_thread(\n prompt,\n)\nDataset structure mappings\n\n\n\n\n\nprompt_strategies.orpo.chat_template.ORPOPrompter(\n self,\n chat_template,\n tokenizer,\n)\nSingle Turn prompter for ORPO\n\n\n\nprompt_strategies.orpo.chat_template.ORPOTokenizingStrategy(\n self,\n *args,\n dataset_parser=None,\n **kwargs,\n)\nrejected_input_ids\ninput_ids\nrejected_attention_mask\nattention_mask\nrejected_labels\nlabels" }, { - "objectID": "docs/api/utils.models.html", - "href": "docs/api/utils.models.html", - "title": "utils.models", + "objectID": "docs/api/prompt_strategies.orpo.chat_template.html#functions", + "href": "docs/api/prompt_strategies.orpo.chat_template.html#functions", + "title": "prompt_strategies.orpo.chat_template", "section": "", - "text": "utils.models\nModule for models and model loading\n\n\n\n\n\nName\nDescription\n\n\n\n\nModelLoader\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nutils.models.ModelLoader(\n self,\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nName\nDescription\n\n\n\n\nhas_flash_attn\nCheck if flash attention is installed\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\npatch_llama_derived_model\nModify all llama derived models in one block\n\n\npatch_loss_llama\nPatch loss functions and other optimizations\n\n\nset_attention_config\nsample packing uses custom FA2 patch\n\n\nset_auto_model_loader\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n\n\n\n\n\nutils.models.ModelLoader.patch_llama_derived_model()\nModify all llama derived models in one block\n\n\n\nutils.models.ModelLoader.patch_loss_llama()\nPatch loss functions and other optimizations\n\n\n\nutils.models.ModelLoader.set_attention_config()\nsample packing uses custom FA2 patch\n\n\n\nutils.models.ModelLoader.set_auto_model_loader()\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n(set at __init__). When using a multimodal model, self.auto_model_loader\nshould be set according to the type of the model.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_module_class_from_name\nGets a class from a module by its name.\n\n\nload_model\nLoad a model for a given configuration and tokenizer.\n\n\nload_tokenizer\nLoad and configure the tokenizer based on the provided config.\n\n\nmodify_tokenizer_files\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\n\n\nsetup_quantized_meta_for_peft\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\nsetup_quantized_peft_meta_for_training\nReplaces dummy quant_state.to method with the original function to allow training to continue\n\n\n\n\n\nutils.models.get_module_class_from_name(module, name)\nGets a class from a module by its name.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodule\ntorch.nn.Module\nThe module to get the class from.\nrequired\n\n\nname\nstr\nThe name of the class.\nrequired\n\n\n\n\n\n\n\nutils.models.load_model(\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nLoad a model for a given configuration and tokenizer.\n\n\n\nutils.models.load_tokenizer(cfg)\nLoad and configure the tokenizer based on the provided config.\n\n\n\nutils.models.modify_tokenizer_files(tokenizer_path, token_mappings, output_dir)\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\nThis only works with reserved tokens that were added to the tokenizer, not tokens already part of the vocab.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer_path\nstr\nPath or name of the original tokenizer\nrequired\n\n\ntoken_mappings\nDict[int, str]\nDict mapping {token_id (int): new_token_string}\nrequired\n\n\noutput_dir\nstr\nDirectory to save the modified tokenizer\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to the modified tokenizer directory\n\n\n\nRef: https://github.com/huggingface/transformers/issues/27974#issuecomment-1854188941\n\n\n\n\nutils.models.setup_quantized_meta_for_peft(model)\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\n\nutils.models.setup_quantized_peft_meta_for_training(model)\nReplaces dummy quant_state.to method with the original function to allow training to continue" + "text": "Name\nDescription\n\n\n\n\nload\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.orpo.chat_template.load(tokenizer, cfg, ds_cfg=None, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected" }, { - "objectID": "docs/api/utils.models.html#classes", - "href": "docs/api/utils.models.html#classes", - "title": "utils.models", + "objectID": "docs/api/monkeypatch.llama_attn_hijack_flash.html", + "href": "docs/api/monkeypatch.llama_attn_hijack_flash.html", + "title": "monkeypatch.llama_attn_hijack_flash", "section": "", - "text": "Name\nDescription\n\n\n\n\nModelLoader\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nutils.models.ModelLoader(\n self,\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nModelLoader: managing all the config and monkey patches while loading model\n\n\n\n\n\nName\nDescription\n\n\n\n\nhas_flash_attn\nCheck if flash attention is installed\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\npatch_llama_derived_model\nModify all llama derived models in one block\n\n\npatch_loss_llama\nPatch loss functions and other optimizations\n\n\nset_attention_config\nsample packing uses custom FA2 patch\n\n\nset_auto_model_loader\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n\n\n\n\n\nutils.models.ModelLoader.patch_llama_derived_model()\nModify all llama derived models in one block\n\n\n\nutils.models.ModelLoader.patch_loss_llama()\nPatch loss functions and other optimizations\n\n\n\nutils.models.ModelLoader.set_attention_config()\nsample packing uses custom FA2 patch\n\n\n\nutils.models.ModelLoader.set_auto_model_loader()\nSet self.auto_model_loader. Defaults to transformers.AutoModelForCausalLM\n(set at __init__). When using a multimodal model, self.auto_model_loader\nshould be set according to the type of the model." + "text": "monkeypatch.llama_attn_hijack_flash\nFlash attention monkey patch for llama model\n\n\n\n\n\nName\nDescription\n\n\n\n\nFusedAttention\nFused QKV Attention layer for incrementally improved training efficiency\n\n\nLlamaDecoderLayer\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.FusedAttention(self, config, q, k, v, o)\nFused QKV Attention layer for incrementally improved training efficiency\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer()\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nflashattn_forward\nInput shape: Batch x Time x Channel\n\n\nflashattn_forward_with_s2attn\nInput shape: Batch x Time x Channel\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nattention_mask: [bsz, q_len]\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward_with_s2attn(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nFrom: https://github.com/dvlab-research/LongLoRA/blob/main/llama_attn_replace.py\nattention_mask: [bsz, q_len]\ncu_seqlens will be ignored if provided\nmax_seqlen will be ignored if provided\n\n\n\nmonkeypatch.llama_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" }, { - "objectID": "docs/api/utils.models.html#functions", - "href": "docs/api/utils.models.html#functions", - "title": "utils.models", + "objectID": "docs/api/monkeypatch.llama_attn_hijack_flash.html#classes", + "href": "docs/api/monkeypatch.llama_attn_hijack_flash.html#classes", + "title": "monkeypatch.llama_attn_hijack_flash", "section": "", - "text": "Name\nDescription\n\n\n\n\nget_module_class_from_name\nGets a class from a module by its name.\n\n\nload_model\nLoad a model for a given configuration and tokenizer.\n\n\nload_tokenizer\nLoad and configure the tokenizer based on the provided config.\n\n\nmodify_tokenizer_files\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\n\n\nsetup_quantized_meta_for_peft\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\nsetup_quantized_peft_meta_for_training\nReplaces dummy quant_state.to method with the original function to allow training to continue\n\n\n\n\n\nutils.models.get_module_class_from_name(module, name)\nGets a class from a module by its name.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodule\ntorch.nn.Module\nThe module to get the class from.\nrequired\n\n\nname\nstr\nThe name of the class.\nrequired\n\n\n\n\n\n\n\nutils.models.load_model(\n cfg,\n tokenizer,\n *,\n processor=None,\n inference=False,\n reference_model=False,\n **kwargs,\n)\nLoad a model for a given configuration and tokenizer.\n\n\n\nutils.models.load_tokenizer(cfg)\nLoad and configure the tokenizer based on the provided config.\n\n\n\nutils.models.modify_tokenizer_files(tokenizer_path, token_mappings, output_dir)\nModify tokenizer files to replace added_tokens strings, save to output directory, and return the path to the modified tokenizer.\nThis only works with reserved tokens that were added to the tokenizer, not tokens already part of the vocab.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer_path\nstr\nPath or name of the original tokenizer\nrequired\n\n\ntoken_mappings\nDict[int, str]\nDict mapping {token_id (int): new_token_string}\nrequired\n\n\noutput_dir\nstr\nDirectory to save the modified tokenizer\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to the modified tokenizer directory\n\n\n\nRef: https://github.com/huggingface/transformers/issues/27974#issuecomment-1854188941\n\n\n\n\nutils.models.setup_quantized_meta_for_peft(model)\nReplaces quant_state.to with a dummy function to prevent PEFT from moving quant_state to meta device\n\n\n\nutils.models.setup_quantized_peft_meta_for_training(model)\nReplaces dummy quant_state.to method with the original function to allow training to continue" + "text": "Name\nDescription\n\n\n\n\nFusedAttention\nFused QKV Attention layer for incrementally improved training efficiency\n\n\nLlamaDecoderLayer\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.FusedAttention(self, config, q, k, v, o)\nFused QKV Attention layer for incrementally improved training efficiency\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer()\npatched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.LlamaDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone" }, { - "objectID": "docs/api/prompt_strategies.user_defined.html", - "href": "docs/api/prompt_strategies.user_defined.html", - "title": "prompt_strategies.user_defined", + "objectID": "docs/api/monkeypatch.llama_attn_hijack_flash.html#functions", + "href": "docs/api/monkeypatch.llama_attn_hijack_flash.html#functions", + "title": "monkeypatch.llama_attn_hijack_flash", "section": "", - "text": "prompt_strategies.user_defined\nUser Defined prompts with configuration from the YML config\n\n\n\n\n\nName\nDescription\n\n\n\n\nUserDefinedDatasetConfig\ndataclass configuration representing a userdefined dataset type\n\n\nUserDefinedPromptTokenizationStrategy\nPrompt Tokenization Strategy for user defined prompts\n\n\n\n\n\nprompt_strategies.user_defined.UserDefinedDatasetConfig(\n self,\n system_prompt='',\n field_system='system',\n field_instruction='instruction',\n field_input='input',\n field_output='output',\n format='{instruction} {input} ',\n no_input_format='{instruction} ',\n system_format='{system}',\n)\ndataclass configuration representing a userdefined dataset type\n\n\n\nprompt_strategies.user_defined.UserDefinedPromptTokenizationStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nPrompt Tokenization Strategy for user defined prompts" + "text": "Name\nDescription\n\n\n\n\nflashattn_forward\nInput shape: Batch x Time x Channel\n\n\nflashattn_forward_with_s2attn\nInput shape: Batch x Time x Channel\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nattention_mask: [bsz, q_len]\n\n\n\nmonkeypatch.llama_attn_hijack_flash.flashattn_forward_with_s2attn(\n self,\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n padding_mask=None,\n cu_seqlens=None,\n max_seqlen=None,\n)\nInput shape: Batch x Time x Channel\nFrom: https://github.com/dvlab-research/LongLoRA/blob/main/llama_attn_replace.py\nattention_mask: [bsz, q_len]\ncu_seqlens will be ignored if provided\nmax_seqlen will be ignored if provided\n\n\n\nmonkeypatch.llama_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" }, { - "objectID": "docs/api/prompt_strategies.user_defined.html#classes", - "href": "docs/api/prompt_strategies.user_defined.html#classes", - "title": "prompt_strategies.user_defined", + "objectID": "docs/api/prompt_strategies.completion.html", + "href": "docs/api/prompt_strategies.completion.html", + "title": "prompt_strategies.completion", "section": "", - "text": "Name\nDescription\n\n\n\n\nUserDefinedDatasetConfig\ndataclass configuration representing a userdefined dataset type\n\n\nUserDefinedPromptTokenizationStrategy\nPrompt Tokenization Strategy for user defined prompts\n\n\n\n\n\nprompt_strategies.user_defined.UserDefinedDatasetConfig(\n self,\n system_prompt='',\n field_system='system',\n field_instruction='instruction',\n field_input='input',\n field_output='output',\n format='{instruction} {input} ',\n no_input_format='{instruction} ',\n system_format='{system}',\n)\ndataclass configuration representing a userdefined dataset type\n\n\n\nprompt_strategies.user_defined.UserDefinedPromptTokenizationStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nPrompt Tokenization Strategy for user defined prompts" + "text": "prompt_strategies.completion\nBasic completion text\n\n\n\n\n\nName\nDescription\n\n\n\n\nCompletionPromptTokenizingStrategy\nTokenizing strategy for Completion prompts.\n\n\nCompletionPrompter\nPrompter for completion\n\n\n\n\n\nprompt_strategies.completion.CompletionPromptTokenizingStrategy(\n self,\n *args,\n max_length=None,\n **kwargs,\n)\nTokenizing strategy for Completion prompts.\n\n\n\nprompt_strategies.completion.CompletionPrompter()\nPrompter for completion" }, { - "objectID": "docs/api/core.trainers.grpo.sampler.html", - "href": "docs/api/core.trainers.grpo.sampler.html", - "title": "core.trainers.grpo.sampler", + "objectID": "docs/api/prompt_strategies.completion.html#classes", + "href": "docs/api/prompt_strategies.completion.html#classes", + "title": "prompt_strategies.completion", "section": "", - "text": "core.trainers.grpo.sampler\nRepeat random sampler (similar to the one implemented in\nhttps://github.com/huggingface/trl/blob/main/trl/trainer/grpo_trainer.py) that adds\nsequence parallelism functionality; i.e., duplicating data across ranks in the same\nsequence parallel group.\n\n\n\n\n\nName\nDescription\n\n\n\n\nSequenceParallelRepeatRandomSampler\nSampler for GRPO training with sequence parallelism.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler(\n self,\n dataset,\n mini_repeat_count,\n world_size,\n rank,\n batch_size=1,\n repeat_count=1,\n sequence_parallel_degree=1,\n shuffle=True,\n seed=0,\n drop_last=False,\n)\nSampler for GRPO training with sequence parallelism.\nThis sampler ensures:\n- Ranks in the same sequence parallel (SP) group receive identical data.\n- Each index is repeated multiple times for sampling different completions.\n- Entire batches are repeated for reuse in multiple updates.\n- Data is properly distributed across SP groups.\nIn the table below, the values represent dataset indices. Each SP group has\nsequence_parallel_degree = 2 GPUs working together on the same data. There are 2\nSP groups (SP0 and SP1), with world_size = 4 total GPUs.\n Sequence Parallel Groups\n | SP0 | SP1 |\n | GPU 0 | GPU 1 | GPU 2 | GPU 3 |\n global_step step <---> mini_repeat_count=3\n <----------> batch_size=2 per SP group\ngrad_accum=2 ▲ ▲ 0 0 [0 0 0 1 1 1] [2 2 2 3 3 3] <- SP groups get different data\n▼ | 0 1 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Same data for each SP group GPU\n|\n| 1 2 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Repeat same indices for iterations\nnum_iterations=2 ▼ 1 3 [0 0 0 1 1 1] [2 2 2 3 3 3] <- When using gradient accumulation\n 2 4 [4 4 4 5 5 5] [6 6 6 7 7 7] <- New batch of data indices\n 2 5 [4 4 4 5 5 5] [6 6 6 7 7 7]\n ...\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nSized\nDataset to sample from.\nrequired\n\n\nmini_repeat_count\nint\nHow many times to repeat each sample immediately.\nrequired\n\n\nworld_size\nint\nTotal number of processes.\nrequired\n\n\nrank\nint\nRank of current process.\nrequired\n\n\nbatch_size\nint\nNumber of samples per batch.\n1\n\n\nrepeat_count\nint\nHow many times to repeat the full sampling process.\n1\n\n\nsequence_parallel_degree\nint\nNumber of ranks in a sequence parallel group.\n1\n\n\nshuffle\nbool\nWhether to shuffle the dataset.\nTrue\n\n\nseed\nint\nRandom seed for shuffling.\n0\n\n\ndrop_last\nbool\nWhether to drop the last incomplete batch.\nFalse\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nset_epoch\nSets the epoch for this sampler.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler.set_epoch(epoch)\nSets the epoch for this sampler.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nepoch\nint\nEpoch number to use for shuffling.\nrequired" + "text": "Name\nDescription\n\n\n\n\nCompletionPromptTokenizingStrategy\nTokenizing strategy for Completion prompts.\n\n\nCompletionPrompter\nPrompter for completion\n\n\n\n\n\nprompt_strategies.completion.CompletionPromptTokenizingStrategy(\n self,\n *args,\n max_length=None,\n **kwargs,\n)\nTokenizing strategy for Completion prompts.\n\n\n\nprompt_strategies.completion.CompletionPrompter()\nPrompter for completion" }, { - "objectID": "docs/api/core.trainers.grpo.sampler.html#classes", - "href": "docs/api/core.trainers.grpo.sampler.html#classes", - "title": "core.trainers.grpo.sampler", + "objectID": "docs/api/evaluate.html", + "href": "docs/api/evaluate.html", + "title": "evaluate", "section": "", - "text": "Name\nDescription\n\n\n\n\nSequenceParallelRepeatRandomSampler\nSampler for GRPO training with sequence parallelism.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler(\n self,\n dataset,\n mini_repeat_count,\n world_size,\n rank,\n batch_size=1,\n repeat_count=1,\n sequence_parallel_degree=1,\n shuffle=True,\n seed=0,\n drop_last=False,\n)\nSampler for GRPO training with sequence parallelism.\nThis sampler ensures:\n- Ranks in the same sequence parallel (SP) group receive identical data.\n- Each index is repeated multiple times for sampling different completions.\n- Entire batches are repeated for reuse in multiple updates.\n- Data is properly distributed across SP groups.\nIn the table below, the values represent dataset indices. Each SP group has\nsequence_parallel_degree = 2 GPUs working together on the same data. There are 2\nSP groups (SP0 and SP1), with world_size = 4 total GPUs.\n Sequence Parallel Groups\n | SP0 | SP1 |\n | GPU 0 | GPU 1 | GPU 2 | GPU 3 |\n global_step step <---> mini_repeat_count=3\n <----------> batch_size=2 per SP group\ngrad_accum=2 ▲ ▲ 0 0 [0 0 0 1 1 1] [2 2 2 3 3 3] <- SP groups get different data\n▼ | 0 1 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Same data for each SP group GPU\n|\n| 1 2 [0 0 0 1 1 1] [2 2 2 3 3 3] <- Repeat same indices for iterations\nnum_iterations=2 ▼ 1 3 [0 0 0 1 1 1] [2 2 2 3 3 3] <- When using gradient accumulation\n 2 4 [4 4 4 5 5 5] [6 6 6 7 7 7] <- New batch of data indices\n 2 5 [4 4 4 5 5 5] [6 6 6 7 7 7]\n ...\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nSized\nDataset to sample from.\nrequired\n\n\nmini_repeat_count\nint\nHow many times to repeat each sample immediately.\nrequired\n\n\nworld_size\nint\nTotal number of processes.\nrequired\n\n\nrank\nint\nRank of current process.\nrequired\n\n\nbatch_size\nint\nNumber of samples per batch.\n1\n\n\nrepeat_count\nint\nHow many times to repeat the full sampling process.\n1\n\n\nsequence_parallel_degree\nint\nNumber of ranks in a sequence parallel group.\n1\n\n\nshuffle\nbool\nWhether to shuffle the dataset.\nTrue\n\n\nseed\nint\nRandom seed for shuffling.\n0\n\n\ndrop_last\nbool\nWhether to drop the last incomplete batch.\nFalse\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nset_epoch\nSets the epoch for this sampler.\n\n\n\n\n\ncore.trainers.grpo.sampler.SequenceParallelRepeatRandomSampler.set_epoch(epoch)\nSets the epoch for this sampler.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nepoch\nint\nEpoch number to use for shuffling.\nrequired" + "text": "evaluate\nModule for evaluating models.\n\n\n\n\n\nName\nDescription\n\n\n\n\nevaluate\nEvaluate a model on training and validation datasets.\n\n\nevaluate_dataset\nHelper function to evaluate a single dataset.\n\n\n\n\n\nevaluate.evaluate(cfg, dataset_meta)\nEvaluate a model on training and validation datasets.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nDataset metadata containing training and evaluation datasets.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDict[str, float]\nDictionary mapping metric names to their values.\n\n\n\n\n\n\n\nevaluate.evaluate_dataset(trainer, dataset, dataset_type, flash_optimum=False)\nHelper function to evaluate a single dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrainer\nTrainer\nThe trainer instance.\nrequired\n\n\ndataset\nDataset\nDataset to evaluate.\nrequired\n\n\ndataset_type\nstr\nType of dataset (‘train’ or ‘eval’).\nrequired\n\n\nflash_optimum\nbool\nWhether to use flash optimum.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nOptional[Dict[str, float]]\nDictionary of metrics or None if dataset is None." }, { - "objectID": "docs/api/common.const.html", - "href": "docs/api/common.const.html", - "title": "common.const", + "objectID": "docs/api/evaluate.html#functions", + "href": "docs/api/evaluate.html#functions", + "title": "evaluate", "section": "", - "text": "common.const\ncommon.const\nVarious shared constants" + "text": "Name\nDescription\n\n\n\n\nevaluate\nEvaluate a model on training and validation datasets.\n\n\nevaluate_dataset\nHelper function to evaluate a single dataset.\n\n\n\n\n\nevaluate.evaluate(cfg, dataset_meta)\nEvaluate a model on training and validation datasets.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nDataset metadata containing training and evaluation datasets.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDict[str, float]\nDictionary mapping metric names to their values.\n\n\n\n\n\n\n\nevaluate.evaluate_dataset(trainer, dataset, dataset_type, flash_optimum=False)\nHelper function to evaluate a single dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrainer\nTrainer\nThe trainer instance.\nrequired\n\n\ndataset\nDataset\nDataset to evaluate.\nrequired\n\n\ndataset_type\nstr\nType of dataset (‘train’ or ‘eval’).\nrequired\n\n\nflash_optimum\nbool\nWhether to use flash optimum.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nOptional[Dict[str, float]]\nDictionary of metrics or None if dataset is None." }, { - "objectID": "docs/api/prompt_strategies.bradley_terry.llama3.html", - "href": "docs/api/prompt_strategies.bradley_terry.llama3.html", - "title": "prompt_strategies.bradley_terry.llama3", + "objectID": "docs/api/utils.ctx_managers.sequence_parallel.html", + "href": "docs/api/utils.ctx_managers.sequence_parallel.html", + "title": "utils.ctx_managers.sequence_parallel", "section": "", - "text": "prompt_strategies.bradley_terry.llama3\nchatml transforms for datasets with system, input, chosen, rejected to match llama3 chat template\n\n\n\n\n\nName\nDescription\n\n\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.bradley_terry.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs" + "text": "utils.ctx_managers.sequence_parallel\nModule for Axolotl trainer sequence parallelism manager and utilities\n\n\n\n\n\nName\nDescription\n\n\n\n\nAllGatherWithGrad\nCustom autograd function for all-gather to preserve gradients.\n\n\nSequenceParallelContextManager\nContext manager for sequence parallelism operations.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad()\nCustom autograd function for all-gather to preserve gradients.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass for all-gather operation.\n\n\nforward\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.backward(\n ctx,\n grad_output,\n)\nBackward pass for all-gather operation.\nExtracts the gradient slice corresponding to this rank’s original input\nfrom the full gradient tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient from subsequent layers with respect to the concatenated output tensor.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None]\nTuple containing the gradient slice for this rank’s input tensor and None for the process group parameter which doesn’t require gradients.\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.forward(\n ctx,\n input_tensor,\n group,\n)\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ninput_tensor\ntorch.Tensor\nTensor from model output with sequence dimension.\nrequired\n\n\ngroup\ndist.ProcessGroup\ntorch.distributed process group.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTensor from gathering the input_tensor from across the process group and concatenating along the sequence dimension.\n\n\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager(\n self,\n models,\n sequence_parallel_degree,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nContext manager for sequence parallelism operations.\nThis class provides a context that will automatically apply sequence parallelism\nduring model forward passes using a pre-forward hook, and gather outputs from\nacross the sequence parallelism group using a post-forward hook.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodels\nlist[nn.Module]\nList of models to apply sequence parallelism to pre- and post- forward hooks.\nrequired\n\n\nsequence_parallel_degree\nint\nNumber of processes to split sequences over.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused.\nrequired\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ngather_outputs\nGather sharded outputs from all ranks and reconstruct the full tensor.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager.gather_outputs(\n output,\n)\nGather sharded outputs from all ranks and reconstruct the full tensor.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\napply_sequence_parallelism\nApply sequence parallelism slicing to a batch.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.apply_sequence_parallelism(\n batch,\n local_rank,\n local_world_size,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nApply sequence parallelism slicing to a batch.\nSpecial handling is implemented for integer logits_to_keep, which indicates\nto only keep the last N tokens in the sequence during generation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbatch\ndict[str, torch.Tensor]\nBatch dictionary (e.g., input_ids, attention_mask, etc.).\nrequired\n\n\nlocal_rank\nint\nLocal rank in the sequence parallel group.\nrequired\n\n\nlocal_world_size\nint\nWorld size of the sequence parallel group.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused, but related to above TODO.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[dict[str, torch.Tensor], int, int]\ntuple of: - Batch dictionary with sliced tensors. - The original sequence length before padding. - The number of padding tokens added." }, { - "objectID": "docs/api/prompt_strategies.bradley_terry.llama3.html#functions", - "href": "docs/api/prompt_strategies.bradley_terry.llama3.html#functions", - "title": "prompt_strategies.bradley_terry.llama3", + "objectID": "docs/api/utils.ctx_managers.sequence_parallel.html#classes", + "href": "docs/api/utils.ctx_managers.sequence_parallel.html#classes", + "title": "utils.ctx_managers.sequence_parallel", "section": "", - "text": "Name\nDescription\n\n\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\n\n\n\nprompt_strategies.bradley_terry.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs" + "text": "Name\nDescription\n\n\n\n\nAllGatherWithGrad\nCustom autograd function for all-gather to preserve gradients.\n\n\nSequenceParallelContextManager\nContext manager for sequence parallelism operations.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad()\nCustom autograd function for all-gather to preserve gradients.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass for all-gather operation.\n\n\nforward\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.backward(\n ctx,\n grad_output,\n)\nBackward pass for all-gather operation.\nExtracts the gradient slice corresponding to this rank’s original input\nfrom the full gradient tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient from subsequent layers with respect to the concatenated output tensor.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None]\nTuple containing the gradient slice for this rank’s input tensor and None for the process group parameter which doesn’t require gradients.\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.AllGatherWithGrad.forward(\n ctx,\n input_tensor,\n group,\n)\nForward pass of all-gather of data with sequence dimension.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\ntorch.autograd function context.\nrequired\n\n\ninput_tensor\ntorch.Tensor\nTensor from model output with sequence dimension.\nrequired\n\n\ngroup\ndist.ProcessGroup\ntorch.distributed process group.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTensor from gathering the input_tensor from across the process group and concatenating along the sequence dimension.\n\n\n\n\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager(\n self,\n models,\n sequence_parallel_degree,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nContext manager for sequence parallelism operations.\nThis class provides a context that will automatically apply sequence parallelism\nduring model forward passes using a pre-forward hook, and gather outputs from\nacross the sequence parallelism group using a post-forward hook.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodels\nlist[nn.Module]\nList of models to apply sequence parallelism to pre- and post- forward hooks.\nrequired\n\n\nsequence_parallel_degree\nint\nNumber of processes to split sequences over.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused.\nrequired\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ngather_outputs\nGather sharded outputs from all ranks and reconstruct the full tensor.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.SequenceParallelContextManager.gather_outputs(\n output,\n)\nGather sharded outputs from all ranks and reconstruct the full tensor." }, { - "objectID": "docs/api/utils.distributed.html", - "href": "docs/api/utils.distributed.html", - "title": "utils.distributed", + "objectID": "docs/api/utils.ctx_managers.sequence_parallel.html#functions", + "href": "docs/api/utils.ctx_managers.sequence_parallel.html#functions", + "title": "utils.ctx_managers.sequence_parallel", "section": "", - "text": "utils.distributed\nutility helpers for distributed checks\n\n\n\n\n\nName\nDescription\n\n\n\n\nbarrier\nActs as a barrier to wait for all processes. This ensures that all processes\n\n\ncleanup_distributed\nDestroy process group if torch distributed is initialized. Called in training early\n\n\ncompute_and_broadcast\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\n\n\ngather_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\ngather_scalar_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\nis_distributed\nCheck if distributed training is initialized.\n\n\nis_main_process\nCheck if the current process is the main process. If not in distributed mode,\n\n\nreduce_and_broadcast\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\n\n\nzero_first\nruns the wrapped context so that rank 0 runs first before other ranks\n\n\n\n\n\nutils.distributed.barrier()\nActs as a barrier to wait for all processes. This ensures that all processes\nreach the barrier before proceeding further.\n\n\n\nutils.distributed.cleanup_distributed()\nDestroy process group if torch distributed is initialized. Called in training early\ntermination or when training successfully completes.\n\n\n\nutils.distributed.compute_and_broadcast(fn)\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\nThe value is then broadcasted to all other ranks.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that computes the value. Default is 0.\nReturns:\n- The computed value (int or float).\n\n\n\nutils.distributed.gather_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.gather_scalar_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.is_distributed()\nCheck if distributed training is initialized.\n\n\n\nutils.distributed.is_main_process(use_environ=False)\nCheck if the current process is the main process. If not in distributed mode,\nalways return True.\nArgs:\n- use_environ (bool, optional): Use environment variable to determine main process.\nReturns:\n- bool: True if the current process is the main process, False otherwise.\n\n\n\nutils.distributed.reduce_and_broadcast(fn1, fn2)\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\nand then broadcast the reduced result to all ranks.\nArgs:\n- fn1 (callable): A function that computes the value on each rank.\n- fn2 (callable): A reduction function that takes a list of values and returns a single value.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- The reduced and broadcasted value.\n\n\n\nutils.distributed.zero_first(is_main)\nruns the wrapped context so that rank 0 runs first before other ranks" + "text": "Name\nDescription\n\n\n\n\napply_sequence_parallelism\nApply sequence parallelism slicing to a batch.\n\n\n\n\n\nutils.ctx_managers.sequence_parallel.apply_sequence_parallelism(\n batch,\n local_rank,\n local_world_size,\n gradient_accumulation_steps,\n ring_attn_func,\n)\nApply sequence parallelism slicing to a batch.\nSpecial handling is implemented for integer logits_to_keep, which indicates\nto only keep the last N tokens in the sequence during generation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbatch\ndict[str, torch.Tensor]\nBatch dictionary (e.g., input_ids, attention_mask, etc.).\nrequired\n\n\nlocal_rank\nint\nLocal rank in the sequence parallel group.\nrequired\n\n\nlocal_world_size\nint\nWorld size of the sequence parallel group.\nrequired\n\n\ngradient_accumulation_steps\nint\nNumber of steps to accumulate gradients over.\nrequired\n\n\nring_attn_func\nRingAttnFunc\nWhich ring attention function to use. Currently unused, but related to above TODO.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[dict[str, torch.Tensor], int, int]\ntuple of: - Batch dictionary with sliced tensors. - The original sequence length before padding. - The number of padding tokens added." }, { - "objectID": "docs/api/utils.distributed.html#functions", - "href": "docs/api/utils.distributed.html#functions", - "title": "utils.distributed", + "objectID": "docs/api/monkeypatch.data.batch_dataset_fetcher.html", + "href": "docs/api/monkeypatch.data.batch_dataset_fetcher.html", + "title": "monkeypatch.data.batch_dataset_fetcher", "section": "", - "text": "Name\nDescription\n\n\n\n\nbarrier\nActs as a barrier to wait for all processes. This ensures that all processes\n\n\ncleanup_distributed\nDestroy process group if torch distributed is initialized. Called in training early\n\n\ncompute_and_broadcast\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\n\n\ngather_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\ngather_scalar_from_all_ranks\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\n\n\nis_distributed\nCheck if distributed training is initialized.\n\n\nis_main_process\nCheck if the current process is the main process. If not in distributed mode,\n\n\nreduce_and_broadcast\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\n\n\nzero_first\nruns the wrapped context so that rank 0 runs first before other ranks\n\n\n\n\n\nutils.distributed.barrier()\nActs as a barrier to wait for all processes. This ensures that all processes\nreach the barrier before proceeding further.\n\n\n\nutils.distributed.cleanup_distributed()\nDestroy process group if torch distributed is initialized. Called in training early\ntermination or when training successfully completes.\n\n\n\nutils.distributed.compute_and_broadcast(fn)\nCompute a value using the function ‘fn’ only on the specified rank (default is 0).\nThe value is then broadcasted to all other ranks.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that computes the value. Default is 0.\nReturns:\n- The computed value (int or float).\n\n\n\nutils.distributed.gather_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.gather_scalar_from_all_ranks(fn, world_size=1)\nRun a callable ‘fn’ on all ranks and gather the results on the specified rank.\nArgs:\n- fn (callable): A function that computes the value. This should not have any side effects.\n- rank (int, optional): The rank that gathers the values. Default is 0.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- A list of computed values from all ranks if on the gathering rank, otherwise None.\n\n\n\nutils.distributed.is_distributed()\nCheck if distributed training is initialized.\n\n\n\nutils.distributed.is_main_process(use_environ=False)\nCheck if the current process is the main process. If not in distributed mode,\nalways return True.\nArgs:\n- use_environ (bool, optional): Use environment variable to determine main process.\nReturns:\n- bool: True if the current process is the main process, False otherwise.\n\n\n\nutils.distributed.reduce_and_broadcast(fn1, fn2)\nRun a callable ‘fn1’ on all ranks, gather the results, reduce them using ‘fn2’,\nand then broadcast the reduced result to all ranks.\nArgs:\n- fn1 (callable): A function that computes the value on each rank.\n- fn2 (callable): A reduction function that takes a list of values and returns a single value.\n- world_size (int, optional): Total number of processes in the current distributed setup.\nReturns:\n- The reduced and broadcasted value.\n\n\n\nutils.distributed.zero_first(is_main)\nruns the wrapped context so that rank 0 runs first before other ranks" + "text": "monkeypatch.data.batch_dataset_fetcher\nmonkeypatch.data.batch_dataset_fetcher\nmonkey patches for the dataset fetcher to handle batches of packed indexes" }, { - "objectID": "docs/api/utils.tokenization.html", - "href": "docs/api/utils.tokenization.html", - "title": "utils.tokenization", + "objectID": "docs/api/core.trainers.utils.html", + "href": "docs/api/core.trainers.utils.html", + "title": "core.trainers.utils", "section": "", - "text": "utils.tokenization\nModule for tokenization utilities\n\n\n\n\n\nName\nDescription\n\n\n\n\ncolor_token_for_rl_debug\nHelper function to color tokens based on their type.\n\n\nprocess_tokens_for_rl_debug\nHelper function to process and color tokens.\n\n\n\n\n\nutils.tokenization.color_token_for_rl_debug(\n decoded_token,\n encoded_token,\n color,\n text_only,\n)\nHelper function to color tokens based on their type.\n\n\n\nutils.tokenization.process_tokens_for_rl_debug(\n tokens,\n color,\n tokenizer,\n text_only,\n)\nHelper function to process and color tokens." + "text": "core.trainers.utils\ncore.trainers.utils\nUtils for Axolotl trainers" }, { - "objectID": "docs/api/utils.tokenization.html#functions", - "href": "docs/api/utils.tokenization.html#functions", - "title": "utils.tokenization", + "objectID": "docs/api/kernels.quantize.html", + "href": "docs/api/kernels.quantize.html", + "title": "kernels.quantize", "section": "", - "text": "Name\nDescription\n\n\n\n\ncolor_token_for_rl_debug\nHelper function to color tokens based on their type.\n\n\nprocess_tokens_for_rl_debug\nHelper function to process and color tokens.\n\n\n\n\n\nutils.tokenization.color_token_for_rl_debug(\n decoded_token,\n encoded_token,\n color,\n text_only,\n)\nHelper function to color tokens based on their type.\n\n\n\nutils.tokenization.process_tokens_for_rl_debug(\n tokens,\n color,\n tokenizer,\n text_only,\n)\nHelper function to process and color tokens." + "text": "kernels.quantize\nDequantization utilities for bitsandbytes integration.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndequantize\nFast NF4 dequantization using bitsandbytes CUDA kernels.\n\n\n\n\n\nkernels.quantize.dequantize(W, quant_state=None, out=None)\nFast NF4 dequantization using bitsandbytes CUDA kernels.\nPerforms efficient dequantization of weights from NF4 format using bitsandbytes’\noptimized CUDA implementations. Supports both legacy list and new QuantState\nformats.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nW\ntorch.Tensor\nQuantized weight tensor to dequantize\nrequired\n\n\nquant_state\nQuantState | list | None\nQuantization state containing metadata needed for dequantization. Can be either a QuantState object or legacy list format. If None, returns W unchanged.\nNone\n\n\nout\ntorch.Tensor | None\nOptional output tensor for storing dequantized results. Must match expected shape and dtype if provided.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nDequantized tensor in the specified dtype (fp16 or bf16). Will be transposed if\n\n\n\ntorch.Tensor\ninput W was transposed.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf provided output tensor doesn’t match expected shape / dtype.\n\n\n\n\n\n\nUses CUDA streams for better performance when available in newer bitsandbytes\nversions (>0.43.3)." }, { - "objectID": "docs/api/utils.schemas.integrations.html", - "href": "docs/api/utils.schemas.integrations.html", - "title": "utils.schemas.integrations", + "objectID": "docs/api/kernels.quantize.html#functions", + "href": "docs/api/kernels.quantize.html#functions", + "title": "kernels.quantize", "section": "", - "text": "utils.schemas.integrations\nPydantic models for Axolotl integrations\n\n\n\n\n\nName\nDescription\n\n\n\n\nCometConfig\nComet configuration subset\n\n\nGradioConfig\nGradio configuration subset\n\n\nLISAConfig\nLISA configuration subset\n\n\nMLFlowConfig\nMLFlow configuration subset\n\n\nRayConfig\nRay launcher configuration subset\n\n\nWandbConfig\nWandb configuration subset\n\n\n\n\n\nutils.schemas.integrations.CometConfig()\nComet configuration subset\n\n\n\nutils.schemas.integrations.GradioConfig()\nGradio configuration subset\n\n\n\nutils.schemas.integrations.LISAConfig()\nLISA configuration subset\n\n\n\nutils.schemas.integrations.MLFlowConfig()\nMLFlow configuration subset\n\n\n\nutils.schemas.integrations.RayConfig()\nRay launcher configuration subset\n\n\n\nutils.schemas.integrations.WandbConfig()\nWandb configuration subset" + "text": "Name\nDescription\n\n\n\n\ndequantize\nFast NF4 dequantization using bitsandbytes CUDA kernels.\n\n\n\n\n\nkernels.quantize.dequantize(W, quant_state=None, out=None)\nFast NF4 dequantization using bitsandbytes CUDA kernels.\nPerforms efficient dequantization of weights from NF4 format using bitsandbytes’\noptimized CUDA implementations. Supports both legacy list and new QuantState\nformats.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nW\ntorch.Tensor\nQuantized weight tensor to dequantize\nrequired\n\n\nquant_state\nQuantState | list | None\nQuantization state containing metadata needed for dequantization. Can be either a QuantState object or legacy list format. If None, returns W unchanged.\nNone\n\n\nout\ntorch.Tensor | None\nOptional output tensor for storing dequantized results. Must match expected shape and dtype if provided.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nDequantized tensor in the specified dtype (fp16 or bf16). Will be transposed if\n\n\n\ntorch.Tensor\ninput W was transposed.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf provided output tensor doesn’t match expected shape / dtype.\n\n\n\n\n\n\nUses CUDA streams for better performance when available in newer bitsandbytes\nversions (>0.43.3)." }, { - "objectID": "docs/api/utils.schemas.integrations.html#classes", - "href": "docs/api/utils.schemas.integrations.html#classes", - "title": "utils.schemas.integrations", + "objectID": "docs/api/utils.dict.html", + "href": "docs/api/utils.dict.html", + "title": "utils.dict", "section": "", - "text": "Name\nDescription\n\n\n\n\nCometConfig\nComet configuration subset\n\n\nGradioConfig\nGradio configuration subset\n\n\nLISAConfig\nLISA configuration subset\n\n\nMLFlowConfig\nMLFlow configuration subset\n\n\nRayConfig\nRay launcher configuration subset\n\n\nWandbConfig\nWandb configuration subset\n\n\n\n\n\nutils.schemas.integrations.CometConfig()\nComet configuration subset\n\n\n\nutils.schemas.integrations.GradioConfig()\nGradio configuration subset\n\n\n\nutils.schemas.integrations.LISAConfig()\nLISA configuration subset\n\n\n\nutils.schemas.integrations.MLFlowConfig()\nMLFlow configuration subset\n\n\n\nutils.schemas.integrations.RayConfig()\nRay launcher configuration subset\n\n\n\nutils.schemas.integrations.WandbConfig()\nWandb configuration subset" + "text": "utils.dict\nModule containing the DictDefault class\n\n\n\n\n\nName\nDescription\n\n\n\n\nDictDefault\nA Dict that returns None instead of returning empty Dict for missing keys.\n\n\n\n\n\nutils.dict.DictDefault()\nA Dict that returns None instead of returning empty Dict for missing keys." }, { - "objectID": "docs/api/utils.schedulers.html", - "href": "docs/api/utils.schedulers.html", - "title": "utils.schedulers", + "objectID": "docs/api/utils.dict.html#classes", + "href": "docs/api/utils.dict.html#classes", + "title": "utils.dict", "section": "", - "text": "utils.schedulers\nModule for custom LRScheduler class\n\n\n\n\n\nName\nDescription\n\n\n\n\nInterpolatingLogScheduler\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\nRexLR\nReflected Exponential (REX) learning rate scheduler.\n\n\n\n\n\nutils.schedulers.InterpolatingLogScheduler(\n self,\n optimizer,\n num_steps,\n min_lr,\n max_lr,\n last_epoch=-1,\n)\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\n\nutils.schedulers.RexLR(\n self,\n optimizer,\n max_lr,\n min_lr,\n total_steps=0,\n num_warmup_steps=0,\n last_step=0,\n)\nReflected Exponential (REX) learning rate scheduler.\n\nOriginal implementation: https://github.com/IvanVassi/REX_LR\nOriginal license: Apache 2.0\nBased on: https://arxiv.org/abs/2107.04197\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\ntorch.optim.Optimizer\nThe optimizer to schedule the learning rate for.\nrequired\n\n\nmax_lr\nfloat\nThe maximum learning rate.\nrequired\n\n\nmin_lr\nfloat\nThe minimum learning rate.\nrequired\n\n\ntotal_steps\nint\nThe total number of training steps.\n0\n\n\nnum_warmup_steps\nint\nThe number of warmup steps.\n0\n\n\nlast_step\nint\nThe index of last step.\n0\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_cosine_schedule_with_min_lr\n\n\n\nget_cosine_schedule_with_quadratic_warmup\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\n\n\nget_cosine_schedule_with_warmup_decay_constant\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_min_lr(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n min_lr_ratio=0.0,\n)\n\n\n\nlinear warmup from 0 -> max_lr over num_warmup_steps\ncosine learning rate annealing from max_lr -> min_lr over num_training_steps\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_quadratic_warmup(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n num_cycles=0.5,\n last_epoch=-1,\n)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the\ninitial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nnum_cycles\nfloat, optional, defaults to 0.5\nThe number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine).\n0.5\n\n\nlast_epoch\nint, optional, defaults to -1\nThe index of the last epoch when resuming training.\n-1\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule.\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_warmup_decay_constant(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n constant_lr_ratio,\n min_lr_ratio,\n num_cycles=0.5,\n last_epoch=-1,\n)\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to min_lr_ratio until num_training_steps * constant_lr_ratio, after constant_rate returns constant value of min_rate\n, after a warmup period during which it increases linearly between 0 and the initial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nconstant_lr_ratio\nfloat\n(float): The ratio of num_training_steps to decrease by cosine function.\nrequired\n\n\nmin_lr_ratio\nfloat\n(float): The ratio of maximum learning rate for cosine function to decay to minimum learning rate. | _required_ | | num_cycles |float, *optional*, defaults to 0.5 | The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine). |0.5| | last_epoch |int, *optional*, defaults to -1 | The index of the last epoch when resuming training. |-1`\n\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule." + "text": "Name\nDescription\n\n\n\n\nDictDefault\nA Dict that returns None instead of returning empty Dict for missing keys.\n\n\n\n\n\nutils.dict.DictDefault()\nA Dict that returns None instead of returning empty Dict for missing keys." }, { - "objectID": "docs/api/utils.schedulers.html#classes", - "href": "docs/api/utils.schedulers.html#classes", - "title": "utils.schedulers", + "objectID": "docs/api/utils.trainer.html", + "href": "docs/api/utils.trainer.html", + "title": "utils.trainer", "section": "", - "text": "Name\nDescription\n\n\n\n\nInterpolatingLogScheduler\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\nRexLR\nReflected Exponential (REX) learning rate scheduler.\n\n\n\n\n\nutils.schedulers.InterpolatingLogScheduler(\n self,\n optimizer,\n num_steps,\n min_lr,\n max_lr,\n last_epoch=-1,\n)\nA scheduler that interpolates learning rates in a logarithmic fashion\n\n\n\nutils.schedulers.RexLR(\n self,\n optimizer,\n max_lr,\n min_lr,\n total_steps=0,\n num_warmup_steps=0,\n last_step=0,\n)\nReflected Exponential (REX) learning rate scheduler.\n\nOriginal implementation: https://github.com/IvanVassi/REX_LR\nOriginal license: Apache 2.0\nBased on: https://arxiv.org/abs/2107.04197\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\ntorch.optim.Optimizer\nThe optimizer to schedule the learning rate for.\nrequired\n\n\nmax_lr\nfloat\nThe maximum learning rate.\nrequired\n\n\nmin_lr\nfloat\nThe minimum learning rate.\nrequired\n\n\ntotal_steps\nint\nThe total number of training steps.\n0\n\n\nnum_warmup_steps\nint\nThe number of warmup steps.\n0\n\n\nlast_step\nint\nThe index of last step.\n0" + "text": "utils.trainer\nModule containing the Trainer class and related functions\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_pose_position_ids\nuse the PoSE technique to extend the context length by randomly skipping\n\n\nadd_position_ids\nHandle both single-example and batched data.\n\n\ndrop_long_seq\nDrop samples whose sequence length is either too long (> sequence_len)\n\n\nsetup_trainer\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\nutils.trainer.add_pose_position_ids(\n sample,\n max_context_len=32768,\n split_on_token_ids=None,\n chunks=2,\n)\nuse the PoSE technique to extend the context length by randomly skipping\npositions in the context. We only want to skip right before tokens in\nthe split_on_token_ids list. We should attempt to randomly distribute\nthe skips, but we don’t need the final position_ids to be the full\ncontext_len. There may be multiple turns in the context, so we want to\nmake sure we take into account the maximum possible number of skips\nremaining in each sample.\n\n\n\nutils.trainer.add_position_ids(sample)\nHandle both single-example and batched data.\n- single example: sample[‘input_ids’] is a list[int]\n- batched data: sample[‘input_ids’] is a list[list[int]]\n\n\n\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\nDrop samples whose sequence length is either too long (> sequence_len)\nor too short (< min_sequence_len).\nWorks for both single-example (list[int]) or batched (list[list[int]]).\n\n\n\nutils.trainer.setup_trainer(\n cfg,\n train_dataset,\n eval_dataset,\n model,\n tokenizer,\n processor,\n total_num_steps,\n model_ref=None,\n peft_config=None,\n)\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nAxolotl config object containing training parameters.\nrequired\n\n\ntrain_dataset\n\nDataset to use for training.\nrequired\n\n\neval_dataset\n\nDataset to use for evaluation.\nrequired\n\n\nmodel\n\nThe model to train.\nrequired\n\n\ntokenizer\n\nTokenizer for processing text input.\nrequired\n\n\nprocessor\n\nProcessor for data preparation.\nrequired\n\n\ntotal_num_steps\n\nThe total number of training steps.\nrequired\n\n\nmodel_ref\n\nOptional reference model for RLHF training. Default is None.\nNone\n\n\npeft_config\n\nOptional PEFT (Parameter-Efficient Fine-Tuning) configuration. Default is None.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nA trainer instance (either HFRLTrainer or HFCausalTrainer) configured based on the provided parameters." }, { - "objectID": "docs/api/utils.schedulers.html#functions", - "href": "docs/api/utils.schedulers.html#functions", - "title": "utils.schedulers", + "objectID": "docs/api/utils.trainer.html#functions", + "href": "docs/api/utils.trainer.html#functions", + "title": "utils.trainer", "section": "", - "text": "Name\nDescription\n\n\n\n\nget_cosine_schedule_with_min_lr\n\n\n\nget_cosine_schedule_with_quadratic_warmup\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\n\n\nget_cosine_schedule_with_warmup_decay_constant\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_min_lr(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n min_lr_ratio=0.0,\n)\n\n\n\nlinear warmup from 0 -> max_lr over num_warmup_steps\ncosine learning rate annealing from max_lr -> min_lr over num_training_steps\n\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_quadratic_warmup(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n num_cycles=0.5,\n last_epoch=-1,\n)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the\ninitial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nnum_cycles\nfloat, optional, defaults to 0.5\nThe number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine).\n0.5\n\n\nlast_epoch\nint, optional, defaults to -1\nThe index of the last epoch when resuming training.\n-1\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule.\n\n\n\n\nutils.schedulers.get_cosine_schedule_with_warmup_decay_constant(\n optimizer,\n num_warmup_steps,\n num_training_steps,\n constant_lr_ratio,\n min_lr_ratio,\n num_cycles=0.5,\n last_epoch=-1,\n)\nImplementation of Continual Pre-Training of Large Language Models: How to (re)warm your model? (https://arxiv.org/pdf/2308.04014.pdf)\nCreate a schedule with a learning rate that decreases following the values of the cosine function between the\ninitial lr set in the optimizer to min_lr_ratio until num_training_steps * constant_lr_ratio, after constant_rate returns constant value of min_rate\n, after a warmup period during which it increases linearly between 0 and the initial lr set in the optimizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\noptimizer\n[~torch.optim.Optimizer]\nThe optimizer for which to schedule the learning rate.\nrequired\n\n\nnum_warmup_steps\nint\nThe number of steps for the warmup phase.\nrequired\n\n\nnum_training_steps\nint\nThe total number of training steps.\nrequired\n\n\nconstant_lr_ratio\nfloat\n(float): The ratio of num_training_steps to decrease by cosine function.\nrequired\n\n\nmin_lr_ratio\nfloat\n(float): The ratio of maximum learning rate for cosine function to decay to minimum learning rate. | _required_ | | num_cycles |float, *optional*, defaults to 0.5 | The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0 following a half-cosine). |0.5| | last_epoch |int, *optional*, defaults to -1 | The index of the last epoch when resuming training. |-1`\n\n\n\n\n\n\n\ntorch.optim.lr_scheduler.LambdaLR with the appropriate schedule." + "text": "Name\nDescription\n\n\n\n\nadd_pose_position_ids\nuse the PoSE technique to extend the context length by randomly skipping\n\n\nadd_position_ids\nHandle both single-example and batched data.\n\n\ndrop_long_seq\nDrop samples whose sequence length is either too long (> sequence_len)\n\n\nsetup_trainer\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\nutils.trainer.add_pose_position_ids(\n sample,\n max_context_len=32768,\n split_on_token_ids=None,\n chunks=2,\n)\nuse the PoSE technique to extend the context length by randomly skipping\npositions in the context. We only want to skip right before tokens in\nthe split_on_token_ids list. We should attempt to randomly distribute\nthe skips, but we don’t need the final position_ids to be the full\ncontext_len. There may be multiple turns in the context, so we want to\nmake sure we take into account the maximum possible number of skips\nremaining in each sample.\n\n\n\nutils.trainer.add_position_ids(sample)\nHandle both single-example and batched data.\n- single example: sample[‘input_ids’] is a list[int]\n- batched data: sample[‘input_ids’] is a list[list[int]]\n\n\n\nutils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)\nDrop samples whose sequence length is either too long (> sequence_len)\nor too short (< min_sequence_len).\nWorks for both single-example (list[int]) or batched (list[list[int]]).\n\n\n\nutils.trainer.setup_trainer(\n cfg,\n train_dataset,\n eval_dataset,\n model,\n tokenizer,\n processor,\n total_num_steps,\n model_ref=None,\n peft_config=None,\n)\nHelper method for instantiating and building a (causal or RLHF) trainer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nAxolotl config object containing training parameters.\nrequired\n\n\ntrain_dataset\n\nDataset to use for training.\nrequired\n\n\neval_dataset\n\nDataset to use for evaluation.\nrequired\n\n\nmodel\n\nThe model to train.\nrequired\n\n\ntokenizer\n\nTokenizer for processing text input.\nrequired\n\n\nprocessor\n\nProcessor for data preparation.\nrequired\n\n\ntotal_num_steps\n\nThe total number of training steps.\nrequired\n\n\nmodel_ref\n\nOptional reference model for RLHF training. Default is None.\nNone\n\n\npeft_config\n\nOptional PEFT (Parameter-Efficient Fine-Tuning) configuration. Default is None.\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nA trainer instance (either HFRLTrainer or HFCausalTrainer) configured based on the provided parameters." }, { - "objectID": "docs/api/core.trainers.mixins.scheduler.html", - "href": "docs/api/core.trainers.mixins.scheduler.html", - "title": "core.trainers.mixins.scheduler", + "objectID": "docs/api/cli.merge_lora.html", + "href": "docs/api/cli.merge_lora.html", + "title": "cli.merge_lora", "section": "", - "text": "core.trainers.mixins.scheduler\nModule for Axolotl trainer scheduler mixin\n\n\n\n\n\nName\nDescription\n\n\n\n\nSchedulerMixin\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin()\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncreate_scheduler\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin.create_scheduler(\n num_training_steps,\n optimizer=None,\n)\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\npassed as an argument.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nnum_training_steps\nint\nThe number of training steps to do.\nrequired\n\n\noptimizer\ntorch.optim.Optimizer\nThe training optimizer\nNone" + "text": "cli.merge_lora\nCLI to merge a trained LoRA into a base model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\n\n\ndo_merge_lora\nCalls transformers’ merge_and_unload on the model given in the axolotl config\n\n\n\n\n\ncli.merge_lora.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\nconfig values will be overwritten to allow the LoRA merge logic to work as expected\n(load_in_8bit=False, load_in4bit=False, flash_attention=False, etc.).\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf target directory for LoRA merged model does not exist.\n\n\n\n\n\n\n\ncli.merge_lora.do_merge_lora(cfg)\nCalls transformers’ merge_and_unload on the model given in the axolotl config\nalong with the LoRA adapters to combine them into a single base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" }, { - "objectID": "docs/api/core.trainers.mixins.scheduler.html#classes", - "href": "docs/api/core.trainers.mixins.scheduler.html#classes", - "title": "core.trainers.mixins.scheduler", + "objectID": "docs/api/cli.merge_lora.html#functions", + "href": "docs/api/cli.merge_lora.html#functions", + "title": "cli.merge_lora", "section": "", - "text": "Name\nDescription\n\n\n\n\nSchedulerMixin\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin()\nMixin class for scheduler setup in CausalTrainer.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncreate_scheduler\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\n\n\n\n\n\ncore.trainers.mixins.scheduler.SchedulerMixin.create_scheduler(\n num_training_steps,\n optimizer=None,\n)\nSet up the scheduler. The optimizer of the trainer must have been set up either before this method is called or\npassed as an argument.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nnum_training_steps\nint\nThe number of training steps to do.\nrequired\n\n\noptimizer\ntorch.optim.Optimizer\nThe training optimizer\nNone" + "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\n\n\ndo_merge_lora\nCalls transformers’ merge_and_unload on the model given in the axolotl config\n\n\n\n\n\ncli.merge_lora.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_merge_lora. Note that various\nconfig values will be overwritten to allow the LoRA merge logic to work as expected\n(load_in_8bit=False, load_in4bit=False, flash_attention=False, etc.).\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf target directory for LoRA merged model does not exist.\n\n\n\n\n\n\n\ncli.merge_lora.do_merge_lora(cfg)\nCalls transformers’ merge_and_unload on the model given in the axolotl config\nalong with the LoRA adapters to combine them into a single base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" }, { - "objectID": "docs/api/core.datasets.chat.html", - "href": "docs/api/core.datasets.chat.html", - "title": "core.datasets.chat", + "objectID": "docs/api/monkeypatch.lora_kernels.html", + "href": "docs/api/monkeypatch.lora_kernels.html", + "title": "monkeypatch.lora_kernels", "section": "", - "text": "core.datasets.chat\nchat dataset module\n\n\n\n\n\nName\nDescription\n\n\n\n\nTokenizedChatDataset\nTokenized chat dataset\n\n\n\n\n\ncore.datasets.chat.TokenizedChatDataset(\n self,\n data,\n model_transform,\n *args,\n message_transform=None,\n formatter=None,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nTokenized chat dataset" + "text": "monkeypatch.lora_kernels\nModule for patching custom LoRA Triton kernels and torch.autograd functions.\n\n\n\n\n\nName\nDescription\n\n\n\n\nFakeMLP\nplaceholder MLP for triton patching\n\n\n\n\n\nmonkeypatch.lora_kernels.FakeMLP(self, gate_proj, up_proj, down_proj)\nplaceholder MLP for triton patching\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\napply_lora_kernel_patches\nApplies optimized Triton kernel patches to a PEFT model.\n\n\nget_attention_cls_from_config\nGet the appropriate attention class by inspecting the model config.\n\n\noriginal_apply_o\nOriginal implementation of output projection without optimizations.\n\n\noriginal_apply_qkv\nOriginal implementation of QKV projection without optimizations.\n\n\npatch_self_attn_lora\nGiven an axolotl config, this method patches the inferred attention class forward\n\n\n\n\n\nmonkeypatch.lora_kernels.apply_lora_kernel_patches(model, cfg)\nApplies optimized Triton kernel patches to a PEFT model.\nPatches a PEFT model with optimized implementations for MLP and attention\ncomputations. The optimizations include custom Triton kernels for activation\nfunctions and specialized autograd functions for LoRA computations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\nPeftModelForCausalLM\nA PEFT model to be patched with optimized kernels.\nrequired\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nPeftModelForCausalLM\nPeftModelForCausalLM\nThe patched model with optimized kernels.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTypeError\nIf the provided model is not a PeftModelForCausalLM.\n\n\n\nNotImplementedError\nIf the model type is not supported.\n\n\n\nAssertionError\nIf multiple adapters are active (currently unsupported).\n\n\n\n\n\n\nThe optimizations require LoRA adapters with no dropout and no bias terms. The\nfunction will skip patching if these conditions aren’t met.\n\n\n\n\nmonkeypatch.lora_kernels.get_attention_cls_from_config(cfg)\nGet the appropriate attention class by inspecting the model config.\nUses dynamic import to support any model architecture that follows\nthe standard transformers naming convention.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nType[nn.Module]\nThe appropriate attention class for the model.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf base_model not specified or attention class cannot be imported\n\n\n\nImportError\nIf the model module or attention class doesn’t exist\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_o(self, hidden_states)\nOriginal implementation of output projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim]`.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nThe output projection result.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_qkv(self, hidden_states)\nOriginal implementation of QKV projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nA tuple (query_states, key_states, value_states) containing the projected states for query, key, and value.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.patch_self_attn_lora(cfg)\nGiven an axolotl config, this method patches the inferred attention class forward\npass with optimized LoRA implementations.\nIt modifies the attention class to use optimized QKV and output projections. The\noriginal implementation is preserved and can be restored if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf the required code blocks are not found in the attention implementation." }, { - "objectID": "docs/api/core.datasets.chat.html#classes", - "href": "docs/api/core.datasets.chat.html#classes", - "title": "core.datasets.chat", + "objectID": "docs/api/monkeypatch.lora_kernels.html#classes", + "href": "docs/api/monkeypatch.lora_kernels.html#classes", + "title": "monkeypatch.lora_kernels", "section": "", - "text": "Name\nDescription\n\n\n\n\nTokenizedChatDataset\nTokenized chat dataset\n\n\n\n\n\ncore.datasets.chat.TokenizedChatDataset(\n self,\n data,\n model_transform,\n *args,\n message_transform=None,\n formatter=None,\n process_count=None,\n keep_in_memory=False,\n **kwargs,\n)\nTokenized chat dataset" + "text": "Name\nDescription\n\n\n\n\nFakeMLP\nplaceholder MLP for triton patching\n\n\n\n\n\nmonkeypatch.lora_kernels.FakeMLP(self, gate_proj, up_proj, down_proj)\nplaceholder MLP for triton patching" }, { - "objectID": "docs/api/utils.callbacks.mlflow_.html", - "href": "docs/api/utils.callbacks.mlflow_.html", - "title": "utils.callbacks.mlflow_", + "objectID": "docs/api/monkeypatch.lora_kernels.html#functions", + "href": "docs/api/monkeypatch.lora_kernels.html#functions", + "title": "monkeypatch.lora_kernels", "section": "", - "text": "utils.callbacks.mlflow_\nMLFlow module for trainer callbacks\n\n\n\n\n\nName\nDescription\n\n\n\n\nSaveAxolotlConfigtoMlflowCallback\nCallback to save axolotl config to mlflow\n\n\n\n\n\nutils.callbacks.mlflow_.SaveAxolotlConfigtoMlflowCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to mlflow" + "text": "Name\nDescription\n\n\n\n\napply_lora_kernel_patches\nApplies optimized Triton kernel patches to a PEFT model.\n\n\nget_attention_cls_from_config\nGet the appropriate attention class by inspecting the model config.\n\n\noriginal_apply_o\nOriginal implementation of output projection without optimizations.\n\n\noriginal_apply_qkv\nOriginal implementation of QKV projection without optimizations.\n\n\npatch_self_attn_lora\nGiven an axolotl config, this method patches the inferred attention class forward\n\n\n\n\n\nmonkeypatch.lora_kernels.apply_lora_kernel_patches(model, cfg)\nApplies optimized Triton kernel patches to a PEFT model.\nPatches a PEFT model with optimized implementations for MLP and attention\ncomputations. The optimizations include custom Triton kernels for activation\nfunctions and specialized autograd functions for LoRA computations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\nPeftModelForCausalLM\nA PEFT model to be patched with optimized kernels.\nrequired\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nPeftModelForCausalLM\nPeftModelForCausalLM\nThe patched model with optimized kernels.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTypeError\nIf the provided model is not a PeftModelForCausalLM.\n\n\n\nNotImplementedError\nIf the model type is not supported.\n\n\n\nAssertionError\nIf multiple adapters are active (currently unsupported).\n\n\n\n\n\n\nThe optimizations require LoRA adapters with no dropout and no bias terms. The\nfunction will skip patching if these conditions aren’t met.\n\n\n\n\nmonkeypatch.lora_kernels.get_attention_cls_from_config(cfg)\nGet the appropriate attention class by inspecting the model config.\nUses dynamic import to support any model architecture that follows\nthe standard transformers naming convention.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nType[nn.Module]\nThe appropriate attention class for the model.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf base_model not specified or attention class cannot be imported\n\n\n\nImportError\nIf the model module or attention class doesn’t exist\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_o(self, hidden_states)\nOriginal implementation of output projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim]`.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nThe output projection result.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.original_apply_qkv(self, hidden_states)\nOriginal implementation of QKV projection without optimizations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nself\nnn.Module\nThe attention module instance.\nrequired\n\n\nhidden_states\ntorch.Tensor\nInput tensor of shape [batch_size, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nA tuple (query_states, key_states, value_states) containing the projected states for query, key, and value.\n\n\n\n\n\n\n\nmonkeypatch.lora_kernels.patch_self_attn_lora(cfg)\nGiven an axolotl config, this method patches the inferred attention class forward\npass with optimized LoRA implementations.\nIt modifies the attention class to use optimized QKV and output projections. The\noriginal implementation is preserved and can be restored if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nAssertionError\nIf the required code blocks are not found in the attention implementation." }, { - "objectID": "docs/api/utils.callbacks.mlflow_.html#classes", - "href": "docs/api/utils.callbacks.mlflow_.html#classes", - "title": "utils.callbacks.mlflow_", + "objectID": "docs/api/core.chat.format.shared.html", + "href": "docs/api/core.chat.format.shared.html", + "title": "core.chat.format.shared", "section": "", - "text": "Name\nDescription\n\n\n\n\nSaveAxolotlConfigtoMlflowCallback\nCallback to save axolotl config to mlflow\n\n\n\n\n\nutils.callbacks.mlflow_.SaveAxolotlConfigtoMlflowCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to mlflow" + "text": "core.chat.format.shared\ncore.chat.format.shared\nshared functions for format transforms" }, { - "objectID": "docs/api/monkeypatch.mistral_attn_hijack_flash.html", - "href": "docs/api/monkeypatch.mistral_attn_hijack_flash.html", - "title": "monkeypatch.mistral_attn_hijack_flash", + "objectID": "docs/api/utils.callbacks.comet_.html", + "href": "docs/api/utils.callbacks.comet_.html", + "title": "utils.callbacks.comet_", "section": "", - "text": "monkeypatch.mistral_attn_hijack_flash\nFlash attention monkey patch for mistral model\n\n\n\n\n\nName\nDescription\n\n\n\n\nMistralDecoderLayer\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer()\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" + "text": "utils.callbacks.comet_\nComet module for trainer callbacks\n\n\n\n\n\nName\nDescription\n\n\n\n\nSaveAxolotlConfigtoCometCallback\nCallback to save axolotl config to comet\n\n\n\n\n\nutils.callbacks.comet_.SaveAxolotlConfigtoCometCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to comet" }, { - "objectID": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#classes", - "href": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#classes", - "title": "monkeypatch.mistral_attn_hijack_flash", + "objectID": "docs/api/utils.callbacks.comet_.html#classes", + "href": "docs/api/utils.callbacks.comet_.html#classes", + "title": "utils.callbacks.comet_", "section": "", - "text": "Name\nDescription\n\n\n\n\nMistralDecoderLayer\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer()\npatched version of MistralDecoderLayer to pass through the precalculated cu_seqlens\n\n\n\n\n\nName\nDescription\n\n\n\n\nforward\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.MistralDecoderLayer.forward(\n hidden_states,\n attention_mask=None,\n position_ids=None,\n past_key_value=None,\n output_attentions=False,\n use_cache=False,\n cu_seqlens=None,\n max_seqlen=None,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nhidden_states\ntorch.FloatTensor\ninput to the layer of shape (batch, seq_len, embed_dim)\nrequired\n\n\nattention_mask\ntorch.FloatTensor, optional\nattention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values.\nNone\n\n\noutput_attentions\nbool, optional\nWhether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.\nFalse\n\n\nuse_cache\nbool, optional\nIf set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).\nFalse\n\n\npast_key_value\nTuple(torch.FloatTensor), optional\ncached past key and value projection states\nNone" + "text": "Name\nDescription\n\n\n\n\nSaveAxolotlConfigtoCometCallback\nCallback to save axolotl config to comet\n\n\n\n\n\nutils.callbacks.comet_.SaveAxolotlConfigtoCometCallback(\n self,\n axolotl_config_path,\n)\nCallback to save axolotl config to comet" }, { - "objectID": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#functions", - "href": "docs/api/monkeypatch.mistral_attn_hijack_flash.html#functions", - "title": "monkeypatch.mistral_attn_hijack_flash", + "objectID": "docs/api/core.training_args.html", + "href": "docs/api/core.training_args.html", + "title": "core.training_args", "section": "", - "text": "Name\nDescription\n\n\n\n\ngenerate_qkv\n\n\n\n\n\n\nmonkeypatch.mistral_attn_hijack_flash.generate_qkv(\n q,\n k,\n v,\n query_padding_mask=None,\n key_padding_mask=None,\n kvpacked=False,\n qkvpacked=False,\n)\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nq\n\n(batch_size, seqlen_q, nheads, d)\nrequired\n\n\nk\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nv\n\n(batch_size, seqlen_k, nheads_k, d)\nrequired\n\n\nquery_padding_mask\n\n(batch_size, seqlen), bool\nNone\n\n\nkey_padding_mask\n\n(batch_size, seqlen), bool\nNone" + "text": "core.training_args\nextra axolotl specific training args\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlCPOConfig\nCPO config for CPO training\n\n\nAxolotlKTOConfig\nKTO config for KTO training\n\n\nAxolotlORPOConfig\nORPO config for ORPO training\n\n\nAxolotlPRMConfig\nPRM config for PRM training\n\n\nAxolotlRewardConfig\nReward config for Reward training\n\n\nAxolotlTrainingArguments\nTraining arguments for Causal trainer\n\n\nAxolotlTrainingMixins\nMixin class for the Axolotl training args.\n\n\n\n\n\ncore.training_args.AxolotlCPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n simpo_gamma=None,\n)\nCPO config for CPO training\n\n\n\ncore.training_args.AxolotlKTOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nKTO config for KTO training\n\n\n\ncore.training_args.AxolotlORPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nORPO config for ORPO training\n\n\n\ncore.training_args.AxolotlPRMConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nPRM config for PRM training\n\n\n\ncore.training_args.AxolotlRewardConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nReward config for Reward training\n\n\n\ncore.training_args.AxolotlTrainingArguments(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nTraining arguments for Causal trainer\nThis code is duplicated due to HF TrainingArguments not setting output_dir with a\ndefault value so it can’t be used as a mixin.\n\n\n\ncore.training_args.AxolotlTrainingMixins(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nMixin class for the Axolotl training args." }, { - "objectID": "docs/api/core.chat.format.llama3x.html", - "href": "docs/api/core.chat.format.llama3x.html", - "title": "core.chat.format.llama3x", + "objectID": "docs/api/core.training_args.html#classes", + "href": "docs/api/core.training_args.html#classes", + "title": "core.training_args", "section": "", - "text": "core.chat.format.llama3x\ncore.chat.format.llama3x\nLlama 3.x chat formatting functions for MessageContents" + "text": "Name\nDescription\n\n\n\n\nAxolotlCPOConfig\nCPO config for CPO training\n\n\nAxolotlKTOConfig\nKTO config for KTO training\n\n\nAxolotlORPOConfig\nORPO config for ORPO training\n\n\nAxolotlPRMConfig\nPRM config for PRM training\n\n\nAxolotlRewardConfig\nReward config for Reward training\n\n\nAxolotlTrainingArguments\nTraining arguments for Causal trainer\n\n\nAxolotlTrainingMixins\nMixin class for the Axolotl training args.\n\n\n\n\n\ncore.training_args.AxolotlCPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n simpo_gamma=None,\n)\nCPO config for CPO training\n\n\n\ncore.training_args.AxolotlKTOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nKTO config for KTO training\n\n\n\ncore.training_args.AxolotlORPOConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nORPO config for ORPO training\n\n\n\ncore.training_args.AxolotlPRMConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nPRM config for PRM training\n\n\n\ncore.training_args.AxolotlRewardConfig(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nReward config for Reward training\n\n\n\ncore.training_args.AxolotlTrainingArguments(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nTraining arguments for Causal trainer\nThis code is duplicated due to HF TrainingArguments not setting output_dir with a\ndefault value so it can’t be used as a mixin.\n\n\n\ncore.training_args.AxolotlTrainingMixins(\n self,\n model_type=None,\n lr_quadratic_warmup=False,\n pretraining=False,\n sample_packing=False,\n sample_packing_sequentially=False,\n multipack_real_batches=False,\n eval_sample_packing=None,\n sample_packing_efficiency=1.0,\n sample_packing_bin_size=200,\n sample_packing_group_size=100000,\n max_seq_length=2048,\n relora_steps=None,\n relora_warmup_steps=None,\n relora_anneal_steps=None,\n relora_prune_ratio=0.9,\n bench_split='eval',\n bench_dataset='pharaouk/dharma-1/dharma_1_mini.json',\n do_bench_eval=False,\n do_causal_lm_eval=False,\n max_bench_samples=None,\n bench_source_max_len=2048,\n dataloader_prefetch_factor=None,\n cosine_min_lr_ratio=None,\n cosine_constant_lr_ratio=None,\n loraplus_lr_ratio=None,\n loraplus_lr_embedding=1e-06,\n embedding_lr_scale=None,\n lr_groups=None,\n embedding_lr=None,\n qlora=False,\n orpo_alpha=None,\n lisa_n_layers=None,\n lisa_step_interval=None,\n lisa_layers_attribute=None,\n curriculum_sampling=None,\n alternate_optimizer=None,\n alternate_lr_scheduler_type=None,\n chat_template=None,\n kd_ce_alpha=None,\n kd_alpha=1.0,\n kd_temperature=1.0,\n kd_zscore_base_temp=None,\n kd_top_k_before_softmax=None,\n adam_beta3=None,\n adam_epsilon2=None,\n image_size=None,\n image_resize_algorithm=None,\n)\nMixin class for the Axolotl training args." }, { - "objectID": "docs/api/cli.checks.html", - "href": "docs/api/cli.checks.html", - "title": "cli.checks", + "objectID": "docs/api/cli.cloud.modal_.html", + "href": "docs/api/cli.cloud.modal_.html", + "title": "cli.cloud.modal_", "section": "", - "text": "cli.checks\nVarious checks for Axolotl CLI.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncheck_accelerate_default_config\nLogs at warning level if no accelerate config file is found.\n\n\ncheck_user_token\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\ncli.checks.check_accelerate_default_config()\nLogs at warning level if no accelerate config file is found.\n\n\n\ncli.checks.check_user_token()\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nbool\nBoolean indicating successful check (i.e., HF_HUB_OFFLINE=1 or HF user info is retrieved).\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nLocalTokenNotFoundError\nIf HF user info can’t be retrieved." + "text": "cli.cloud.modal_\nModal Cloud support from CLI\n\n\n\n\n\nName\nDescription\n\n\n\n\nModalCloud\nModal Cloud implementation.\n\n\n\n\n\ncli.cloud.modal_.ModalCloud(self, config, app=None)\nModal Cloud implementation.\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nrun_cmd\nRun a command inside a folder, with Modal Volume reloading before and commit on success.\n\n\n\n\n\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\nRun a command inside a folder, with Modal Volume reloading before and commit on success." }, { - "objectID": "docs/api/cli.checks.html#functions", - "href": "docs/api/cli.checks.html#functions", - "title": "cli.checks", + "objectID": "docs/api/cli.cloud.modal_.html#classes", + "href": "docs/api/cli.cloud.modal_.html#classes", + "title": "cli.cloud.modal_", "section": "", - "text": "Name\nDescription\n\n\n\n\ncheck_accelerate_default_config\nLogs at warning level if no accelerate config file is found.\n\n\ncheck_user_token\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\ncli.checks.check_accelerate_default_config()\nLogs at warning level if no accelerate config file is found.\n\n\n\ncli.checks.check_user_token()\nChecks for HF user info. Check is skipped if HF_HUB_OFFLINE=1.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nbool\nBoolean indicating successful check (i.e., HF_HUB_OFFLINE=1 or HF user info is retrieved).\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nLocalTokenNotFoundError\nIf HF user info can’t be retrieved." + "text": "Name\nDescription\n\n\n\n\nModalCloud\nModal Cloud implementation.\n\n\n\n\n\ncli.cloud.modal_.ModalCloud(self, config, app=None)\nModal Cloud implementation." }, { - "objectID": "docs/api/monkeypatch.transformers_fa_utils.html", - "href": "docs/api/monkeypatch.transformers_fa_utils.html", - "title": "monkeypatch.transformers_fa_utils", + "objectID": "docs/api/cli.cloud.modal_.html#functions", + "href": "docs/api/cli.cloud.modal_.html#functions", + "title": "cli.cloud.modal_", "section": "", - "text": "monkeypatch.transformers_fa_utils\nsee https://github.com/huggingface/transformers/pull/35834\n\n\n\n\n\nName\nDescription\n\n\n\n\nfixed_fa_peft_integration_check\nPEFT usually casts the layer norms in float32 for training stability reasons\n\n\n\n\n\nmonkeypatch.transformers_fa_utils.fixed_fa_peft_integration_check(\n query,\n key,\n value,\n target_dtype=None,\n preferred_dtype=None,\n)\nPEFT usually casts the layer norms in float32 for training stability reasons\ntherefore the input hidden states gets silently casted in float32. Hence, we need\ncast them back in float16 / bfloat16 just to be sure everything works as expected.\nThis might slowdown training & inference so it is recommended to not cast the LayerNorms!\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nquery\ntorch.Tensor\nInput query states to be passed to Flash Attention API\nrequired\n\n\nkey\ntorch.Tensor\nInput key states to be passed to Flash Attention API\nrequired\n\n\nvalue\ntorch.Tensor\nInput value states to be passed to Flash Attention API\nrequired\n\n\ntarget_dtype\ntorch.dtype, optional\nThe dtype to convert the attention tensors to. Conversion can be ignored by not providing the target dtype.\nNone\n\n\npreferred_dtype\ntorch.dtype, optional\nThe preferred dtype to convert the attention tensors to regardless of the target dtype.\nNone" + "text": "Name\nDescription\n\n\n\n\nrun_cmd\nRun a command inside a folder, with Modal Volume reloading before and commit on success.\n\n\n\n\n\ncli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)\nRun a command inside a folder, with Modal Volume reloading before and commit on success." }, { - "objectID": "docs/api/monkeypatch.transformers_fa_utils.html#functions", - "href": "docs/api/monkeypatch.transformers_fa_utils.html#functions", - "title": "monkeypatch.transformers_fa_utils", + "objectID": "docs/api/monkeypatch.relora.html", + "href": "docs/api/monkeypatch.relora.html", + "title": "monkeypatch.relora", "section": "", - "text": "Name\nDescription\n\n\n\n\nfixed_fa_peft_integration_check\nPEFT usually casts the layer norms in float32 for training stability reasons\n\n\n\n\n\nmonkeypatch.transformers_fa_utils.fixed_fa_peft_integration_check(\n query,\n key,\n value,\n target_dtype=None,\n preferred_dtype=None,\n)\nPEFT usually casts the layer norms in float32 for training stability reasons\ntherefore the input hidden states gets silently casted in float32. Hence, we need\ncast them back in float16 / bfloat16 just to be sure everything works as expected.\nThis might slowdown training & inference so it is recommended to not cast the LayerNorms!\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nquery\ntorch.Tensor\nInput query states to be passed to Flash Attention API\nrequired\n\n\nkey\ntorch.Tensor\nInput key states to be passed to Flash Attention API\nrequired\n\n\nvalue\ntorch.Tensor\nInput value states to be passed to Flash Attention API\nrequired\n\n\ntarget_dtype\ntorch.dtype, optional\nThe dtype to convert the attention tensors to. Conversion can be ignored by not providing the target dtype.\nNone\n\n\npreferred_dtype\ntorch.dtype, optional\nThe preferred dtype to convert the attention tensors to regardless of the target dtype.\nNone" + "text": "monkeypatch.relora\nImplements the ReLoRA training procedure from https://arxiv.org/abs/2307.05695, minus the initial full fine-tune.\n\n\n\n\n\nName\nDescription\n\n\n\n\nReLoRACallback\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\nReLoRAScheduler\nWraps another scheduler to apply per-lora-restart learning rate warmups.\n\n\n\n\n\nmonkeypatch.relora.ReLoRACallback(self, cfg)\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\n\nmonkeypatch.relora.ReLoRAScheduler(\n self,\n optimizer,\n inner_schedule,\n relora_steps,\n warmup_steps,\n anneal_steps=1,\n min_lr_scale=0.001,\n)\nWraps another scheduler to apply per-lora-restart learning rate warmups." }, { - "objectID": "docs/api/prompt_strategies.llama2_chat.html", - "href": "docs/api/prompt_strategies.llama2_chat.html", - "title": "prompt_strategies.llama2_chat", + "objectID": "docs/api/monkeypatch.relora.html#classes", + "href": "docs/api/monkeypatch.relora.html#classes", + "title": "monkeypatch.relora", "section": "", - "text": "prompt_strategies.llama2_chat\nPrompt Strategy for finetuning Llama2 chat models\nsee also https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L213 for ma reference implementation.\nThis implementation is based on the Vicuna PR and the fastchat repo, see also:\nhttps://github.com/lm-sys/FastChat/blob/cdd7730686cb1bf9ae2b768ee171bdf7d1ff04f3/fastchat/conversation.py#L847\nUse dataset type: “llama2_chat” in conig.yml to use this prompt style.\nE.g. in the config.yml:\ndatasets:\n - path: llama_finetune_train.jsonl\n type: llama2_chat\nThe dataset itself should look like this:\n{'conversations':[{\"from\": \"human\", \"value\": \"Who are you?\"}, {\"from\": \"gpt\", \"value\": \"I am Vicuna\"},...]}\nin a jsonl file. The first message should be from the human, the second from gpt.\nFor a custom system message, the first “from” can be “system” (followed by alternating “human” and “gpt” turns).\nImportant: Don’t use “special_tokens:” in your config.yml if you are not sure what you are doing!\n\n\n\n\n\nName\nDescription\n\n\n\n\nLLama2ChatTokenizingStrategy\nTokenizing strategy for Llama2 prompts.\n\n\nLlama2ChatConversation\nA class that manages prompt templates and keeps all conversation history.\n\n\nLlama2ChatPrompter\nA prompter that generates prompts for Llama2 models.\n\n\n\n\n\nprompt_strategies.llama2_chat.LLama2ChatTokenizingStrategy(\n self,\n *args,\n **kwargs,\n)\nTokenizing strategy for Llama2 prompts.\nadapted from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation(\n self,\n name='llama2',\n system=\"[INST] <<SYS>>\\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\\n<</SYS>>\\n\\n\",\n roles=('[INST]', '[/INST]'),\n messages=list(),\n offset=0,\n)\nA class that manages prompt templates and keeps all conversation history.\ncopied from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n\n\n\n\n\nName\nDescription\n\n\n\n\nappend_message\nAppend a new message.\n\n\nget_prompt\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.append_message(\n role,\n message,\n)\nAppend a new message.\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.get_prompt()\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatPrompter()\nA prompter that generates prompts for Llama2 models." + "text": "Name\nDescription\n\n\n\n\nReLoRACallback\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\nReLoRAScheduler\nWraps another scheduler to apply per-lora-restart learning rate warmups.\n\n\n\n\n\nmonkeypatch.relora.ReLoRACallback(self, cfg)\nCallback to merge LoRA weights into the base model and save full-weight checkpoints\n\n\n\nmonkeypatch.relora.ReLoRAScheduler(\n self,\n optimizer,\n inner_schedule,\n relora_steps,\n warmup_steps,\n anneal_steps=1,\n min_lr_scale=0.001,\n)\nWraps another scheduler to apply per-lora-restart learning rate warmups." }, { - "objectID": "docs/api/prompt_strategies.llama2_chat.html#classes", - "href": "docs/api/prompt_strategies.llama2_chat.html#classes", - "title": "prompt_strategies.llama2_chat", + "objectID": "docs/api/core.trainers.base.html", + "href": "docs/api/core.trainers.base.html", + "title": "core.trainers.base", "section": "", - "text": "Name\nDescription\n\n\n\n\nLLama2ChatTokenizingStrategy\nTokenizing strategy for Llama2 prompts.\n\n\nLlama2ChatConversation\nA class that manages prompt templates and keeps all conversation history.\n\n\nLlama2ChatPrompter\nA prompter that generates prompts for Llama2 models.\n\n\n\n\n\nprompt_strategies.llama2_chat.LLama2ChatTokenizingStrategy(\n self,\n *args,\n **kwargs,\n)\nTokenizing strategy for Llama2 prompts.\nadapted from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation(\n self,\n name='llama2',\n system=\"[INST] <<SYS>>\\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\\n<</SYS>>\\n\\n\",\n roles=('[INST]', '[/INST]'),\n messages=list(),\n offset=0,\n)\nA class that manages prompt templates and keeps all conversation history.\ncopied from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py\n\n\n\n\n\nName\nDescription\n\n\n\n\nappend_message\nAppend a new message.\n\n\nget_prompt\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.append_message(\n role,\n message,\n)\nAppend a new message.\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatConversation.get_prompt()\nGet the prompt for generation.\n\n\n\n\n\nprompt_strategies.llama2_chat.Llama2ChatPrompter()\nA prompter that generates prompts for Llama2 models." + "text": "core.trainers.base\nModule for customized trainers\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlTrainer\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_eval_dataloader\nGet dataloader for evaluation\n\n\nget_train_dataloader\nGet dataloader for training\n\n\nlog\nLog logs on the various objects watching training, including stored metrics.\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.get_eval_dataloader(eval_dataset=None)\nGet dataloader for evaluation\n\n\n\ncore.trainers.base.AxolotlTrainer.get_train_dataloader()\nGet dataloader for training\n\n\n\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\nLog logs on the various objects watching training, including stored metrics.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nlogs\ndict[str, float]\nThe values to log.\nrequired\n\n\nstart_time\nfloat | None\nThe start of training.\nNone\n\n\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\nmodel on the Hub. Please refer to ~transformers.Trainer.push_to_hub for more details." }, { - "objectID": "docs/api/convert.html", - "href": "docs/api/convert.html", - "title": "convert", + "objectID": "docs/api/core.trainers.base.html#classes", + "href": "docs/api/core.trainers.base.html#classes", + "title": "core.trainers.base", "section": "", - "text": "convert\nModule containing File Reader, File Writer, Json Parser, and Jsonl Serializer classes\n\n\n\n\n\nName\nDescription\n\n\n\n\nFileReader\nReads a file and returns its contents as a string\n\n\nFileWriter\nWrites a string to a file\n\n\nJsonParser\nParses a string as JSON and returns the result\n\n\nJsonToJsonlConverter\nConverts a JSON file to JSONL\n\n\nJsonlSerializer\nSerializes a list of JSON objects into a JSONL string\n\n\nStdoutWriter\nWrites a string to stdout\n\n\n\n\n\nconvert.FileReader()\nReads a file and returns its contents as a string\n\n\n\nconvert.FileWriter(self, file_path)\nWrites a string to a file\n\n\n\nconvert.JsonParser()\nParses a string as JSON and returns the result\n\n\n\nconvert.JsonToJsonlConverter(\n self,\n file_reader,\n file_writer,\n json_parser,\n jsonl_serializer,\n)\nConverts a JSON file to JSONL\n\n\n\nconvert.JsonlSerializer()\nSerializes a list of JSON objects into a JSONL string\n\n\n\nconvert.StdoutWriter()\nWrites a string to stdout" + "text": "Name\nDescription\n\n\n\n\nAxolotlTrainer\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base Trainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_eval_dataloader\nGet dataloader for evaluation\n\n\nget_train_dataloader\nGet dataloader for training\n\n\nlog\nLog logs on the various objects watching training, including stored metrics.\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.get_eval_dataloader(eval_dataset=None)\nGet dataloader for evaluation\n\n\n\ncore.trainers.base.AxolotlTrainer.get_train_dataloader()\nGet dataloader for training\n\n\n\ncore.trainers.base.AxolotlTrainer.log(logs, start_time=None)\nLog logs on the various objects watching training, including stored metrics.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nlogs\ndict[str, float]\nThe values to log.\nrequired\n\n\nstart_time\nfloat | None\nThe start of training.\nNone\n\n\n\n\n\n\n\ncore.trainers.base.AxolotlTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing the\nmodel on the Hub. Please refer to ~transformers.Trainer.push_to_hub for more details." }, { - "objectID": "docs/api/convert.html#classes", - "href": "docs/api/convert.html#classes", - "title": "convert", + "objectID": "docs/api/kernels.swiglu.html", + "href": "docs/api/kernels.swiglu.html", + "title": "kernels.swiglu", "section": "", - "text": "Name\nDescription\n\n\n\n\nFileReader\nReads a file and returns its contents as a string\n\n\nFileWriter\nWrites a string to a file\n\n\nJsonParser\nParses a string as JSON and returns the result\n\n\nJsonToJsonlConverter\nConverts a JSON file to JSONL\n\n\nJsonlSerializer\nSerializes a list of JSON objects into a JSONL string\n\n\nStdoutWriter\nWrites a string to stdout\n\n\n\n\n\nconvert.FileReader()\nReads a file and returns its contents as a string\n\n\n\nconvert.FileWriter(self, file_path)\nWrites a string to a file\n\n\n\nconvert.JsonParser()\nParses a string as JSON and returns the result\n\n\n\nconvert.JsonToJsonlConverter(\n self,\n file_reader,\n file_writer,\n json_parser,\n jsonl_serializer,\n)\nConverts a JSON file to JSONL\n\n\n\nconvert.JsonlSerializer()\nSerializes a list of JSON objects into a JSONL string\n\n\n\nconvert.StdoutWriter()\nWrites a string to stdout" + "text": "kernels.swiglu\nModule for definition of SwiGLU Triton kernels.\nSee “GLU Variants Improve Transformer” (https://arxiv.org/abs/2002.05202).\nCredit to unsloth (https://unsloth.ai/) for inspiration for this implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nswiglu_backward\nSwiGLU backward pass using in-place operations.\n\n\nswiglu_forward\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\n\n\n\n\n\nkernels.swiglu.swiglu_backward(grad_output, gate, up)\nSwiGLU backward pass using in-place operations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to output, shape [batch, seq_len, hidden_dim].\nrequired\n\n\ngate\ntorch.Tensor\nGate tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple containing: - Forward pass output (h) - Gradient with respect to gate (df) - Gradient with respect to up-projection (de)\n\n\n\n\n\n\n\nkernels.swiglu.swiglu_forward(gate, up)\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\nx is the gate tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngate\ntorch.Tensor\nInput gate tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor of shape [batch, seq_len, hidden_dim]." }, { - "objectID": "docs/api/utils.schemas.datasets.html", - "href": "docs/api/utils.schemas.datasets.html", - "title": "utils.schemas.datasets", + "objectID": "docs/api/kernels.swiglu.html#functions", + "href": "docs/api/kernels.swiglu.html#functions", + "title": "kernels.swiglu", "section": "", - "text": "utils.schemas.datasets\nPydantic models for datasets-related configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nDPODataset\nDPO configuration subset\n\n\nKTODataset\nKTO configuration subset\n\n\nPretrainingDataset\nPretraining dataset configuration subset\n\n\nSFTDataset\nSFT configuration subset\n\n\nStepwiseSupervisedDataset\nStepwise supervised dataset configuration subset\n\n\nUserDefinedDPOType\nUser defined typing for DPO\n\n\nUserDefinedKTOType\nUser defined typing for KTO\n\n\nUserDefinedPrompterType\nStructure for user defined prompt types\n\n\n\n\n\nutils.schemas.datasets.DPODataset()\nDPO configuration subset\n\n\n\nutils.schemas.datasets.KTODataset()\nKTO configuration subset\n\n\n\nutils.schemas.datasets.PretrainingDataset()\nPretraining dataset configuration subset\n\n\n\nutils.schemas.datasets.SFTDataset()\nSFT configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nhandle_legacy_message_fields\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.SFTDataset.handle_legacy_message_fields(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.StepwiseSupervisedDataset()\nStepwise supervised dataset configuration subset\n\n\n\nutils.schemas.datasets.UserDefinedDPOType()\nUser defined typing for DPO\n\n\n\nutils.schemas.datasets.UserDefinedKTOType()\nUser defined typing for KTO\n\n\n\nutils.schemas.datasets.UserDefinedPrompterType()\nStructure for user defined prompt types" + "text": "Name\nDescription\n\n\n\n\nswiglu_backward\nSwiGLU backward pass using in-place operations.\n\n\nswiglu_forward\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\n\n\n\n\n\nkernels.swiglu.swiglu_backward(grad_output, gate, up)\nSwiGLU backward pass using in-place operations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to output, shape [batch, seq_len, hidden_dim].\nrequired\n\n\ngate\ntorch.Tensor\nGate tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor from forward pass, shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple containing: - Forward pass output (h) - Gradient with respect to gate (df) - Gradient with respect to up-projection (de)\n\n\n\n\n\n\n\nkernels.swiglu.swiglu_forward(gate, up)\nSwiGLU forward pass. Computes SwiGLU activation: x * sigmoid(x) * up, where\nx is the gate tensor.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ngate\ntorch.Tensor\nInput gate tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\nup\ntorch.Tensor\nUp-projection tensor of shape [batch, seq_len, hidden_dim].\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor of shape [batch, seq_len, hidden_dim]." }, { - "objectID": "docs/api/utils.schemas.datasets.html#classes", - "href": "docs/api/utils.schemas.datasets.html#classes", - "title": "utils.schemas.datasets", + "objectID": "docs/api/prompt_strategies.metharme.html", + "href": "docs/api/prompt_strategies.metharme.html", + "title": "prompt_strategies.metharme", "section": "", - "text": "Name\nDescription\n\n\n\n\nDPODataset\nDPO configuration subset\n\n\nKTODataset\nKTO configuration subset\n\n\nPretrainingDataset\nPretraining dataset configuration subset\n\n\nSFTDataset\nSFT configuration subset\n\n\nStepwiseSupervisedDataset\nStepwise supervised dataset configuration subset\n\n\nUserDefinedDPOType\nUser defined typing for DPO\n\n\nUserDefinedKTOType\nUser defined typing for KTO\n\n\nUserDefinedPrompterType\nStructure for user defined prompt types\n\n\n\n\n\nutils.schemas.datasets.DPODataset()\nDPO configuration subset\n\n\n\nutils.schemas.datasets.KTODataset()\nKTO configuration subset\n\n\n\nutils.schemas.datasets.PretrainingDataset()\nPretraining dataset configuration subset\n\n\n\nutils.schemas.datasets.SFTDataset()\nSFT configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nhandle_legacy_message_fields\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.SFTDataset.handle_legacy_message_fields(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.datasets.StepwiseSupervisedDataset()\nStepwise supervised dataset configuration subset\n\n\n\nutils.schemas.datasets.UserDefinedDPOType()\nUser defined typing for DPO\n\n\n\nutils.schemas.datasets.UserDefinedKTOType()\nUser defined typing for KTO\n\n\n\nutils.schemas.datasets.UserDefinedPrompterType()\nStructure for user defined prompt types" + "text": "prompt_strategies.metharme\nModule containing the MetharmenPromptTokenizingStrategy and MetharmePrompter class\n\n\n\n\n\nName\nDescription\n\n\n\n\nMetharmePromptTokenizingStrategy\nTokenizing strategy for the Metharme models\n\n\nMetharmePrompter\nPrompter for the Metharme models.\n\n\n\n\n\nprompt_strategies.metharme.MetharmePromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for the Metharme models\n\n\n\nprompt_strategies.metharme.MetharmePrompter(self, *args, **kwargs)\nPrompter for the Metharme models." }, { - "objectID": "docs/api/utils.schemas.enums.html", - "href": "docs/api/utils.schemas.enums.html", - "title": "utils.schemas.enums", + "objectID": "docs/api/prompt_strategies.metharme.html#classes", + "href": "docs/api/prompt_strategies.metharme.html#classes", + "title": "prompt_strategies.metharme", "section": "", - "text": "utils.schemas.enums\nEnums for Axolotl input config\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatTemplate\nChat templates configuration subset\n\n\nCustomSupportedOptimizers\nCustom supported optimizers\n\n\nRLType\nRL trainer type configuration subset\n\n\nRingAttnFunc\nEnum class for supported ring-flash-attn implementations\n\n\n\n\n\nutils.schemas.enums.ChatTemplate()\nChat templates configuration subset\n\n\n\nutils.schemas.enums.CustomSupportedOptimizers()\nCustom supported optimizers\n\n\n\nutils.schemas.enums.RLType()\nRL trainer type configuration subset\n\n\n\nutils.schemas.enums.RingAttnFunc()\nEnum class for supported ring-flash-attn implementations" + "text": "Name\nDescription\n\n\n\n\nMetharmePromptTokenizingStrategy\nTokenizing strategy for the Metharme models\n\n\nMetharmePrompter\nPrompter for the Metharme models.\n\n\n\n\n\nprompt_strategies.metharme.MetharmePromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for the Metharme models\n\n\n\nprompt_strategies.metharme.MetharmePrompter(self, *args, **kwargs)\nPrompter for the Metharme models." }, { - "objectID": "docs/api/utils.schemas.enums.html#classes", - "href": "docs/api/utils.schemas.enums.html#classes", - "title": "utils.schemas.enums", + "objectID": "docs/api/prompt_strategies.dpo.llama3.html", + "href": "docs/api/prompt_strategies.dpo.llama3.html", + "title": "prompt_strategies.dpo.llama3", "section": "", - "text": "Name\nDescription\n\n\n\n\nChatTemplate\nChat templates configuration subset\n\n\nCustomSupportedOptimizers\nCustom supported optimizers\n\n\nRLType\nRL trainer type configuration subset\n\n\nRingAttnFunc\nEnum class for supported ring-flash-attn implementations\n\n\n\n\n\nutils.schemas.enums.ChatTemplate()\nChat templates configuration subset\n\n\n\nutils.schemas.enums.CustomSupportedOptimizers()\nCustom supported optimizers\n\n\n\nutils.schemas.enums.RLType()\nRL trainer type configuration subset\n\n\n\nutils.schemas.enums.RingAttnFunc()\nEnum class for supported ring-flash-attn implementations" + "text": "prompt_strategies.dpo.llama3\nDPO strategies for llama-3 chat template\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.llama3.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" }, { - "objectID": "docs/api/cli.args.html", - "href": "docs/api/cli.args.html", - "title": "cli.args", + "objectID": "docs/api/prompt_strategies.dpo.llama3.html#functions", + "href": "docs/api/prompt_strategies.dpo.llama3.html#functions", + "title": "prompt_strategies.dpo.llama3", "section": "", - "text": "cli.args\nModule for axolotl CLI command arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nEvaluateCliArgs\nDataclass with CLI arguments for axolotl evaluate command.\n\n\nInferenceCliArgs\nDataclass with CLI arguments for axolotl inference command.\n\n\nPreprocessCliArgs\nDataclass with CLI arguments for axolotl preprocess command.\n\n\nTrainerCliArgs\nDataclass with CLI arguments for axolotl train command.\n\n\nVllmServeCliArgs\nDataclass with CLI arguments for axolotl vllm-serve command.\n\n\n\n\n\ncli.args.EvaluateCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n)\nDataclass with CLI arguments for axolotl evaluate command.\n\n\n\ncli.args.InferenceCliArgs(self, prompter=None)\nDataclass with CLI arguments for axolotl inference command.\n\n\n\ncli.args.PreprocessCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=1,\n prompter=None,\n download=True,\n iterable=None,\n)\nDataclass with CLI arguments for axolotl preprocess command.\n\n\n\ncli.args.TrainerCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n merge_lora=False,\n prompter=None,\n shard=False,\n main_process_port=None,\n num_processes=None,\n)\nDataclass with CLI arguments for axolotl train command.\n\n\n\ncli.args.VllmServeCliArgs(\n self,\n tensor_parallel_size=None,\n host=None,\n port=None,\n gpu_memory_utilization=None,\n dtype=None,\n max_model_len=None,\n enable_prefix_caching=None,\n serve_module=None,\n)\nDataclass with CLI arguments for axolotl vllm-serve command." + "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.llama3.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.llama3.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" }, { - "objectID": "docs/api/cli.args.html#classes", - "href": "docs/api/cli.args.html#classes", - "title": "cli.args", + "objectID": "docs/api/utils.gradient_checkpointing.offload_disk.html", + "href": "docs/api/utils.gradient_checkpointing.offload_disk.html", + "title": "utils.gradient_checkpointing.offload_disk", "section": "", - "text": "Name\nDescription\n\n\n\n\nEvaluateCliArgs\nDataclass with CLI arguments for axolotl evaluate command.\n\n\nInferenceCliArgs\nDataclass with CLI arguments for axolotl inference command.\n\n\nPreprocessCliArgs\nDataclass with CLI arguments for axolotl preprocess command.\n\n\nTrainerCliArgs\nDataclass with CLI arguments for axolotl train command.\n\n\nVllmServeCliArgs\nDataclass with CLI arguments for axolotl vllm-serve command.\n\n\n\n\n\ncli.args.EvaluateCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n)\nDataclass with CLI arguments for axolotl evaluate command.\n\n\n\ncli.args.InferenceCliArgs(self, prompter=None)\nDataclass with CLI arguments for axolotl inference command.\n\n\n\ncli.args.PreprocessCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=1,\n prompter=None,\n download=True,\n iterable=None,\n)\nDataclass with CLI arguments for axolotl preprocess command.\n\n\n\ncli.args.TrainerCliArgs(\n self,\n debug=False,\n debug_text_only=False,\n debug_num_examples=0,\n merge_lora=False,\n prompter=None,\n shard=False,\n main_process_port=None,\n num_processes=None,\n)\nDataclass with CLI arguments for axolotl train command.\n\n\n\ncli.args.VllmServeCliArgs(\n self,\n tensor_parallel_size=None,\n host=None,\n port=None,\n gpu_memory_utilization=None,\n dtype=None,\n max_model_len=None,\n enable_prefix_caching=None,\n serve_module=None,\n)\nDataclass with CLI arguments for axolotl vllm-serve command." + "text": "utils.gradient_checkpointing.offload_disk\nDISCO - DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\n\n\n\nName\nDescription\n\n\n\n\nDisco\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\nDiskOffloadManager\nManages offloaded tensors and handles prefetching in a separate thread.\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco()\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\nAdvanced disk-based gradient checkpointer with prefetching.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass that loads activations from disk with prefetching\n\n\nforward\nForward pass that offloads activations to disk asynchronously\n\n\nget_instance\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.backward(ctx, *grad_outputs)\nBackward pass that loads activations from disk with prefetching\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.forward(\n ctx,\n forward_function,\n hidden_states,\n *args,\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nForward pass that offloads activations to disk asynchronously\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.get_instance(\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager(\n self,\n prefetch_size=3,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nManages offloaded tensors and handles prefetching in a separate thread.\nIncludes synchronization to prevent race conditions.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncleanup\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\ncleanup_tensor\nClean up a specific tensor file after it’s been used\n\n\nload_tensor\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\nsave_tensor\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\ntrigger_prefetch\nTrigger prefetching of the next N tensors with proper synchronization\n\n\nwait_for_save\nWait for a tensor to be saved to disk\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup()\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup_tensor(\n file_path,\n)\nClean up a specific tensor file after it’s been used\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.load_tensor(\n file_path,\n target_device='cuda',\n)\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.save_tensor(tensor)\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.trigger_prefetch(\n n=None,\n)\nTrigger prefetching of the next N tensors with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.wait_for_save(\n file_path,\n timeout=None,\n)\nWait for a tensor to be saved to disk" }, { - "objectID": "docs/api/monkeypatch.llama_attn_hijack_xformers.html", - "href": "docs/api/monkeypatch.llama_attn_hijack_xformers.html", - "title": "monkeypatch.llama_attn_hijack_xformers", + "objectID": "docs/api/utils.gradient_checkpointing.offload_disk.html#classes", + "href": "docs/api/utils.gradient_checkpointing.offload_disk.html#classes", + "title": "utils.gradient_checkpointing.offload_disk", "section": "", - "text": "monkeypatch.llama_attn_hijack_xformers\nmonkeypatch.llama_attn_hijack_xformers\nDirectly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments" + "text": "Name\nDescription\n\n\n\n\nDisco\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\nDiskOffloadManager\nManages offloaded tensors and handles prefetching in a separate thread.\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco()\nDisco: DIsk-based Storage and Checkpointing with Optimized prefetching\nAdvanced disk-based gradient checkpointer with prefetching.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass that loads activations from disk with prefetching\n\n\nforward\nForward pass that offloads activations to disk asynchronously\n\n\nget_instance\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.backward(ctx, *grad_outputs)\nBackward pass that loads activations from disk with prefetching\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.forward(\n ctx,\n forward_function,\n hidden_states,\n *args,\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nForward pass that offloads activations to disk asynchronously\n\n\n\nutils.gradient_checkpointing.offload_disk.Disco.get_instance(\n prefetch_size=1,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nGet or create the offload manager\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager(\n self,\n prefetch_size=3,\n prefetch_to_gpu=True,\n save_workers=4,\n)\nManages offloaded tensors and handles prefetching in a separate thread.\nIncludes synchronization to prevent race conditions.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncleanup\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\ncleanup_tensor\nClean up a specific tensor file after it’s been used\n\n\nload_tensor\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\nsave_tensor\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\ntrigger_prefetch\nTrigger prefetching of the next N tensors with proper synchronization\n\n\nwait_for_save\nWait for a tensor to be saved to disk\n\n\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup()\nClean up all temp files and stop prefetch thread with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.cleanup_tensor(\n file_path,\n)\nClean up a specific tensor file after it’s been used\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.load_tensor(\n file_path,\n target_device='cuda',\n)\nLoad tensor from disk or prefetch cache with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.save_tensor(tensor)\nSave tensor to disk asynchronously and return file path with thread-safe operations\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.trigger_prefetch(\n n=None,\n)\nTrigger prefetching of the next N tensors with proper synchronization\n\n\n\nutils.gradient_checkpointing.offload_disk.DiskOffloadManager.wait_for_save(\n file_path,\n timeout=None,\n)\nWait for a tensor to be saved to disk" }, { - "objectID": "docs/api/train.html", - "href": "docs/api/train.html", - "title": "train", + "objectID": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html", + "href": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html", + "title": "monkeypatch.stablelm_attn_hijack_flash", "section": "", - "text": "train\nPrepare and train a model on a dataset. Can also infer from a model or merge lora\n\n\n\n\n\nName\nDescription\n\n\n\n\ncreate_model_card\nCreate a model card for the trained model if needed.\n\n\ndetermine_resume_checkpoint\nDetermine the checkpoint to resume from based on configuration.\n\n\nexecute_training\nExecute the training process with appropriate SDP kernel configurations.\n\n\nhandle_untrained_tokens_fix\nApply fixes for untrained tokens if configured.\n\n\nsave_initial_configs\nSave initial configurations before training.\n\n\nsave_trained_model\nSave the trained model according to configuration and training setup.\n\n\nsetup_model_and_tokenizer\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\nsetup_model_and_trainer\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\n\n\nsetup_model_card\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\nsetup_reference_model\nSet up the reference model for RL training if needed.\n\n\nsetup_signal_handler\nSet up signal handler for graceful termination.\n\n\ntrain\nTrain a model on the given dataset.\n\n\n\n\n\ntrain.create_model_card(cfg, trainer)\nCreate a model card for the trained model if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nTrainer\nThe trainer object with model card creation capabilities.\nrequired\n\n\n\n\n\n\n\ntrain.determine_resume_checkpoint(cfg)\nDetermine the checkpoint to resume from based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr | None\nPath to the checkpoint to resume from, or None if not resuming.\n\n\n\n\n\n\n\ntrain.execute_training(cfg, trainer, resume_from_checkpoint)\nExecute the training process with appropriate SDP kernel configurations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe configured trainer object.\nrequired\n\n\nresume_from_checkpoint\nstr | None\nPath to checkpoint to resume from, if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.handle_untrained_tokens_fix(\n cfg,\n model,\n tokenizer,\n train_dataset,\n safe_serialization,\n)\nApply fixes for untrained tokens if configured.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to apply fixes to.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer for token identification.\nrequired\n\n\ntrain_dataset\nDataset\nThe training dataset to use.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving.\nrequired\n\n\n\n\n\n\n\ntrain.save_initial_configs(cfg, tokenizer, model, peft_config, processor)\nSave initial configurations before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to save.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save configuration for.\nrequired\n\n\npeft_config\nPeftConfig | None\nThe PEFT configuration to save if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.save_trained_model(cfg, trainer, model, safe_serialization)\nSave the trained model according to configuration and training setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe trainer object.\nrequired\n\n\nmodel\nPreTrainedModel\nThe trained model to save.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization.\nrequired\n\n\n\n\n\n\n\ntrain.setup_model_and_tokenizer(cfg)\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple containing model, tokenizer, peft_config (if LoRA / QLoRA, else None), and processor (if multimodal, else None).\n\n\n\n\n\n\n\ntrain.setup_model_and_trainer(cfg, dataset_meta)\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\ntrainer setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[HFRLTrainerBuilder | HFCausalTrainerBuilder, PeftModel | PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple of: - Trainer (Causal or RLHF) - Model - Tokenizer - PEFT config - Processor\n\n\n\n\n\n\n\ntrain.setup_model_card(cfg)\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\ntrain.setup_reference_model(cfg, tokenizer)\nSet up the reference model for RL training if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to use for the reference model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nPreTrainedModel | None\nReference model if needed for RL training, None otherwise.\n\n\n\n\n\n\n\ntrain.setup_signal_handler(cfg, model, safe_serialization)\nSet up signal handler for graceful termination.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save on termination\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving\nrequired\n\n\n\n\n\n\n\ntrain.train(cfg, dataset_meta)\nTrain a model on the given dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PeftModel | PreTrainedModel, PreTrainedTokenizer, Trainer]\nTuple of (model, tokenizer) after training" + "text": "monkeypatch.stablelm_attn_hijack_flash\nPyTorch StableLM Epoch model.\n\n\n\n\n\nName\nDescription\n\n\n\n\nrepeat_kv\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\n\n\nrotate_half\nRotates half the hidden dims of the input.\n\n\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.repeat_kv(hidden_states, n_rep)\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\nnum_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.rotate_half(x)\nRotates half the hidden dims of the input." }, { - "objectID": "docs/api/train.html#functions", - "href": "docs/api/train.html#functions", - "title": "train", + "objectID": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html#functions", + "href": "docs/api/monkeypatch.stablelm_attn_hijack_flash.html#functions", + "title": "monkeypatch.stablelm_attn_hijack_flash", "section": "", - "text": "Name\nDescription\n\n\n\n\ncreate_model_card\nCreate a model card for the trained model if needed.\n\n\ndetermine_resume_checkpoint\nDetermine the checkpoint to resume from based on configuration.\n\n\nexecute_training\nExecute the training process with appropriate SDP kernel configurations.\n\n\nhandle_untrained_tokens_fix\nApply fixes for untrained tokens if configured.\n\n\nsave_initial_configs\nSave initial configurations before training.\n\n\nsave_trained_model\nSave the trained model according to configuration and training setup.\n\n\nsetup_model_and_tokenizer\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\nsetup_model_and_trainer\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\n\n\nsetup_model_card\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\nsetup_reference_model\nSet up the reference model for RL training if needed.\n\n\nsetup_signal_handler\nSet up signal handler for graceful termination.\n\n\ntrain\nTrain a model on the given dataset.\n\n\n\n\n\ntrain.create_model_card(cfg, trainer)\nCreate a model card for the trained model if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nTrainer\nThe trainer object with model card creation capabilities.\nrequired\n\n\n\n\n\n\n\ntrain.determine_resume_checkpoint(cfg)\nDetermine the checkpoint to resume from based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr | None\nPath to the checkpoint to resume from, or None if not resuming.\n\n\n\n\n\n\n\ntrain.execute_training(cfg, trainer, resume_from_checkpoint)\nExecute the training process with appropriate SDP kernel configurations.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe configured trainer object.\nrequired\n\n\nresume_from_checkpoint\nstr | None\nPath to checkpoint to resume from, if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.handle_untrained_tokens_fix(\n cfg,\n model,\n tokenizer,\n train_dataset,\n safe_serialization,\n)\nApply fixes for untrained tokens if configured.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to apply fixes to.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer for token identification.\nrequired\n\n\ntrain_dataset\nDataset\nThe training dataset to use.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving.\nrequired\n\n\n\n\n\n\n\ntrain.save_initial_configs(cfg, tokenizer, model, peft_config, processor)\nSave initial configurations before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to save.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save configuration for.\nrequired\n\n\npeft_config\nPeftConfig | None\nThe PEFT configuration to save if applicable.\nrequired\n\n\n\n\n\n\n\ntrain.save_trained_model(cfg, trainer, model, safe_serialization)\nSave the trained model according to configuration and training setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntrainer\nAny\nThe trainer object.\nrequired\n\n\nmodel\nPreTrainedModel\nThe trained model to save.\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization.\nrequired\n\n\n\n\n\n\n\ntrain.setup_model_and_tokenizer(cfg)\nLoad the tokenizer, processor (for multimodal models), and model based on configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple containing model, tokenizer, peft_config (if LoRA / QLoRA, else None), and processor (if multimodal, else None).\n\n\n\n\n\n\n\ntrain.setup_model_and_trainer(cfg, dataset_meta)\nLoad model, tokenizer, trainer, etc. Helper function to encapsulate the full\ntrainer setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters.\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[HFRLTrainerBuilder | HFCausalTrainerBuilder, PeftModel | PreTrainedModel, PreTrainedTokenizer, PeftConfig | None, ProcessorMixin | None]\nTuple of: - Trainer (Causal or RLHF) - Model - Tokenizer - PEFT config - Processor\n\n\n\n\n\n\n\ntrain.setup_model_card(cfg)\nSet up the Axolotl badge and add the Axolotl config to the model card if available.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\n\n\n\n\n\ntrain.setup_reference_model(cfg, tokenizer)\nSet up the reference model for RL training if needed.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ntokenizer\nPreTrainedTokenizer\nThe tokenizer to use for the reference model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nPreTrainedModel | None\nReference model if needed for RL training, None otherwise.\n\n\n\n\n\n\n\ntrain.setup_signal_handler(cfg, model, safe_serialization)\nSet up signal handler for graceful termination.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\nmodel\nPreTrainedModel\nThe model to save on termination\nrequired\n\n\nsafe_serialization\nbool\nWhether to use safe serialization when saving\nrequired\n\n\n\n\n\n\n\ntrain.train(cfg, dataset_meta)\nTrain a model on the given dataset.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration dictionary with training parameters\nrequired\n\n\ndataset_meta\nTrainDatasetMeta\nObject with training, validation datasets and metadata\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[PeftModel | PreTrainedModel, PreTrainedTokenizer, Trainer]\nTuple of (model, tokenizer) after training" + "text": "Name\nDescription\n\n\n\n\nrepeat_kv\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\n\n\nrotate_half\nRotates half the hidden dims of the input.\n\n\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.repeat_kv(hidden_states, n_rep)\nThis is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,\nnum_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)\n\n\n\nmonkeypatch.stablelm_attn_hijack_flash.rotate_half(x)\nRotates half the hidden dims of the input." }, { - "objectID": "docs/api/utils.gradient_checkpointing.offload_cpu.html", - "href": "docs/api/utils.gradient_checkpointing.offload_cpu.html", - "title": "utils.gradient_checkpointing.offload_cpu", + "objectID": "docs/api/prompt_strategies.dpo.chat_template.html", + "href": "docs/api/prompt_strategies.dpo.chat_template.html", + "title": "prompt_strategies.dpo.chat_template", "section": "", - "text": "utils.gradient_checkpointing.offload_cpu\nCPU offloaded checkpointing\n\n\n\n\n\nName\nDescription\n\n\n\n\nCPU_Offloaded_Gradient_Checkpointer\nSaves VRAM by smartly offloading to RAM.\n\n\n\n\n\nutils.gradient_checkpointing.offload_cpu.CPU_Offloaded_Gradient_Checkpointer()\nSaves VRAM by smartly offloading to RAM.\nTiny hit to performance, since we mask the movement via non blocking calls." + "text": "prompt_strategies.dpo.chat_template\nprompt_strategies.dpo.chat_template\nDPO prompt strategies for using tokenizer chat templates." }, { - "objectID": "docs/api/utils.gradient_checkpointing.offload_cpu.html#classes", - "href": "docs/api/utils.gradient_checkpointing.offload_cpu.html#classes", - "title": "utils.gradient_checkpointing.offload_cpu", + "objectID": "docs/api/models.mamba.modeling_mamba.html", + "href": "docs/api/models.mamba.modeling_mamba.html", + "title": "models.mamba.modeling_mamba", "section": "", - "text": "Name\nDescription\n\n\n\n\nCPU_Offloaded_Gradient_Checkpointer\nSaves VRAM by smartly offloading to RAM.\n\n\n\n\n\nutils.gradient_checkpointing.offload_cpu.CPU_Offloaded_Gradient_Checkpointer()\nSaves VRAM by smartly offloading to RAM.\nTiny hit to performance, since we mask the movement via non blocking calls." + "text": "models.mamba.modeling_mamba\nmodels.mamba.modeling_mamba" }, { - "objectID": "docs/api/prompt_strategies.messages.chat.html", - "href": "docs/api/prompt_strategies.messages.chat.html", - "title": "prompt_strategies.messages.chat", + "objectID": "docs/api/core.trainer_builder.html", + "href": "docs/api/core.trainer_builder.html", + "title": "core.trainer_builder", "section": "", - "text": "prompt_strategies.messages.chat\nChat dataset wrapping strategy for new internal messages representations\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatMessageDatasetWrappingStrategy\nChat dataset wrapping strategy for new internal messages representations\n\n\n\n\n\nprompt_strategies.messages.chat.ChatMessageDatasetWrappingStrategy(\n self,\n processor,\n message_transform=None,\n formatter=None,\n **kwargs,\n)\nChat dataset wrapping strategy for new internal messages representations" + "text": "core.trainer_builder\nBuilder for the training args and trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nHFCausalTrainerBuilder\nBuild the HuggingFace training args/trainer for causal models and reward modeling\n\n\nHFPPOTrainerBuilder\nHF Factory class for PPO Trainer\n\n\nHFRLTrainerBuilder\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\nTrainerBuilderBase\nBase class for trainer builder.\n\n\n\n\n\ncore.trainer_builder.HFCausalTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBuild the HuggingFace training args/trainer for causal models and reward modeling\nusing TRL.\n\n\n\ncore.trainer_builder.HFPPOTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nHF Factory class for PPO Trainer\n\n\n\ncore.trainer_builder.HFRLTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\n\ncore.trainer_builder.TrainerBuilderBase(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBase class for trainer builder.\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_post_trainer_create_callbacks\nCallbacks added after the trainer is created, usually b/c these need access to the trainer\n\n\n\n\n\ncore.trainer_builder.TrainerBuilderBase.get_post_trainer_create_callbacks(\n trainer,\n)\nCallbacks added after the trainer is created, usually b/c these need access to the trainer" }, { - "objectID": "docs/api/prompt_strategies.messages.chat.html#classes", - "href": "docs/api/prompt_strategies.messages.chat.html#classes", - "title": "prompt_strategies.messages.chat", + "objectID": "docs/api/core.trainer_builder.html#classes", + "href": "docs/api/core.trainer_builder.html#classes", + "title": "core.trainer_builder", "section": "", - "text": "Name\nDescription\n\n\n\n\nChatMessageDatasetWrappingStrategy\nChat dataset wrapping strategy for new internal messages representations\n\n\n\n\n\nprompt_strategies.messages.chat.ChatMessageDatasetWrappingStrategy(\n self,\n processor,\n message_transform=None,\n formatter=None,\n **kwargs,\n)\nChat dataset wrapping strategy for new internal messages representations" + "text": "Name\nDescription\n\n\n\n\nHFCausalTrainerBuilder\nBuild the HuggingFace training args/trainer for causal models and reward modeling\n\n\nHFPPOTrainerBuilder\nHF Factory class for PPO Trainer\n\n\nHFRLTrainerBuilder\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\nTrainerBuilderBase\nBase class for trainer builder.\n\n\n\n\n\ncore.trainer_builder.HFCausalTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBuild the HuggingFace training args/trainer for causal models and reward modeling\nusing TRL.\n\n\n\ncore.trainer_builder.HFPPOTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nHF Factory class for PPO Trainer\n\n\n\ncore.trainer_builder.HFRLTrainerBuilder(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nTrainer factory class for TRL-based RLHF trainers (e.g. DPO)\n\n\n\ncore.trainer_builder.TrainerBuilderBase(\n self,\n cfg,\n model,\n tokenizer,\n processor=None,\n)\nBase class for trainer builder.\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_post_trainer_create_callbacks\nCallbacks added after the trainer is created, usually b/c these need access to the trainer\n\n\n\n\n\ncore.trainer_builder.TrainerBuilderBase.get_post_trainer_create_callbacks(\n trainer,\n)\nCallbacks added after the trainer is created, usually b/c these need access to the trainer" }, { - "objectID": "docs/api/monkeypatch.llama_patch_multipack.html", - "href": "docs/api/monkeypatch.llama_patch_multipack.html", - "title": "monkeypatch.llama_patch_multipack", + "objectID": "docs/api/prompt_strategies.dpo.chatml.html", + "href": "docs/api/prompt_strategies.dpo.chatml.html", + "title": "prompt_strategies.dpo.chatml", "section": "", - "text": "monkeypatch.llama_patch_multipack\nmonkeypatch.llama_patch_multipack\nPatched LlamaAttention to use torch.nn.functional.scaled_dot_product_attention" + "text": "prompt_strategies.dpo.chatml\nDPO strategies for chatml\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.chatml.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.chatml.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" }, { - "objectID": "docs/api/index.html", - "href": "docs/api/index.html", - "title": "API Reference", + "objectID": "docs/api/prompt_strategies.dpo.chatml.html#functions", + "href": "docs/api/prompt_strategies.dpo.chatml.html#functions", + "title": "prompt_strategies.dpo.chatml", "section": "", - "text": "Core functionality for training\n\n\n\ntrain\nPrepare and train a model on a dataset. Can also infer from a model or merge lora\n\n\nevaluate\nModule for evaluating models.\n\n\ndatasets\nModule containing Dataset functionality\n\n\nconvert\nModule containing File Reader, File Writer, Json Parser, and Jsonl Serializer classes\n\n\nprompt_tokenizers\nModule containing PromptTokenizingStrategy and Prompter classes\n\n\nlogging_config\nCommon logging module for axolotl\n\n\ncore.trainer_builder\nBuilder for the training args and trainer\n\n\ncore.training_args\nextra axolotl specific training args\n\n\ncore.chat.messages\ninternal message representations of chat messages\n\n\ncore.chat.format.chatml\nChatML transformation functions for MessageContents\n\n\ncore.chat.format.llama3x\nLlama 3.x chat formatting functions for MessageContents\n\n\ncore.chat.format.shared\nshared functions for format transforms\n\n\ncore.datasets.chat\nchat dataset module\n\n\ncore.datasets.transforms.chat_builder\nThis module contains a function that builds a transform that takes a row from the dataset and converts it to a Chat.\n\n\n\n\n\n\nCommand-line interface\n\n\n\ncli.main\nClick CLI definitions for various axolotl commands.\n\n\ncli.train\nCLI to run training on a model.\n\n\ncli.evaluate\nCLI to run evaluation on a model.\n\n\ncli.args\nModule for axolotl CLI command arguments.\n\n\ncli.checks\nVarious checks for Axolotl CLI.\n\n\ncli.config\nConfiguration loading and processing.\n\n\ncli.inference\nCLI to run inference on a trained model.\n\n\ncli.merge_lora\nCLI to merge a trained LoRA into a base model.\n\n\ncli.merge_sharded_fsdp_weights\nCLI to merge sharded FSDP model checkpoints into a single combined checkpoint.\n\n\ncli.preprocess\nCLI to run preprocessing of a dataset.\n\n\ncli.sweeps\nUtilities for handling sweeps over configs for axolotl train CLI command\n\n\ncli.utils\nUtility methods for axolotl CLI.\n\n\ncli.vllm_serve\nCLI to start the vllm server for online RL\n\n\ncli.cloud.base\nbase class for cloud platforms from cli\n\n\ncli.cloud.modal_\nModal Cloud support from CLI\n\n\n\n\n\n\nTraining implementations\n\n\n\ncore.trainers.base\nModule for customized trainers\n\n\ncore.trainers.trl\nModule for TRL PPO trainer\n\n\ncore.trainers.mamba\nModule for mamba trainer\n\n\ncore.trainers.relora\nModule for ReLoRA trainer\n\n\ncore.trainers.dpo.trainer\nDPO trainer for axolotl\n\n\ncore.trainers.grpo.trainer\nAxolotl GRPO trainers (with and without sequence parallelism handling)\n\n\ncore.trainers.grpo.sampler\nRepeat random sampler (similar to the one implemented in\n\n\ncore.trainers.utils\nUtils for Axolotl trainers\n\n\n\n\n\n\nMixin classes for augmenting trainers\n\n\n\ncore.trainers.mixins.optimizer\nModule for Axolotl trainer optimizer mixin\n\n\ncore.trainers.mixins.rng_state_loader\nTemporary fix/override for bug in resume from checkpoint\n\n\ncore.trainers.mixins.scheduler\nModule for Axolotl trainer scheduler mixin\n\n\ncore.trainers.mixins.sequence_parallel\nModule for Axolotl trainer sequence parallelism mixin\n\n\n\n\n\n\nContext managers for altering trainer behaviors\n\n\n\nutils.ctx_managers.sequence_parallel\nModule for Axolotl trainer sequence parallelism manager and utilities\n\n\n\n\n\n\nPrompt formatting strategies\n\n\n\nprompt_strategies.base\nmodule for base dataset transform strategies\n\n\nprompt_strategies.chat_template\nHF Chat Templates prompt strategy\n\n\nprompt_strategies.alpaca_chat\nModule for Alpaca prompt strategy classes\n\n\nprompt_strategies.alpaca_instruct\nModule loading the AlpacaInstructPromptTokenizingStrategy class\n\n\nprompt_strategies.alpaca_w_system\nPrompt strategies loader for alpaca instruction datasets with system prompts\n\n\nprompt_strategies.user_defined\nUser Defined prompts with configuration from the YML config\n\n\nprompt_strategies.llama2_chat\nPrompt Strategy for finetuning Llama2 chat models\n\n\nprompt_strategies.completion\nBasic completion text\n\n\nprompt_strategies.input_output\nModule for plain input/output prompt pairs\n\n\nprompt_strategies.stepwise_supervised\nModule for stepwise datasets, typically including a prompt and reasoning traces,\n\n\nprompt_strategies.metharme\nModule containing the MetharmenPromptTokenizingStrategy and MetharmePrompter class\n\n\nprompt_strategies.orcamini\nPrompt Strategy for finetuning Orca Mini (v2) models\n\n\nprompt_strategies.pygmalion\nModule containing the PygmalionPromptTokenizingStrategy and PygmalionPrompter class\n\n\nprompt_strategies.messages.chat\nChat dataset wrapping strategy for new internal messages representations\n\n\nprompt_strategies.dpo.chat_template\nDPO prompt strategies for using tokenizer chat templates.\n\n\nprompt_strategies.dpo.llama3\nDPO strategies for llama-3 chat template\n\n\nprompt_strategies.dpo.chatml\nDPO strategies for chatml\n\n\nprompt_strategies.dpo.zephyr\nDPO strategies for zephyr\n\n\nprompt_strategies.dpo.user_defined\nUser-defined DPO strategies\n\n\nprompt_strategies.dpo.passthrough\nDPO prompt strategies passthrough/zero-processing strategy\n\n\nprompt_strategies.kto.llama3\nKTO strategies for llama-3 chat template\n\n\nprompt_strategies.kto.chatml\nKTO strategies for chatml\n\n\nprompt_strategies.kto.user_defined\nUser-defined KTO strategies\n\n\nprompt_strategies.orpo.chat_template\nchatml prompt tokenization strategy for ORPO\n\n\nprompt_strategies.bradley_terry.llama3\nchatml transforms for datasets with system, input, chosen, rejected to match llama3 chat template\n\n\n\n\n\n\nLow-level performance optimizations\n\n\n\nkernels.lora\nModule for definition of Low-Rank Adaptation (LoRA) Triton kernels.\n\n\nkernels.geglu\nModule for definition of GEGLU Triton kernels.\n\n\nkernels.swiglu\nModule for definition of SwiGLU Triton kernels.\n\n\nkernels.quantize\nDequantization utilities for bitsandbytes integration.\n\n\nkernels.utils\nUtilities for axolotl.kernels submodules.\n\n\n\n\n\n\nRuntime patches for model optimizations\n\n\n\nmonkeypatch.llama_attn_hijack_flash\nFlash attention monkey patch for llama model\n\n\nmonkeypatch.llama_attn_hijack_xformers\nDirectly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments\n\n\nmonkeypatch.mistral_attn_hijack_flash\nFlash attention monkey patch for mistral model\n\n\nmonkeypatch.multipack\nmultipack patching for v2 of sample packing\n\n\nmonkeypatch.relora\nImplements the ReLoRA training procedure from https://arxiv.org/abs/2307.05695, minus the initial full fine-tune.\n\n\nmonkeypatch.llama_expand_mask\nexpands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf\n\n\nmonkeypatch.lora_kernels\nModule for patching custom LoRA Triton kernels and torch.autograd functions.\n\n\nmonkeypatch.utils\nShared utils for the monkeypatches\n\n\nmonkeypatch.btlm_attn_hijack_flash\nFlash attention monkey patch for cerebras btlm model\n\n\nmonkeypatch.llama_patch_multipack\nPatched LlamaAttention to use torch.nn.functional.scaled_dot_product_attention\n\n\nmonkeypatch.stablelm_attn_hijack_flash\nPyTorch StableLM Epoch model.\n\n\nmonkeypatch.trainer_fsdp_optim\nfix for FSDP optimizer save in trainer w 4.47.0\n\n\nmonkeypatch.transformers_fa_utils\nsee https://github.com/huggingface/transformers/pull/35834\n\n\nmonkeypatch.unsloth_\nmodule for patching with unsloth optimizations\n\n\nmonkeypatch.attention.mllama\nMonkeypatch for Vision Llama for FA2 support\n\n\nmonkeypatch.data.batch_dataset_fetcher\nmonkey patches for the dataset fetcher to handle batches of packed indexes\n\n\nmonkeypatch.mixtral\nPatches to support multipack for mixtral\n\n\n\n\n\n\nUtility functions\n\n\n\nutils.models\nModule for models and model loading\n\n\nutils.tokenization\nModule for tokenization utilities\n\n\nutils.chat_templates\nThis module provides functionality for selecting chat templates based on user choices.\n\n\nutils.lora\nmodule to get the state dict of a merged lora model\n\n\nutils.lora_embeddings\nhelpers for lora embeddings\n\n\nutils.model_shard_quant\nmodule to handle loading model on cpu/meta device for FSDP\n\n\nutils.bench\nBenchmarking and measurement utilities\n\n\nutils.freeze\nmodule to freeze/unfreeze parameters by name\n\n\nutils.trainer\nModule containing the Trainer class and related functions\n\n\nutils.schedulers\nModule for custom LRScheduler class\n\n\nutils.distributed\nutility helpers for distributed checks\n\n\nutils.dict\nModule containing the DictDefault class\n\n\nutils.optimizers.adopt\nCopied from https://github.com/iShohei220/adopt\n\n\nutils.data.pretraining\ndata handling specific to pretraining\n\n\nutils.data.sft\ndata handling specific to SFT\n\n\nutils.gradient_checkpointing.offload_cpu\nCPU offloaded checkpointing\n\n\nutils.gradient_checkpointing.offload_disk\nDISCO - DIsk-based Storage and Checkpointing with Optimized prefetching\n\n\n\n\n\n\nPydantic data models for Axolotl config\n\n\n\nutils.schemas.config\nModule with Pydantic models for configuration.\n\n\nutils.schemas.model\nPydantic models for model input / output, etc. configuration\n\n\nutils.schemas.training\nPydantic models for training hyperparameters\n\n\nutils.schemas.datasets\nPydantic models for datasets-related configuration\n\n\nutils.schemas.peft\nPydantic models for PEFT-related configuration\n\n\nutils.schemas.trl\nPydantic models for TRL trainer configuration\n\n\nutils.schemas.multimodal\nPydantic models for multimodal-related configuration\n\n\nutils.schemas.integrations\nPydantic models for Axolotl integrations\n\n\nutils.schemas.enums\nEnums for Axolotl input config\n\n\nutils.schemas.utils\nUtilities for Axolotl Pydantic models\n\n\n\n\n\n\nThird-party integrations and extensions\n\n\n\nintegrations.base\nBase class for all plugins.\n\n\nintegrations.cut_cross_entropy.args\nModule for handling Cut Cross Entropy input arguments.\n\n\nintegrations.grokfast.optimizer\n\n\n\nintegrations.kd.trainer\nKD trainer\n\n\nintegrations.liger.args\nModule for handling LIGER input arguments.\n\n\nintegrations.lm_eval.args\nModule for handling lm eval harness input arguments.\n\n\nintegrations.spectrum.args\nModule for handling Spectrum input arguments.\n\n\n\n\n\n\nCommon utilities and shared functionality\n\n\n\ncommon.architectures\nCommon architecture specific constants\n\n\ncommon.const\nVarious shared constants\n\n\ncommon.datasets\nDataset loading utilities.\n\n\n\n\n\n\nCustom model implementations\n\n\n\nmodels.mamba.modeling_mamba\n\n\n\n\n\n\n\nData processing utilities\n\n\n\nutils.collators.core\nbasic shared collator constants\n\n\nutils.collators.batching\nData collators for axolotl to pad labels and position_ids for packed sequences\n\n\nutils.collators.mamba\ncollators for Mamba\n\n\nutils.collators.mm_chat\nCollators for multi-modal chat messages and packing\n\n\nutils.samplers.multipack\nMultipack Batch Sampler - An efficient batch sampler for packing variable-length sequences\n\n\n\n\n\n\nTraining callbacks\n\n\n\nutils.callbacks.perplexity\ncallback to calculate perplexity as an evaluation metric.\n\n\nutils.callbacks.profiler\nHF Trainer callback for creating pytorch profiling snapshots\n\n\nutils.callbacks.lisa\nmodule for LISA\n\n\nutils.callbacks.mlflow_\nMLFlow module for trainer callbacks\n\n\nutils.callbacks.comet_\nComet module for trainer callbacks" + "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/dpo-mix-7k conversations\n\n\nicr\nchatml transforms for datasets with system, input, chosen, rejected\n\n\nintel\nFor Intel Orca DPO Pairs\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.dpo.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/dpo-mix-7k conversations\n\n\n\nprompt_strategies.dpo.chatml.icr(cfg, **kwargs)\nchatml transforms for datasets with system, input, chosen, rejected\nex. https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs\n\n\n\nprompt_strategies.dpo.chatml.intel(cfg, **kwargs)\nFor Intel Orca DPO Pairs\n\n\n\nprompt_strategies.dpo.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations" }, { - "objectID": "docs/api/index.html#core", - "href": "docs/api/index.html#core", - "title": "API Reference", + "objectID": "docs/api/cli.main.html", + "href": "docs/api/cli.main.html", + "title": "cli.main", "section": "", - "text": "Core functionality for training\n\n\n\ntrain\nPrepare and train a model on a dataset. Can also infer from a model or merge lora\n\n\nevaluate\nModule for evaluating models.\n\n\ndatasets\nModule containing Dataset functionality\n\n\nconvert\nModule containing File Reader, File Writer, Json Parser, and Jsonl Serializer classes\n\n\nprompt_tokenizers\nModule containing PromptTokenizingStrategy and Prompter classes\n\n\nlogging_config\nCommon logging module for axolotl\n\n\ncore.trainer_builder\nBuilder for the training args and trainer\n\n\ncore.training_args\nextra axolotl specific training args\n\n\ncore.chat.messages\ninternal message representations of chat messages\n\n\ncore.chat.format.chatml\nChatML transformation functions for MessageContents\n\n\ncore.chat.format.llama3x\nLlama 3.x chat formatting functions for MessageContents\n\n\ncore.chat.format.shared\nshared functions for format transforms\n\n\ncore.datasets.chat\nchat dataset module\n\n\ncore.datasets.transforms.chat_builder\nThis module contains a function that builds a transform that takes a row from the dataset and converts it to a Chat." + "text": "cli.main\nClick CLI definitions for various axolotl commands.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncli\nAxolotl CLI - Train and fine-tune large language models\n\n\nevaluate\nEvaluate a model.\n\n\nfetch\nFetch example configs or other resources.\n\n\ninference\nRun inference with a trained model.\n\n\nmerge_lora\nMerge trained LoRA adapters into a base model.\n\n\nmerge_sharded_fsdp_weights\nMerge sharded FSDP model weights.\n\n\npreprocess\nPreprocess datasets before training.\n\n\ntrain\nTrain or fine-tune a model.\n\n\n\n\n\ncli.main.cli()\nAxolotl CLI - Train and fine-tune large language models\n\n\n\ncli.main.evaluate(config, accelerate, **kwargs)\nEvaluate a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.fetch(directory, dest)\nFetch example configs or other resources.\nAvailable directories:\n- examples: Example configuration files\n- deepspeed_configs: DeepSpeed configuration files\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndirectory\nstr\nOne of examples, deepspeed_configs.\nrequired\n\n\ndest\nOptional[str]\nOptional destination directory.\nrequired\n\n\n\n\n\n\n\ncli.main.inference(config, accelerate, gradio, **kwargs)\nRun inference with a trained model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ngradio\nbool\nWhether to use Gradio browser interface or command line for inference.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_lora(config, **kwargs)\nMerge trained LoRA adapters into a base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_sharded_fsdp_weights(config, accelerate, **kwargs)\nMerge sharded FSDP model weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.preprocess(config, cloud=None, **kwargs)\nPreprocess datasets before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.train(config, accelerate, cloud=None, sweep=None, **kwargs)\nTrain or fine-tune a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file\nNone\n\n\nsweep\nOptional[str]\nPath to YAML config for sweeping hyperparameters.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}" }, { - "objectID": "docs/api/index.html#cli", - "href": "docs/api/index.html#cli", - "title": "API Reference", + "objectID": "docs/api/cli.main.html#functions", + "href": "docs/api/cli.main.html#functions", + "title": "cli.main", "section": "", - "text": "Command-line interface\n\n\n\ncli.main\nClick CLI definitions for various axolotl commands.\n\n\ncli.train\nCLI to run training on a model.\n\n\ncli.evaluate\nCLI to run evaluation on a model.\n\n\ncli.args\nModule for axolotl CLI command arguments.\n\n\ncli.checks\nVarious checks for Axolotl CLI.\n\n\ncli.config\nConfiguration loading and processing.\n\n\ncli.inference\nCLI to run inference on a trained model.\n\n\ncli.merge_lora\nCLI to merge a trained LoRA into a base model.\n\n\ncli.merge_sharded_fsdp_weights\nCLI to merge sharded FSDP model checkpoints into a single combined checkpoint.\n\n\ncli.preprocess\nCLI to run preprocessing of a dataset.\n\n\ncli.sweeps\nUtilities for handling sweeps over configs for axolotl train CLI command\n\n\ncli.utils\nUtility methods for axolotl CLI.\n\n\ncli.vllm_serve\nCLI to start the vllm server for online RL\n\n\ncli.cloud.base\nbase class for cloud platforms from cli\n\n\ncli.cloud.modal_\nModal Cloud support from CLI" + "text": "Name\nDescription\n\n\n\n\ncli\nAxolotl CLI - Train and fine-tune large language models\n\n\nevaluate\nEvaluate a model.\n\n\nfetch\nFetch example configs or other resources.\n\n\ninference\nRun inference with a trained model.\n\n\nmerge_lora\nMerge trained LoRA adapters into a base model.\n\n\nmerge_sharded_fsdp_weights\nMerge sharded FSDP model weights.\n\n\npreprocess\nPreprocess datasets before training.\n\n\ntrain\nTrain or fine-tune a model.\n\n\n\n\n\ncli.main.cli()\nAxolotl CLI - Train and fine-tune large language models\n\n\n\ncli.main.evaluate(config, accelerate, **kwargs)\nEvaluate a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.fetch(directory, dest)\nFetch example configs or other resources.\nAvailable directories:\n- examples: Example configuration files\n- deepspeed_configs: DeepSpeed configuration files\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndirectory\nstr\nOne of examples, deepspeed_configs.\nrequired\n\n\ndest\nOptional[str]\nOptional destination directory.\nrequired\n\n\n\n\n\n\n\ncli.main.inference(config, accelerate, gradio, **kwargs)\nRun inference with a trained model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ngradio\nbool\nWhether to use Gradio browser interface or command line for inference.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_lora(config, **kwargs)\nMerge trained LoRA adapters into a base model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.merge_sharded_fsdp_weights(config, accelerate, **kwargs)\nMerge sharded FSDP model weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.preprocess(config, cloud=None, **kwargs)\nPreprocess datasets before training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}\n\n\n\n\n\n\n\ncli.main.train(config, accelerate, cloud=None, sweep=None, **kwargs)\nTrain or fine-tune a model.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr\nPath to axolotl config YAML file.\nrequired\n\n\naccelerate\nbool\nWhether to use accelerate launcher.\nrequired\n\n\ncloud\nOptional[str]\nPath to a cloud accelerator configuration file\nNone\n\n\nsweep\nOptional[str]\nPath to YAML config for sweeping hyperparameters.\nNone\n\n\nkwargs\n\nAdditional keyword arguments which correspond to CLI args or axolotl config options.\n{}" }, { - "objectID": "docs/api/index.html#trainers", - "href": "docs/api/index.html#trainers", - "title": "API Reference", + "objectID": "docs/api/utils.schemas.peft.html", + "href": "docs/api/utils.schemas.peft.html", + "title": "utils.schemas.peft", "section": "", - "text": "Training implementations\n\n\n\ncore.trainers.base\nModule for customized trainers\n\n\ncore.trainers.trl\nModule for TRL PPO trainer\n\n\ncore.trainers.mamba\nModule for mamba trainer\n\n\ncore.trainers.relora\nModule for ReLoRA trainer\n\n\ncore.trainers.dpo.trainer\nDPO trainer for axolotl\n\n\ncore.trainers.grpo.trainer\nAxolotl GRPO trainers (with and without sequence parallelism handling)\n\n\ncore.trainers.grpo.sampler\nRepeat random sampler (similar to the one implemented in\n\n\ncore.trainers.utils\nUtils for Axolotl trainers" + "text": "utils.schemas.peft\nPydantic models for PEFT-related configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nLoftQConfig\nLoftQ configuration subset\n\n\nLoraConfig\nPeft / LoRA configuration subset\n\n\nPeftConfig\npeftq configuration subset\n\n\nReLoRAConfig\nReLoRA configuration subset\n\n\n\n\n\nutils.schemas.peft.LoftQConfig()\nLoftQ configuration subset\n\n\n\nutils.schemas.peft.LoraConfig()\nPeft / LoRA configuration subset\n\n\n\nutils.schemas.peft.PeftConfig()\npeftq configuration subset\n\n\n\nutils.schemas.peft.ReLoRAConfig()\nReLoRA configuration subset" }, { - "objectID": "docs/api/index.html#mixins", - "href": "docs/api/index.html#mixins", - "title": "API Reference", + "objectID": "docs/api/utils.schemas.peft.html#classes", + "href": "docs/api/utils.schemas.peft.html#classes", + "title": "utils.schemas.peft", "section": "", - "text": "Mixin classes for augmenting trainers\n\n\n\ncore.trainers.mixins.optimizer\nModule for Axolotl trainer optimizer mixin\n\n\ncore.trainers.mixins.rng_state_loader\nTemporary fix/override for bug in resume from checkpoint\n\n\ncore.trainers.mixins.scheduler\nModule for Axolotl trainer scheduler mixin\n\n\ncore.trainers.mixins.sequence_parallel\nModule for Axolotl trainer sequence parallelism mixin" + "text": "Name\nDescription\n\n\n\n\nLoftQConfig\nLoftQ configuration subset\n\n\nLoraConfig\nPeft / LoRA configuration subset\n\n\nPeftConfig\npeftq configuration subset\n\n\nReLoRAConfig\nReLoRA configuration subset\n\n\n\n\n\nutils.schemas.peft.LoftQConfig()\nLoftQ configuration subset\n\n\n\nutils.schemas.peft.LoraConfig()\nPeft / LoRA configuration subset\n\n\n\nutils.schemas.peft.PeftConfig()\npeftq configuration subset\n\n\n\nutils.schemas.peft.ReLoRAConfig()\nReLoRA configuration subset" }, { - "objectID": "docs/api/index.html#context-managers", - "href": "docs/api/index.html#context-managers", - "title": "API Reference", + "objectID": "docs/api/monkeypatch.llama_expand_mask.html", + "href": "docs/api/monkeypatch.llama_expand_mask.html", + "title": "monkeypatch.llama_expand_mask", "section": "", - "text": "Context managers for altering trainer behaviors\n\n\n\nutils.ctx_managers.sequence_parallel\nModule for Axolotl trainer sequence parallelism manager and utilities" + "text": "monkeypatch.llama_expand_mask\nmonkeypatch.llama_expand_mask\nexpands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf" }, { - "objectID": "docs/api/index.html#prompt-strategies", - "href": "docs/api/index.html#prompt-strategies", - "title": "API Reference", + "objectID": "docs/api/core.trainers.grpo.trainer.html", + "href": "docs/api/core.trainers.grpo.trainer.html", + "title": "core.trainers.grpo.trainer", "section": "", - "text": "Prompt formatting strategies\n\n\n\nprompt_strategies.base\nmodule for base dataset transform strategies\n\n\nprompt_strategies.chat_template\nHF Chat Templates prompt strategy\n\n\nprompt_strategies.alpaca_chat\nModule for Alpaca prompt strategy classes\n\n\nprompt_strategies.alpaca_instruct\nModule loading the AlpacaInstructPromptTokenizingStrategy class\n\n\nprompt_strategies.alpaca_w_system\nPrompt strategies loader for alpaca instruction datasets with system prompts\n\n\nprompt_strategies.user_defined\nUser Defined prompts with configuration from the YML config\n\n\nprompt_strategies.llama2_chat\nPrompt Strategy for finetuning Llama2 chat models\n\n\nprompt_strategies.completion\nBasic completion text\n\n\nprompt_strategies.input_output\nModule for plain input/output prompt pairs\n\n\nprompt_strategies.stepwise_supervised\nModule for stepwise datasets, typically including a prompt and reasoning traces,\n\n\nprompt_strategies.metharme\nModule containing the MetharmenPromptTokenizingStrategy and MetharmePrompter class\n\n\nprompt_strategies.orcamini\nPrompt Strategy for finetuning Orca Mini (v2) models\n\n\nprompt_strategies.pygmalion\nModule containing the PygmalionPromptTokenizingStrategy and PygmalionPrompter class\n\n\nprompt_strategies.messages.chat\nChat dataset wrapping strategy for new internal messages representations\n\n\nprompt_strategies.dpo.chat_template\nDPO prompt strategies for using tokenizer chat templates.\n\n\nprompt_strategies.dpo.llama3\nDPO strategies for llama-3 chat template\n\n\nprompt_strategies.dpo.chatml\nDPO strategies for chatml\n\n\nprompt_strategies.dpo.zephyr\nDPO strategies for zephyr\n\n\nprompt_strategies.dpo.user_defined\nUser-defined DPO strategies\n\n\nprompt_strategies.dpo.passthrough\nDPO prompt strategies passthrough/zero-processing strategy\n\n\nprompt_strategies.kto.llama3\nKTO strategies for llama-3 chat template\n\n\nprompt_strategies.kto.chatml\nKTO strategies for chatml\n\n\nprompt_strategies.kto.user_defined\nUser-defined KTO strategies\n\n\nprompt_strategies.orpo.chat_template\nchatml prompt tokenization strategy for ORPO\n\n\nprompt_strategies.bradley_terry.llama3\nchatml transforms for datasets with system, input, chosen, rejected to match llama3 chat template" + "text": "core.trainers.grpo.trainer\nAxolotl GRPO trainers (with and without sequence parallelism handling)\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlGRPOSequenceParallelTrainer\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\nAxolotlGRPOTrainer\nExtend the base GRPOTrainer for axolotl helpers\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer(\n self,\n model,\n reward_funcs,\n args=None,\n train_dataset=None,\n eval_dataset=None,\n processing_class=None,\n reward_processing_classes=None,\n callbacks=None,\n optimizers=(None, None),\n peft_config=None,\n)\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_train_dataloader\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer.get_train_dataloader(\n)\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOTrainer()\nExtend the base GRPOTrainer for axolotl helpers" }, { - "objectID": "docs/api/index.html#kernels", - "href": "docs/api/index.html#kernels", - "title": "API Reference", + "objectID": "docs/api/core.trainers.grpo.trainer.html#classes", + "href": "docs/api/core.trainers.grpo.trainer.html#classes", + "title": "core.trainers.grpo.trainer", "section": "", - "text": "Low-level performance optimizations\n\n\n\nkernels.lora\nModule for definition of Low-Rank Adaptation (LoRA) Triton kernels.\n\n\nkernels.geglu\nModule for definition of GEGLU Triton kernels.\n\n\nkernels.swiglu\nModule for definition of SwiGLU Triton kernels.\n\n\nkernels.quantize\nDequantization utilities for bitsandbytes integration.\n\n\nkernels.utils\nUtilities for axolotl.kernels submodules." + "text": "Name\nDescription\n\n\n\n\nAxolotlGRPOSequenceParallelTrainer\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\nAxolotlGRPOTrainer\nExtend the base GRPOTrainer for axolotl helpers\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer(\n self,\n model,\n reward_funcs,\n args=None,\n train_dataset=None,\n eval_dataset=None,\n processing_class=None,\n reward_processing_classes=None,\n callbacks=None,\n optimizers=(None, None),\n peft_config=None,\n)\nExtend the base GRPOTrainer for sequence parallelism handling\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_train_dataloader\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOSequenceParallelTrainer.get_train_dataloader(\n)\nGet dataloader for training\n\n\n\n\n\ncore.trainers.grpo.trainer.AxolotlGRPOTrainer()\nExtend the base GRPOTrainer for axolotl helpers" }, { - "objectID": "docs/api/index.html#monkey-patches", - "href": "docs/api/index.html#monkey-patches", - "title": "API Reference", + "objectID": "docs/api/integrations.spectrum.args.html", + "href": "docs/api/integrations.spectrum.args.html", + "title": "integrations.spectrum.args", "section": "", - "text": "Runtime patches for model optimizations\n\n\n\nmonkeypatch.llama_attn_hijack_flash\nFlash attention monkey patch for llama model\n\n\nmonkeypatch.llama_attn_hijack_xformers\nDirectly copied the code from https://raw.githubusercontent.com/oobabooga/text-generation-webui/main/modules/llama_attn_hijack.py and made some adjustments\n\n\nmonkeypatch.mistral_attn_hijack_flash\nFlash attention monkey patch for mistral model\n\n\nmonkeypatch.multipack\nmultipack patching for v2 of sample packing\n\n\nmonkeypatch.relora\nImplements the ReLoRA training procedure from https://arxiv.org/abs/2307.05695, minus the initial full fine-tune.\n\n\nmonkeypatch.llama_expand_mask\nexpands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf\n\n\nmonkeypatch.lora_kernels\nModule for patching custom LoRA Triton kernels and torch.autograd functions.\n\n\nmonkeypatch.utils\nShared utils for the monkeypatches\n\n\nmonkeypatch.btlm_attn_hijack_flash\nFlash attention monkey patch for cerebras btlm model\n\n\nmonkeypatch.llama_patch_multipack\nPatched LlamaAttention to use torch.nn.functional.scaled_dot_product_attention\n\n\nmonkeypatch.stablelm_attn_hijack_flash\nPyTorch StableLM Epoch model.\n\n\nmonkeypatch.trainer_fsdp_optim\nfix for FSDP optimizer save in trainer w 4.47.0\n\n\nmonkeypatch.transformers_fa_utils\nsee https://github.com/huggingface/transformers/pull/35834\n\n\nmonkeypatch.unsloth_\nmodule for patching with unsloth optimizations\n\n\nmonkeypatch.attention.mllama\nMonkeypatch for Vision Llama for FA2 support\n\n\nmonkeypatch.data.batch_dataset_fetcher\nmonkey patches for the dataset fetcher to handle batches of packed indexes\n\n\nmonkeypatch.mixtral\nPatches to support multipack for mixtral" + "text": "integrations.spectrum.args\nModule for handling Spectrum input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nSpectrumArgs\nInput args for Spectrum.\n\n\n\n\n\nintegrations.spectrum.args.SpectrumArgs()\nInput args for Spectrum." }, { - "objectID": "docs/api/index.html#utils", - "href": "docs/api/index.html#utils", - "title": "API Reference", + "objectID": "docs/api/integrations.spectrum.args.html#classes", + "href": "docs/api/integrations.spectrum.args.html#classes", + "title": "integrations.spectrum.args", "section": "", - "text": "Utility functions\n\n\n\nutils.models\nModule for models and model loading\n\n\nutils.tokenization\nModule for tokenization utilities\n\n\nutils.chat_templates\nThis module provides functionality for selecting chat templates based on user choices.\n\n\nutils.lora\nmodule to get the state dict of a merged lora model\n\n\nutils.lora_embeddings\nhelpers for lora embeddings\n\n\nutils.model_shard_quant\nmodule to handle loading model on cpu/meta device for FSDP\n\n\nutils.bench\nBenchmarking and measurement utilities\n\n\nutils.freeze\nmodule to freeze/unfreeze parameters by name\n\n\nutils.trainer\nModule containing the Trainer class and related functions\n\n\nutils.schedulers\nModule for custom LRScheduler class\n\n\nutils.distributed\nutility helpers for distributed checks\n\n\nutils.dict\nModule containing the DictDefault class\n\n\nutils.optimizers.adopt\nCopied from https://github.com/iShohei220/adopt\n\n\nutils.data.pretraining\ndata handling specific to pretraining\n\n\nutils.data.sft\ndata handling specific to SFT\n\n\nutils.gradient_checkpointing.offload_cpu\nCPU offloaded checkpointing\n\n\nutils.gradient_checkpointing.offload_disk\nDISCO - DIsk-based Storage and Checkpointing with Optimized prefetching" + "text": "Name\nDescription\n\n\n\n\nSpectrumArgs\nInput args for Spectrum.\n\n\n\n\n\nintegrations.spectrum.args.SpectrumArgs()\nInput args for Spectrum." }, { - "objectID": "docs/api/index.html#schemas", - "href": "docs/api/index.html#schemas", - "title": "API Reference", + "objectID": "docs/api/core.trainers.relora.html", + "href": "docs/api/core.trainers.relora.html", + "title": "core.trainers.relora", "section": "", - "text": "Pydantic data models for Axolotl config\n\n\n\nutils.schemas.config\nModule with Pydantic models for configuration.\n\n\nutils.schemas.model\nPydantic models for model input / output, etc. configuration\n\n\nutils.schemas.training\nPydantic models for training hyperparameters\n\n\nutils.schemas.datasets\nPydantic models for datasets-related configuration\n\n\nutils.schemas.peft\nPydantic models for PEFT-related configuration\n\n\nutils.schemas.trl\nPydantic models for TRL trainer configuration\n\n\nutils.schemas.multimodal\nPydantic models for multimodal-related configuration\n\n\nutils.schemas.integrations\nPydantic models for Axolotl integrations\n\n\nutils.schemas.enums\nEnums for Axolotl input config\n\n\nutils.schemas.utils\nUtilities for Axolotl Pydantic models" + "text": "core.trainers.relora\nModule for ReLoRA trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nReLoRATrainer\nTrainer subclass that uses the OneCycleLR scheduler\n\n\n\n\n\ncore.trainers.relora.ReLoRATrainer(self, *args, **kwargs)\nTrainer subclass that uses the OneCycleLR scheduler" }, { - "objectID": "docs/api/index.html#integrations", - "href": "docs/api/index.html#integrations", - "title": "API Reference", + "objectID": "docs/api/core.trainers.relora.html#classes", + "href": "docs/api/core.trainers.relora.html#classes", + "title": "core.trainers.relora", "section": "", - "text": "Third-party integrations and extensions\n\n\n\nintegrations.base\nBase class for all plugins.\n\n\nintegrations.cut_cross_entropy.args\nModule for handling Cut Cross Entropy input arguments.\n\n\nintegrations.grokfast.optimizer\n\n\n\nintegrations.kd.trainer\nKD trainer\n\n\nintegrations.liger.args\nModule for handling LIGER input arguments.\n\n\nintegrations.lm_eval.args\nModule for handling lm eval harness input arguments.\n\n\nintegrations.spectrum.args\nModule for handling Spectrum input arguments." + "text": "Name\nDescription\n\n\n\n\nReLoRATrainer\nTrainer subclass that uses the OneCycleLR scheduler\n\n\n\n\n\ncore.trainers.relora.ReLoRATrainer(self, *args, **kwargs)\nTrainer subclass that uses the OneCycleLR scheduler" }, { - "objectID": "docs/api/index.html#common", - "href": "docs/api/index.html#common", - "title": "API Reference", + "objectID": "docs/api/utils.bench.html", + "href": "docs/api/utils.bench.html", + "title": "utils.bench", "section": "", - "text": "Common utilities and shared functionality\n\n\n\ncommon.architectures\nCommon architecture specific constants\n\n\ncommon.const\nVarious shared constants\n\n\ncommon.datasets\nDataset loading utilities." + "text": "utils.bench\nBenchmarking and measurement utilities\n\n\n\n\n\nName\nDescription\n\n\n\n\ncheck_cuda_device\nwraps a function and returns the default value instead of running the\n\n\n\n\n\nutils.bench.check_cuda_device(default_value)\nwraps a function and returns the default value instead of running the\nwrapped function if cuda isn’t available or the device is auto\n:param default_value:\n:return:" }, { - "objectID": "docs/api/index.html#models", - "href": "docs/api/index.html#models", - "title": "API Reference", + "objectID": "docs/api/utils.bench.html#functions", + "href": "docs/api/utils.bench.html#functions", + "title": "utils.bench", "section": "", - "text": "Custom model implementations\n\n\n\nmodels.mamba.modeling_mamba" + "text": "Name\nDescription\n\n\n\n\ncheck_cuda_device\nwraps a function and returns the default value instead of running the\n\n\n\n\n\nutils.bench.check_cuda_device(default_value)\nwraps a function and returns the default value instead of running the\nwrapped function if cuda isn’t available or the device is auto\n:param default_value:\n:return:" }, { - "objectID": "docs/api/index.html#data-processing", - "href": "docs/api/index.html#data-processing", - "title": "API Reference", + "objectID": "docs/api/prompt_strategies.input_output.html", + "href": "docs/api/prompt_strategies.input_output.html", + "title": "prompt_strategies.input_output", "section": "", - "text": "Data processing utilities\n\n\n\nutils.collators.core\nbasic shared collator constants\n\n\nutils.collators.batching\nData collators for axolotl to pad labels and position_ids for packed sequences\n\n\nutils.collators.mamba\ncollators for Mamba\n\n\nutils.collators.mm_chat\nCollators for multi-modal chat messages and packing\n\n\nutils.samplers.multipack\nMultipack Batch Sampler - An efficient batch sampler for packing variable-length sequences" + "text": "prompt_strategies.input_output\nModule for plain input/output prompt pairs\n\n\n\n\n\nName\nDescription\n\n\n\n\nRawInputOutputPrompter\nprompter for raw i/o data\n\n\nRawInputOutputStrategy\nPrompt Strategy class for input/output pairs\n\n\n\n\n\nprompt_strategies.input_output.RawInputOutputPrompter()\nprompter for raw i/o data\n\n\n\nprompt_strategies.input_output.RawInputOutputStrategy(\n self,\n *args,\n eos_token=None,\n **kwargs,\n)\nPrompt Strategy class for input/output pairs" }, { - "objectID": "docs/api/index.html#callbacks", - "href": "docs/api/index.html#callbacks", - "title": "API Reference", + "objectID": "docs/api/prompt_strategies.input_output.html#classes", + "href": "docs/api/prompt_strategies.input_output.html#classes", + "title": "prompt_strategies.input_output", "section": "", - "text": "Training callbacks\n\n\n\nutils.callbacks.perplexity\ncallback to calculate perplexity as an evaluation metric.\n\n\nutils.callbacks.profiler\nHF Trainer callback for creating pytorch profiling snapshots\n\n\nutils.callbacks.lisa\nmodule for LISA\n\n\nutils.callbacks.mlflow_\nMLFlow module for trainer callbacks\n\n\nutils.callbacks.comet_\nComet module for trainer callbacks" + "text": "Name\nDescription\n\n\n\n\nRawInputOutputPrompter\nprompter for raw i/o data\n\n\nRawInputOutputStrategy\nPrompt Strategy class for input/output pairs\n\n\n\n\n\nprompt_strategies.input_output.RawInputOutputPrompter()\nprompter for raw i/o data\n\n\n\nprompt_strategies.input_output.RawInputOutputStrategy(\n self,\n *args,\n eos_token=None,\n **kwargs,\n)\nPrompt Strategy class for input/output pairs" }, { - "objectID": "docs/api/cli.preprocess.html", - "href": "docs/api/cli.preprocess.html", - "title": "cli.preprocess", + "objectID": "docs/api/cli.inference.html", + "href": "docs/api/cli.inference.html", + "title": "cli.inference", "section": "", - "text": "cli.preprocess\nCLI to run preprocessing of a dataset.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\ndo_preprocess\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\ncli.preprocess.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.preprocess.do_preprocess(cfg, cli_args)\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs\nPreprocessing-specific CLI arguments.\nrequired" + "text": "cli.inference\nCLI to run inference on a trained model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\ndo_inference\nRuns inference on the command line in a loop. User input is accepted, a chat template\n\n\ndo_inference_gradio\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n\n\nget_multi_line_input\nGets multi-line input from terminal.\n\n\n\n\n\ncli.inference.do_cli(config=Path('examples/'), gradio=False, **kwargs)\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.inference.do_inference(cfg, cli_args)\nRuns inference on the command line in a loop. User input is accepted, a chat template\nis (optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.do_inference_gradio(cfg, cli_args)\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n(optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.get_multi_line_input()\nGets multi-line input from terminal.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPossibly multi-line, possibly empty stdin input as a string." }, { - "objectID": "docs/api/cli.preprocess.html#functions", - "href": "docs/api/cli.preprocess.html#functions", - "title": "cli.preprocess", + "objectID": "docs/api/cli.inference.html#functions", + "href": "docs/api/cli.inference.html#functions", + "title": "cli.inference", "section": "", - "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\ndo_preprocess\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\ncli.preprocess.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_preprocess.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.preprocess.do_preprocess(cfg, cli_args)\nPreprocesses dataset specified in axolotl config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs\nPreprocessing-specific CLI arguments.\nrequired" + "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\ndo_inference\nRuns inference on the command line in a loop. User input is accepted, a chat template\n\n\ndo_inference_gradio\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n\n\nget_multi_line_input\nGets multi-line input from terminal.\n\n\n\n\n\ncli.inference.do_cli(config=Path('examples/'), gradio=False, **kwargs)\nParses axolotl config, CLI args, and calls do_inference or do_inference_gradio.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.inference.do_inference(cfg, cli_args)\nRuns inference on the command line in a loop. User input is accepted, a chat template\nis (optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.do_inference_gradio(cfg, cli_args)\nRuns inference in a Gradio interface. User input is accepted, a chat template is\n(optionally) applied, and the model specified in the axolotl config is used to\ngenerate completions according to a default generation config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nInferenceCliArgs\nInference-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\ncli.inference.get_multi_line_input()\nGets multi-line input from terminal.\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPossibly multi-line, possibly empty stdin input as a string." }, { - "objectID": "docs/api/utils.freeze.html", - "href": "docs/api/utils.freeze.html", - "title": "utils.freeze", + "objectID": "docs/api/core.trainers.dpo.trainer.html", + "href": "docs/api/core.trainers.dpo.trainer.html", + "title": "core.trainers.dpo.trainer", "section": "", - "text": "utils.freeze\nmodule to freeze/unfreeze parameters by name\n\n\n\n\n\nName\nDescription\n\n\n\n\nLayerNamePattern\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nutils.freeze.LayerNamePattern(self, pattern)\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nName\nDescription\n\n\n\n\nmatch\nChecks if the given layer name matches the regex pattern.\n\n\n\n\n\nutils.freeze.LayerNamePattern.match(name)\nChecks if the given layer name matches the regex pattern.\nParameters:\n- name (str): The layer name to check.\nReturns:\n- bool: True if the layer name matches the pattern, False otherwise.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nfreeze_layers_except\nFreezes all layers of the given model except for the layers that match given regex patterns.\n\n\n\n\n\nutils.freeze.freeze_layers_except(model, regex_patterns)\nFreezes all layers of the given model except for the layers that match given regex patterns.\nPeriods in the patterns are treated as literal periods, not as wildcard characters.\nParameters:\n- model (nn.Module): The PyTorch model to be modified.\n- regex_patterns (list of str): List of regex patterns to match layer names to keep unfrozen.\nNote that you cannot use a dot as a wildcard character in the patterns since it is reserved for separating layer names.\nAlso, to match the entire layer name, the pattern should start with “^” and end with “\\(\", otherwise it will match any part of the layer name.\n The range pattern part is optional and it is not compiled as a regex pattern which means you must put \"\\)” before the range pattern if you want to match the entire layer name.\nE.g., [“^model.embed_tokens.weight\\([:32000]\", \"layers.2[0-9]+.block_sparse_moe.gate.[a-z]+\\)”]\nReturns:\nNone; the model is modified in place." + "text": "core.trainers.dpo.trainer\nDPO trainer for axolotl\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlDPOTrainer\nExtend the base DPOTrainer for axolotl helpers.\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer(\n self,\n *args,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base DPOTrainer for axolotl helpers.\n\n\n\n\n\nName\nDescription\n\n\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing\nthe model on the Hub. Please refer to ~transformers.Trainer.push_to_hub\nfor more details." }, { - "objectID": "docs/api/utils.freeze.html#classes", - "href": "docs/api/utils.freeze.html#classes", - "title": "utils.freeze", + "objectID": "docs/api/core.trainers.dpo.trainer.html#classes", + "href": "docs/api/core.trainers.dpo.trainer.html#classes", + "title": "core.trainers.dpo.trainer", "section": "", - "text": "Name\nDescription\n\n\n\n\nLayerNamePattern\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nutils.freeze.LayerNamePattern(self, pattern)\nRepresents a regex pattern for layer names, potentially including a parameter index range.\n\n\n\n\n\nName\nDescription\n\n\n\n\nmatch\nChecks if the given layer name matches the regex pattern.\n\n\n\n\n\nutils.freeze.LayerNamePattern.match(name)\nChecks if the given layer name matches the regex pattern.\nParameters:\n- name (str): The layer name to check.\nReturns:\n- bool: True if the layer name matches the pattern, False otherwise." + "text": "Name\nDescription\n\n\n\n\nAxolotlDPOTrainer\nExtend the base DPOTrainer for axolotl helpers.\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer(\n self,\n *args,\n dataset_tags=None,\n **kwargs,\n)\nExtend the base DPOTrainer for axolotl helpers.\n\n\n\n\n\nName\nDescription\n\n\n\n\npush_to_hub\nOverwrite the push_to_hub method in order to force-add the tags when pushing\n\n\n\n\n\ncore.trainers.dpo.trainer.AxolotlDPOTrainer.push_to_hub(*args, **kwargs)\nOverwrite the push_to_hub method in order to force-add the tags when pushing\nthe model on the Hub. Please refer to ~transformers.Trainer.push_to_hub\nfor more details." }, { - "objectID": "docs/api/utils.freeze.html#functions", - "href": "docs/api/utils.freeze.html#functions", - "title": "utils.freeze", + "objectID": "docs/api/integrations.grokfast.optimizer.html", + "href": "docs/api/integrations.grokfast.optimizer.html", + "title": "integrations.grokfast.optimizer", "section": "", - "text": "Name\nDescription\n\n\n\n\nfreeze_layers_except\nFreezes all layers of the given model except for the layers that match given regex patterns.\n\n\n\n\n\nutils.freeze.freeze_layers_except(model, regex_patterns)\nFreezes all layers of the given model except for the layers that match given regex patterns.\nPeriods in the patterns are treated as literal periods, not as wildcard characters.\nParameters:\n- model (nn.Module): The PyTorch model to be modified.\n- regex_patterns (list of str): List of regex patterns to match layer names to keep unfrozen.\nNote that you cannot use a dot as a wildcard character in the patterns since it is reserved for separating layer names.\nAlso, to match the entire layer name, the pattern should start with “^” and end with “\\(\", otherwise it will match any part of the layer name.\n The range pattern part is optional and it is not compiled as a regex pattern which means you must put \"\\)” before the range pattern if you want to match the entire layer name.\nE.g., [“^model.embed_tokens.weight\\([:32000]\", \"layers.2[0-9]+.block_sparse_moe.gate.[a-z]+\\)”]\nReturns:\nNone; the model is modified in place." + "text": "integrations.grokfast.optimizer\nintegrations.grokfast.optimizer" }, { - "objectID": "docs/api/utils.data.sft.html", - "href": "docs/api/utils.data.sft.html", - "title": "utils.data.sft", + "objectID": "docs/api/core.trainers.mamba.html", + "href": "docs/api/core.trainers.mamba.html", + "title": "core.trainers.mamba", "section": "", - "text": "utils.data.sft\nutils.data.sft\ndata handling specific to SFT" + "text": "core.trainers.mamba\nModule for mamba trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlMambaTrainer\nMamba specific trainer to handle loss calculation\n\n\n\n\n\ncore.trainers.mamba.AxolotlMambaTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nMamba specific trainer to handle loss calculation" }, { - "objectID": "docs/api/integrations.liger.args.html", - "href": "docs/api/integrations.liger.args.html", - "title": "integrations.liger.args", + "objectID": "docs/api/core.trainers.mamba.html#classes", + "href": "docs/api/core.trainers.mamba.html#classes", + "title": "core.trainers.mamba", "section": "", - "text": "integrations.liger.args\nModule for handling LIGER input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nLigerArgs\nInput args for LIGER.\n\n\n\n\n\nintegrations.liger.args.LigerArgs()\nInput args for LIGER." + "text": "Name\nDescription\n\n\n\n\nAxolotlMambaTrainer\nMamba specific trainer to handle loss calculation\n\n\n\n\n\ncore.trainers.mamba.AxolotlMambaTrainer(\n self,\n *_args,\n bench_data_collator=None,\n eval_data_collator=None,\n dataset_tags=None,\n **kwargs,\n)\nMamba specific trainer to handle loss calculation" }, { - "objectID": "docs/api/integrations.liger.args.html#classes", - "href": "docs/api/integrations.liger.args.html#classes", - "title": "integrations.liger.args", + "objectID": "docs/api/utils.schemas.trl.html", + "href": "docs/api/utils.schemas.trl.html", + "title": "utils.schemas.trl", "section": "", - "text": "Name\nDescription\n\n\n\n\nLigerArgs\nInput args for LIGER.\n\n\n\n\n\nintegrations.liger.args.LigerArgs()\nInput args for LIGER." + "text": "utils.schemas.trl\nPydantic models for TRL trainer configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nTRLConfig\nInput args for TRL.\n\n\n\n\n\nutils.schemas.trl.TRLConfig()\nInput args for TRL." }, { - "objectID": "docs/api/core.trainers.mixins.rng_state_loader.html", - "href": "docs/api/core.trainers.mixins.rng_state_loader.html", - "title": "core.trainers.mixins.rng_state_loader", + "objectID": "docs/api/utils.schemas.trl.html#classes", + "href": "docs/api/utils.schemas.trl.html#classes", + "title": "utils.schemas.trl", "section": "", - "text": "core.trainers.mixins.rng_state_loader\nTemporary fix/override for bug in resume from checkpoint\nSee https://github.com/huggingface/transformers/pull/37162\nTODO: Remove when upstream added PR to release\n\n\n\n\n\nName\nDescription\n\n\n\n\nRngLoaderMixin\nmixin for method override to load RNG states from a checkpoint\n\n\n\n\n\ncore.trainers.mixins.rng_state_loader.RngLoaderMixin()\nmixin for method override to load RNG states from a checkpoint" + "text": "Name\nDescription\n\n\n\n\nTRLConfig\nInput args for TRL.\n\n\n\n\n\nutils.schemas.trl.TRLConfig()\nInput args for TRL." }, { - "objectID": "docs/api/core.trainers.mixins.rng_state_loader.html#classes", - "href": "docs/api/core.trainers.mixins.rng_state_loader.html#classes", - "title": "core.trainers.mixins.rng_state_loader", + "objectID": "docs/api/cli.config.html", + "href": "docs/api/cli.config.html", + "title": "cli.config", "section": "", - "text": "Name\nDescription\n\n\n\n\nRngLoaderMixin\nmixin for method override to load RNG states from a checkpoint\n\n\n\n\n\ncore.trainers.mixins.rng_state_loader.RngLoaderMixin()\nmixin for method override to load RNG states from a checkpoint" + "text": "cli.config\nConfiguration loading and processing.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncheck_remote_config\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\n\n\nchoose_config\nHelper method for choosing a axolotl config YAML file (considering only files\n\n\nload_cfg\nLoads the axolotl configuration stored at config, validates it, and performs\n\n\nprepare_plugins\nRegisters the plugins for the given configuration.\n\n\n\n\n\ncli.config.check_remote_config(config)\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\nfor it and parse its content, first as JSON, then as YAML (YAML is preferred).\nFinally, the parsed content is written to a local file and its path is returned.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[str, Path]\nHTTPS URL to a YAML or JSON file.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nUnion[str, Path]\nEither the original config if it’s not a valid HTTPS URL, or the path to the\n\n\n\nUnion[str, Path]\ndownloaded remote config.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the remote configuration is neither valid JSON or YAML.\n\n\n\nRuntimeError\nIf some request-related exception occurs from the file download.\n\n\n\nException\nCatch-all for any other exception.\n\n\n\n\n\n\n\ncli.config.choose_config(path)\nHelper method for choosing a axolotl config YAML file (considering only files\nending with .yml or .yaml). If more than one config file exists in the passed\npath, the user is prompted to choose one.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\npath\nPath\nDirectory in which config file(s) are stored.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to either (1) the sole YAML file, or (2) if more than one YAML files exist,\n\n\n\nstr\nthe user-selected YAML file.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf no YAML files are found in the given path.\n\n\n\n\n\n\n\ncli.config.load_cfg(config=Path('examples/'), **kwargs)\nLoads the axolotl configuration stored at config, validates it, and performs\nvarious setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr | Path | DictDefault\nPath (local or remote) to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDictDefault\nDictDefault mapping configuration keys to values.\n\n\n\n\n\n\n\ncli.config.prepare_plugins(cfg)\nRegisters the plugins for the given configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" }, { - "objectID": "docs/api/prompt_strategies.kto.user_defined.html", - "href": "docs/api/prompt_strategies.kto.user_defined.html", - "title": "prompt_strategies.kto.user_defined", + "objectID": "docs/api/cli.config.html#functions", + "href": "docs/api/cli.config.html#functions", + "title": "cli.config", "section": "", - "text": "prompt_strategies.kto.user_defined\nprompt_strategies.kto.user_defined\nUser-defined KTO strategies" + "text": "Name\nDescription\n\n\n\n\ncheck_remote_config\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\n\n\nchoose_config\nHelper method for choosing a axolotl config YAML file (considering only files\n\n\nload_cfg\nLoads the axolotl configuration stored at config, validates it, and performs\n\n\nprepare_plugins\nRegisters the plugins for the given configuration.\n\n\n\n\n\ncli.config.check_remote_config(config)\nFirst, determines if the passed config is a valid HTTPS URL. Then, attempts to query\nfor it and parse its content, first as JSON, then as YAML (YAML is preferred).\nFinally, the parsed content is written to a local file and its path is returned.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[str, Path]\nHTTPS URL to a YAML or JSON file.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nUnion[str, Path]\nEither the original config if it’s not a valid HTTPS URL, or the path to the\n\n\n\nUnion[str, Path]\ndownloaded remote config.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the remote configuration is neither valid JSON or YAML.\n\n\n\nRuntimeError\nIf some request-related exception occurs from the file download.\n\n\n\nException\nCatch-all for any other exception.\n\n\n\n\n\n\n\ncli.config.choose_config(path)\nHelper method for choosing a axolotl config YAML file (considering only files\nending with .yml or .yaml). If more than one config file exists in the passed\npath, the user is prompted to choose one.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\npath\nPath\nDirectory in which config file(s) are stored.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nstr\nPath to either (1) the sole YAML file, or (2) if more than one YAML files exist,\n\n\n\nstr\nthe user-selected YAML file.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf no YAML files are found in the given path.\n\n\n\n\n\n\n\ncli.config.load_cfg(config=Path('examples/'), **kwargs)\nLoads the axolotl configuration stored at config, validates it, and performs\nvarious setup.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nstr | Path | DictDefault\nPath (local or remote) to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDictDefault\nDictDefault mapping configuration keys to values.\n\n\n\n\n\n\n\ncli.config.prepare_plugins(cfg)\nRegisters the plugins for the given configuration.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired" }, { - "objectID": "docs/api/monkeypatch.utils.html", - "href": "docs/api/monkeypatch.utils.html", - "title": "monkeypatch.utils", + "objectID": "docs/api/cli.vllm_serve.html", + "href": "docs/api/cli.vllm_serve.html", + "title": "cli.vllm_serve", "section": "", - "text": "monkeypatch.utils\nShared utils for the monkeypatches\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_cu_seqlens\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\nget_cu_seqlens_from_pos_ids\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\nmask_2d_to_4d\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\n\n\n\n\n\nmonkeypatch.utils.get_cu_seqlens(attn_mask)\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\n\nmonkeypatch.utils.get_cu_seqlens_from_pos_ids(position_ids)\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\n\nmonkeypatch.utils.mask_2d_to_4d(mask, dtype, tgt_len=None)\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\nThis expansion handles packed sequences so that sequences share the same attention mask integer value\nwhen they attend to each other within that sequence.\nThis expansion transforms the mask to lower triangular form to prevent future peeking." + "text": "cli.vllm_serve\nCLI to start the vllm server for online RL\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_vllm_serve\nStarts the VLLM server for serving LLM models used for online RL\n\n\n\n\n\ncli.vllm_serve.do_vllm_serve(config, cli_args)\nStarts the VLLM server for serving LLM models used for online RL\nArgs\n:param cfg: Parsed doct of the YAML config\n:param cli_args: dict of additional command-line arguments of type VllmServeCliArgs\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nprocess_id\n\nthe process id of the started VLLM server" }, { - "objectID": "docs/api/monkeypatch.utils.html#functions", - "href": "docs/api/monkeypatch.utils.html#functions", - "title": "monkeypatch.utils", + "objectID": "docs/api/cli.vllm_serve.html#functions", + "href": "docs/api/cli.vllm_serve.html#functions", + "title": "cli.vllm_serve", "section": "", - "text": "Name\nDescription\n\n\n\n\nget_cu_seqlens\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\nget_cu_seqlens_from_pos_ids\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\nmask_2d_to_4d\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\n\n\n\n\n\nmonkeypatch.utils.get_cu_seqlens(attn_mask)\ngenerate a cumulative sequence length mask for flash attention using attn mask\n\n\n\nmonkeypatch.utils.get_cu_seqlens_from_pos_ids(position_ids)\ngenerate a cumulative sequence length mask for flash attention using pos ids\n\n\n\nmonkeypatch.utils.mask_2d_to_4d(mask, dtype, tgt_len=None)\nExpands attention_mask from [bsz, seq_len] to [bsz, 1, tgt_seq_len, src_seq_len].\nThis expansion handles packed sequences so that sequences share the same attention mask integer value\nwhen they attend to each other within that sequence.\nThis expansion transforms the mask to lower triangular form to prevent future peeking." + "text": "Name\nDescription\n\n\n\n\ndo_vllm_serve\nStarts the VLLM server for serving LLM models used for online RL\n\n\n\n\n\ncli.vllm_serve.do_vllm_serve(config, cli_args)\nStarts the VLLM server for serving LLM models used for online RL\nArgs\n:param cfg: Parsed doct of the YAML config\n:param cli_args: dict of additional command-line arguments of type VllmServeCliArgs\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nprocess_id\n\nthe process id of the started VLLM server" }, { - "objectID": "docs/api/utils.schemas.multimodal.html", - "href": "docs/api/utils.schemas.multimodal.html", - "title": "utils.schemas.multimodal", + "objectID": "docs/api/core.datasets.transforms.chat_builder.html", + "href": "docs/api/core.datasets.transforms.chat_builder.html", + "title": "core.datasets.transforms.chat_builder", "section": "", - "text": "utils.schemas.multimodal\nPydantic models for multimodal-related configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nMultiModalConfig\nMulti-modal configuration subset\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig()\nMulti-modal configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nconvert_image_resize_algorithm\nConvert the image resize algorithm to a PIL.Image.Resampling enum.\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm(\n image_resize_algorithm,\n)\nConvert the image resize algorithm to a PIL.Image.Resampling enum." + "text": "core.datasets.transforms.chat_builder\nThis module contains a function that builds a transform that takes a row from the dataset and converts it to a Chat.\n\n\n\n\n\nName\nDescription\n\n\n\n\nchat_message_transform_builder\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\ncore.datasets.transforms.chat_builder.chat_message_transform_builder(\n train_on_inputs=False,\n conversations_field='conversations',\n message_field_role=['role', 'from'],\n message_field_content=['value', 'text', 'content'],\n message_field_training=['train', 'weight'],\n)\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrain_on_inputs\nbool\nIf True, the transform will train on the inputs. If False, the transform will train on the targets. Defaults to False.\nFalse\n\n\nconversations_field\nstr\nThe field name of the conversations. Defaults to “conversations”.\n'conversations'\n\n\nmessage_field_role\nstr | list[str]\nThe field name of the role. Defaults to “role”.\n['role', 'from']\n\n\nmessage_field_content\nstr | list[str]\nThe field name of the message content. Defaults to “content”.\n['value', 'text', 'content']\n\n\nmessage_field_training\nstr | list[str]\nThe field name of the train/weight. Defaults to “weight”.\n['train', 'weight']\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nCallable\n\nA function that takes a list of conversations and returns a list of messages." }, { - "objectID": "docs/api/utils.schemas.multimodal.html#classes", - "href": "docs/api/utils.schemas.multimodal.html#classes", - "title": "utils.schemas.multimodal", + "objectID": "docs/api/core.datasets.transforms.chat_builder.html#functions", + "href": "docs/api/core.datasets.transforms.chat_builder.html#functions", + "title": "core.datasets.transforms.chat_builder", "section": "", - "text": "Name\nDescription\n\n\n\n\nMultiModalConfig\nMulti-modal configuration subset\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig()\nMulti-modal configuration subset\n\n\n\n\n\nName\nDescription\n\n\n\n\nconvert_image_resize_algorithm\nConvert the image resize algorithm to a PIL.Image.Resampling enum.\n\n\n\n\n\nutils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm(\n image_resize_algorithm,\n)\nConvert the image resize algorithm to a PIL.Image.Resampling enum." + "text": "Name\nDescription\n\n\n\n\nchat_message_transform_builder\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\ncore.datasets.transforms.chat_builder.chat_message_transform_builder(\n train_on_inputs=False,\n conversations_field='conversations',\n message_field_role=['role', 'from'],\n message_field_content=['value', 'text', 'content'],\n message_field_training=['train', 'weight'],\n)\nBuilds a transform that takes a row from the dataset and converts it to a Chat\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntrain_on_inputs\nbool\nIf True, the transform will train on the inputs. If False, the transform will train on the targets. Defaults to False.\nFalse\n\n\nconversations_field\nstr\nThe field name of the conversations. Defaults to “conversations”.\n'conversations'\n\n\nmessage_field_role\nstr | list[str]\nThe field name of the role. Defaults to “role”.\n['role', 'from']\n\n\nmessage_field_content\nstr | list[str]\nThe field name of the message content. Defaults to “content”.\n['value', 'text', 'content']\n\n\nmessage_field_training\nstr | list[str]\nThe field name of the train/weight. Defaults to “weight”.\n['train', 'weight']\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nCallable\n\nA function that takes a list of conversations and returns a list of messages." }, { - "objectID": "docs/api/prompt_strategies.chat_template.html", - "href": "docs/api/prompt_strategies.chat_template.html", - "title": "prompt_strategies.chat_template", + "objectID": "docs/api/common.datasets.html", + "href": "docs/api/common.datasets.html", + "title": "common.datasets", "section": "", - "text": "prompt_strategies.chat_template\nHF Chat Templates prompt strategy\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatTemplatePrompter\nPrompter for HF chat templates\n\n\nChatTemplateStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nStrategyLoader\nLoad chat template strategy based on configuration.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplatePrompter(\n self,\n tokenizer,\n chat_template,\n processor=None,\n max_length=2048,\n message_property_mappings=None,\n message_field_training=None,\n message_field_training_detail=None,\n field_messages='messages',\n field_system='system',\n roles=None,\n drop_system_message=False,\n)\nPrompter for HF chat templates\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs,\n sequence_len,\n roles_to_train=None,\n train_on_eos=None,\n train_on_eot=None,\n eot_tokens=None,\n split_thinking=False,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\n\n\nName\nDescription\n\n\n\n\nfind_first_eot_token\nFind the first EOT token in the input_ids starting from start_idx.\n\n\nfind_turn\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\ntokenize_prompt\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token(\n input_ids,\n start_idx,\n)\nFind the first EOT token in the input_ids starting from start_idx.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_turn(turns, turn_idx)\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt(prompt)\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.StrategyLoader()\nLoad chat template strategy based on configuration." + "text": "common.datasets\nDataset loading utilities.\n\n\n\n\n\nName\nDescription\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and validation datasets and metadata.\n\n\n\n\n\ncommon.datasets.TrainDatasetMeta(\n self,\n train_dataset,\n eval_dataset=None,\n total_num_steps=None,\n)\nDataclass with fields for training and validation datasets and metadata.\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nload_datasets\nLoads one or more training or evaluation datasets, calling\n\n\nload_preference_datasets\nLoads one or more training or evaluation datasets for RL training using paired\n\n\nsample_dataset\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\ncommon.datasets.load_datasets(cfg, cli_args=None, debug=False)\nLoads one or more training or evaluation datasets, calling\naxolotl.utils.data.prepare_dataset. Optionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs | TrainerCliArgs | None\nCommand-specific CLI arguments.\nNone\n\n\ndebug\nbool\nWhether to print out tokenization of sample\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.load_preference_datasets(cfg, cli_args)\nLoads one or more training or evaluation datasets for RL training using paired\npreference data, calling axolotl.utils.data.rl.load_prepare_preference_datasets.\nOptionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nUnion[PreprocessCliArgs, TrainerCliArgs]\nCommand-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.sample_dataset(dataset, num_samples)\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nDataset\nDataset.\nrequired\n\n\nnum_samples\nint\nNumber of samples to return.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDataset\nRandom sample (with replacement) of examples in dataset." }, { - "objectID": "docs/api/prompt_strategies.chat_template.html#classes", - "href": "docs/api/prompt_strategies.chat_template.html#classes", - "title": "prompt_strategies.chat_template", + "objectID": "docs/api/common.datasets.html#classes", + "href": "docs/api/common.datasets.html#classes", + "title": "common.datasets", "section": "", - "text": "Name\nDescription\n\n\n\n\nChatTemplatePrompter\nPrompter for HF chat templates\n\n\nChatTemplateStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nStrategyLoader\nLoad chat template strategy based on configuration.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplatePrompter(\n self,\n tokenizer,\n chat_template,\n processor=None,\n max_length=2048,\n message_property_mappings=None,\n message_field_training=None,\n message_field_training_detail=None,\n field_messages='messages',\n field_system='system',\n roles=None,\n drop_system_message=False,\n)\nPrompter for HF chat templates\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs,\n sequence_len,\n roles_to_train=None,\n train_on_eos=None,\n train_on_eot=None,\n eot_tokens=None,\n split_thinking=False,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\n\n\nName\nDescription\n\n\n\n\nfind_first_eot_token\nFind the first EOT token in the input_ids starting from start_idx.\n\n\nfind_turn\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\ntokenize_prompt\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token(\n input_ids,\n start_idx,\n)\nFind the first EOT token in the input_ids starting from start_idx.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.find_turn(turns, turn_idx)\nLocate the starting and ending indices of the specified turn in a conversation.\n\n\n\nprompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt(prompt)\nPublic method that can handle either a single prompt or a batch of prompts.\n\n\n\n\n\nprompt_strategies.chat_template.StrategyLoader()\nLoad chat template strategy based on configuration." + "text": "Name\nDescription\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and validation datasets and metadata.\n\n\n\n\n\ncommon.datasets.TrainDatasetMeta(\n self,\n train_dataset,\n eval_dataset=None,\n total_num_steps=None,\n)\nDataclass with fields for training and validation datasets and metadata." }, { - "objectID": "docs/api/utils.lora.html", - "href": "docs/api/utils.lora.html", - "title": "utils.lora", + "objectID": "docs/api/common.datasets.html#functions", + "href": "docs/api/common.datasets.html#functions", + "title": "common.datasets", "section": "", - "text": "utils.lora\nmodule to get the state dict of a merged lora model\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_lora_merged_state_dict\nCreate and return a state_dict that has the LoRA deltas\n\n\n\n\n\nutils.lora.get_lora_merged_state_dict(model)\nCreate and return a state_dict that has the LoRA deltas\nmerged into the base model’s weights, without modifying model in place.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\ntorch.nn.Module\nA model that has LoRA/PEFT adapters attached.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndict\ndict\nA state_dict of the merged parameters." + "text": "Name\nDescription\n\n\n\n\nload_datasets\nLoads one or more training or evaluation datasets, calling\n\n\nload_preference_datasets\nLoads one or more training or evaluation datasets for RL training using paired\n\n\nsample_dataset\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\ncommon.datasets.load_datasets(cfg, cli_args=None, debug=False)\nLoads one or more training or evaluation datasets, calling\naxolotl.utils.data.prepare_dataset. Optionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nPreprocessCliArgs | TrainerCliArgs | None\nCommand-specific CLI arguments.\nNone\n\n\ndebug\nbool\nWhether to print out tokenization of sample\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.load_preference_datasets(cfg, cli_args)\nLoads one or more training or evaluation datasets for RL training using paired\npreference data, calling axolotl.utils.data.rl.load_prepare_preference_datasets.\nOptionally, logs out debug information.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nUnion[PreprocessCliArgs, TrainerCliArgs]\nCommand-specific CLI arguments.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nTrainDatasetMeta\nDataclass with fields for training and evaluation datasets and the computed\n\n\n\nTrainDatasetMeta\ntotal_num_steps.\n\n\n\n\n\n\n\ncommon.datasets.sample_dataset(dataset, num_samples)\nRandomly sample num_samples samples from dataset.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndataset\nDataset\nDataset.\nrequired\n\n\nnum_samples\nint\nNumber of samples to return.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nDataset\nRandom sample (with replacement) of examples in dataset." }, { - "objectID": "docs/api/utils.lora.html#functions", - "href": "docs/api/utils.lora.html#functions", - "title": "utils.lora", + "objectID": "docs/api/prompt_strategies.alpaca_instruct.html", + "href": "docs/api/prompt_strategies.alpaca_instruct.html", + "title": "prompt_strategies.alpaca_instruct", "section": "", - "text": "Name\nDescription\n\n\n\n\nget_lora_merged_state_dict\nCreate and return a state_dict that has the LoRA deltas\n\n\n\n\n\nutils.lora.get_lora_merged_state_dict(model)\nCreate and return a state_dict that has the LoRA deltas\nmerged into the base model’s weights, without modifying model in place.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nmodel\ntorch.nn.Module\nA model that has LoRA/PEFT adapters attached.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndict\ndict\nA state_dict of the merged parameters." + "text": "prompt_strategies.alpaca_instruct\nprompt_strategies.alpaca_instruct\nModule loading the AlpacaInstructPromptTokenizingStrategy class" }, { - "objectID": "docs/api/monkeypatch.btlm_attn_hijack_flash.html", - "href": "docs/api/monkeypatch.btlm_attn_hijack_flash.html", - "title": "monkeypatch.btlm_attn_hijack_flash", + "objectID": "docs/api/core.chat.format.chatml.html", + "href": "docs/api/core.chat.format.chatml.html", + "title": "core.chat.format.chatml", "section": "", - "text": "monkeypatch.btlm_attn_hijack_flash\nmonkeypatch.btlm_attn_hijack_flash\nFlash attention monkey patch for cerebras btlm model" + "text": "core.chat.format.chatml\ncore.chat.format.chatml\nChatML transformation functions for MessageContents" }, { - "objectID": "docs/api/utils.chat_templates.html", - "href": "docs/api/utils.chat_templates.html", - "title": "utils.chat_templates", + "objectID": "docs/api/monkeypatch.attention.mllama.html", + "href": "docs/api/monkeypatch.attention.mllama.html", + "title": "monkeypatch.attention.mllama", "section": "", - "text": "utils.chat_templates\nThis module provides functionality for selecting chat templates based on user choices.\nThese templates are used for formatting messages in a conversation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_chat_template\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\nregister_chat_template\nRegisters chat templates.\n\n\n\n\n\nutils.chat_templates.get_chat_template(\n user_choice,\n jinja_template=None,\n tokenizer=None,\n)\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nuser_choice\nstr\nThe user’s choice of template.\nrequired\n\n\njinja_template\nOptional[str]\nThe jinja template string. Defaults to None.\nNone\n\n\ntokenizer\nOptional[PreTrainedTokenizerBase]\nThe tokenizer. Defaults to None.\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nstr\nstr\nThe chosen template string.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the user_choice is not found in the templates.\n\n\n\n\n\n\n\nutils.chat_templates.register_chat_template(template_name, chat_template)\nRegisters chat templates.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntemplate_name\nstr\nThe name of the template.\nrequired\n\n\nchat_template\nstr\nThe template string.\nrequired" + "text": "monkeypatch.attention.mllama\nMonkeypatch for Vision Llama for FA2 support\n\n\n\n\n\nName\nDescription\n\n\n\n\nMllamaTextCrossFlashAttention2\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\n\n\nMllamaTextSelfFlashAttention2\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\n\n\n\n\n\nmonkeypatch.attention.mllama.MllamaTextCrossFlashAttention2(\n self,\n *args,\n **kwargs,\n)\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\nimplements the forward pass using Flash Attention for improved performance.\n\n\n\nmonkeypatch.attention.mllama.MllamaTextSelfFlashAttention2(\n self,\n config,\n layer_idx,\n *args,\n **kwargs,\n)\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\nimplements the forward pass using Flash Attention for improved performance." }, { - "objectID": "docs/api/utils.chat_templates.html#functions", - "href": "docs/api/utils.chat_templates.html#functions", - "title": "utils.chat_templates", + "objectID": "docs/api/monkeypatch.attention.mllama.html#classes", + "href": "docs/api/monkeypatch.attention.mllama.html#classes", + "title": "monkeypatch.attention.mllama", "section": "", - "text": "Name\nDescription\n\n\n\n\nget_chat_template\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\nregister_chat_template\nRegisters chat templates.\n\n\n\n\n\nutils.chat_templates.get_chat_template(\n user_choice,\n jinja_template=None,\n tokenizer=None,\n)\nFinds the correct chat_template based on the user’s choice, jinja_template, and tokenizer.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nuser_choice\nstr\nThe user’s choice of template.\nrequired\n\n\njinja_template\nOptional[str]\nThe jinja template string. Defaults to None.\nNone\n\n\ntokenizer\nOptional[PreTrainedTokenizerBase]\nThe tokenizer. Defaults to None.\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nstr\nstr\nThe chosen template string.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf the user_choice is not found in the templates.\n\n\n\n\n\n\n\nutils.chat_templates.register_chat_template(template_name, chat_template)\nRegisters chat templates.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntemplate_name\nstr\nThe name of the template.\nrequired\n\n\nchat_template\nstr\nThe template string.\nrequired" + "text": "Name\nDescription\n\n\n\n\nMllamaTextCrossFlashAttention2\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\n\n\nMllamaTextSelfFlashAttention2\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\n\n\n\n\n\nmonkeypatch.attention.mllama.MllamaTextCrossFlashAttention2(\n self,\n *args,\n **kwargs,\n)\nMllama flash cross-attention module. This module inherits from MllamaTextCrossAttention and\nimplements the forward pass using Flash Attention for improved performance.\n\n\n\nmonkeypatch.attention.mllama.MllamaTextSelfFlashAttention2(\n self,\n config,\n layer_idx,\n *args,\n **kwargs,\n)\nMllama flash self-attention module. This module inherits from MllamaTextSelfAttention and\nimplements the forward pass using Flash Attention for improved performance." }, { - "objectID": "docs/api/integrations.cut_cross_entropy.args.html", - "href": "docs/api/integrations.cut_cross_entropy.args.html", - "title": "integrations.cut_cross_entropy.args", + "objectID": "docs/api/prompt_strategies.dpo.zephyr.html", + "href": "docs/api/prompt_strategies.dpo.zephyr.html", + "title": "prompt_strategies.dpo.zephyr", "section": "", - "text": "integrations.cut_cross_entropy.args\nModule for handling Cut Cross Entropy input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nCutCrossEntropyArgs\nInput args for Cut Cross Entropy.\n\n\n\n\n\nintegrations.cut_cross_entropy.args.CutCrossEntropyArgs()\nInput args for Cut Cross Entropy." + "text": "prompt_strategies.dpo.zephyr\nprompt_strategies.dpo.zephyr\nDPO strategies for zephyr" }, { - "objectID": "docs/api/integrations.cut_cross_entropy.args.html#classes", - "href": "docs/api/integrations.cut_cross_entropy.args.html#classes", - "title": "integrations.cut_cross_entropy.args", + "objectID": "docs/api/utils.schemas.config.html", + "href": "docs/api/utils.schemas.config.html", + "title": "utils.schemas.config", "section": "", - "text": "Name\nDescription\n\n\n\n\nCutCrossEntropyArgs\nInput args for Cut Cross Entropy.\n\n\n\n\n\nintegrations.cut_cross_entropy.args.CutCrossEntropyArgs()\nInput args for Cut Cross Entropy." + "text": "utils.schemas.config\nModule with Pydantic models for configuration.\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlConfigWCapabilities\nwrapper to valdiate gpu capabilities with the configured options\n\n\nAxolotlInputConfig\nWrapper of all config options\n\n\n\n\n\nutils.schemas.config.AxolotlConfigWCapabilities()\nwrapper to valdiate gpu capabilities with the configured options\n\n\n\nutils.schemas.config.AxolotlInputConfig()\nWrapper of all config options" }, { - "objectID": "docs/api/monkeypatch.trainer_fsdp_optim.html", - "href": "docs/api/monkeypatch.trainer_fsdp_optim.html", - "title": "monkeypatch.trainer_fsdp_optim", + "objectID": "docs/api/utils.schemas.config.html#classes", + "href": "docs/api/utils.schemas.config.html#classes", + "title": "utils.schemas.config", "section": "", - "text": "monkeypatch.trainer_fsdp_optim\nfix for FSDP optimizer save in trainer w 4.47.0\n\n\n\n\n\nName\nDescription\n\n\n\n\npatch_training_loop_for_fsdp\nmonkeypatch for fixing the training loop for fsdp with optimizer save\n\n\n\n\n\nmonkeypatch.trainer_fsdp_optim.patch_training_loop_for_fsdp()\nmonkeypatch for fixing the training loop for fsdp with optimizer save" + "text": "Name\nDescription\n\n\n\n\nAxolotlConfigWCapabilities\nwrapper to valdiate gpu capabilities with the configured options\n\n\nAxolotlInputConfig\nWrapper of all config options\n\n\n\n\n\nutils.schemas.config.AxolotlConfigWCapabilities()\nwrapper to valdiate gpu capabilities with the configured options\n\n\n\nutils.schemas.config.AxolotlInputConfig()\nWrapper of all config options" }, { - "objectID": "docs/api/monkeypatch.trainer_fsdp_optim.html#functions", - "href": "docs/api/monkeypatch.trainer_fsdp_optim.html#functions", - "title": "monkeypatch.trainer_fsdp_optim", + "objectID": "docs/api/monkeypatch.unsloth_.html", + "href": "docs/api/monkeypatch.unsloth_.html", + "title": "monkeypatch.unsloth_", "section": "", - "text": "Name\nDescription\n\n\n\n\npatch_training_loop_for_fsdp\nmonkeypatch for fixing the training loop for fsdp with optimizer save\n\n\n\n\n\nmonkeypatch.trainer_fsdp_optim.patch_training_loop_for_fsdp()\nmonkeypatch for fixing the training loop for fsdp with optimizer save" + "text": "monkeypatch.unsloth_\nmonkeypatch.unsloth_\nmodule for patching with unsloth optimizations" }, { - "objectID": "docs/api/prompt_strategies.stepwise_supervised.html", - "href": "docs/api/prompt_strategies.stepwise_supervised.html", - "title": "prompt_strategies.stepwise_supervised", + "objectID": "docs/api/prompt_strategies.dpo.passthrough.html", + "href": "docs/api/prompt_strategies.dpo.passthrough.html", + "title": "prompt_strategies.dpo.passthrough", "section": "", - "text": "prompt_strategies.stepwise_supervised\nModule for stepwise datasets, typically including a prompt and reasoning traces,\nand (optionally) per-step, or per-prompt-trace labels for reward modelling.\n\n\n\n\n\nName\nDescription\n\n\n\n\nStepwiseSupervisedPromptTokenizingStrategy\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\n\n\n\n\n\nprompt_strategies.stepwise_supervised.StepwiseSupervisedPromptTokenizingStrategy(\n self,\n tokenizer,\n sequence_len=2048,\n step_separator='\\n',\n max_completion_length=None,\n train_on_last_step_only=False,\n)\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\nThese datasets should include the following columns:\n- prompt: the prompt text\n- completions: a list of n completion steps\n- labels: a list of n labels indicating the “correctness” of each step" + "text": "prompt_strategies.dpo.passthrough\nprompt_strategies.dpo.passthrough\nDPO prompt strategies passthrough/zero-processing strategy" }, { - "objectID": "docs/api/prompt_strategies.stepwise_supervised.html#classes", - "href": "docs/api/prompt_strategies.stepwise_supervised.html#classes", - "title": "prompt_strategies.stepwise_supervised", + "objectID": "docs/api/prompt_strategies.orcamini.html", + "href": "docs/api/prompt_strategies.orcamini.html", + "title": "prompt_strategies.orcamini", "section": "", - "text": "Name\nDescription\n\n\n\n\nStepwiseSupervisedPromptTokenizingStrategy\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\n\n\n\n\n\nprompt_strategies.stepwise_supervised.StepwiseSupervisedPromptTokenizingStrategy(\n self,\n tokenizer,\n sequence_len=2048,\n step_separator='\\n',\n max_completion_length=None,\n train_on_last_step_only=False,\n)\nTokenizing strategy for supervised stepwise datasets, typically used for COT-reasoning.\nThese datasets should include the following columns:\n- prompt: the prompt text\n- completions: a list of n completion steps\n- labels: a list of n labels indicating the “correctness” of each step" + "text": "prompt_strategies.orcamini\nPrompt Strategy for finetuning Orca Mini (v2) models\nsee also https://huggingface.co/psmathur/orca_mini_v2_7b for more information\nUse dataset type: orcamini in conig.yml to use this prompt style.\nCompared to the alpaca_w_system.open_orca dataset type,\nthis one specifies the system prompt with “### System:”.\nNot suited/tested for multiple-turn conversations without further adjustments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nOrcaMiniPrompter\nAdjusted Prompter for Orca Mini (v2) datasets\n\n\n\n\n\nprompt_strategies.orcamini.OrcaMiniPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAdjusted Prompter for Orca Mini (v2) datasets" }, { - "objectID": "docs/api/utils.callbacks.profiler.html", - "href": "docs/api/utils.callbacks.profiler.html", - "title": "utils.callbacks.profiler", + "objectID": "docs/api/prompt_strategies.orcamini.html#classes", + "href": "docs/api/prompt_strategies.orcamini.html#classes", + "title": "prompt_strategies.orcamini", "section": "", - "text": "utils.callbacks.profiler\nHF Trainer callback for creating pytorch profiling snapshots\n\n\n\n\n\nName\nDescription\n\n\n\n\nPytorchProfilerCallback\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps.\n\n\n\n\n\nutils.callbacks.profiler.PytorchProfilerCallback(self, steps_to_profile=5)\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps." + "text": "Name\nDescription\n\n\n\n\nOrcaMiniPrompter\nAdjusted Prompter for Orca Mini (v2) datasets\n\n\n\n\n\nprompt_strategies.orcamini.OrcaMiniPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAdjusted Prompter for Orca Mini (v2) datasets" }, { - "objectID": "docs/api/utils.callbacks.profiler.html#classes", - "href": "docs/api/utils.callbacks.profiler.html#classes", - "title": "utils.callbacks.profiler", + "objectID": "docs/api/cli.evaluate.html", + "href": "docs/api/cli.evaluate.html", + "title": "cli.evaluate", "section": "", - "text": "Name\nDescription\n\n\n\n\nPytorchProfilerCallback\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps.\n\n\n\n\n\nutils.callbacks.profiler.PytorchProfilerCallback(self, steps_to_profile=5)\nPyTorch Profiler callback to create snapshots of GPU memory usage at specified steps." + "text": "cli.evaluate\nCLI to run evaluation on a model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\ndo_evaluate\nEvaluates a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.evaluate.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.evaluate.do_evaluate(cfg, cli_args)\nEvaluates a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.evaluate.evaluate, which computes\nevaluation metrics on the given dataset(s) and writes them to disk.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nCLI arguments.\nrequired" }, { - "objectID": "docs/api/cli.merge_sharded_fsdp_weights.html", - "href": "docs/api/cli.merge_sharded_fsdp_weights.html", - "title": "cli.merge_sharded_fsdp_weights", + "objectID": "docs/api/cli.evaluate.html#functions", + "href": "docs/api/cli.evaluate.html#functions", + "title": "cli.evaluate", "section": "", - "text": "cli.merge_sharded_fsdp_weights\nCLI to merge sharded FSDP model checkpoints into a single combined checkpoint.\n\n\n\n\n\nName\nDescription\n\n\n\n\nBFloat16CastPlanner\nA custom planner to cast tensors to bfloat16 on the fly during loading.\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.BFloat16CastPlanner()\nA custom planner to cast tensors to bfloat16 on the fly during loading.\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\nmerge_fsdp_weights\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.merge_fsdp_weights(\n checkpoint_dir,\n output_path,\n safe_serialization=False,\n remove_checkpoint_dir=False,\n)\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\nSHARDED_STATE_DICT was used for the model. Weights will be saved to {output_path}/model.safetensors if\nsafe_serialization else pytorch_model.bin.\nNote: this is a CPU-bound process.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncheckpoint_dir\nstr\nThe directory containing the FSDP checkpoints (can be either the model or optimizer).\nrequired\n\n\noutput_path\nstr\nThe path to save the merged checkpoint.\nrequired\n\n\nsafe_serialization\nbool, optional, defaults to True\nWhether to save the merged weights with safetensors (recommended).\nFalse\n\n\nremove_checkpoint_dir\nbool, optional, defaults to False\nWhether to remove the checkpoint directory after merging.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf torch version < 2.3.0, or if checkpoint_dir does not exist." + "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\ndo_evaluate\nEvaluates a transformers model by first loading the dataset(s) specified in the\n\n\n\n\n\ncli.evaluate.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls do_evaluate.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.evaluate.do_evaluate(cfg, cli_args)\nEvaluates a transformers model by first loading the dataset(s) specified in the\naxolotl config, and then calling axolotl.evaluate.evaluate, which computes\nevaluation metrics on the given dataset(s) and writes them to disk.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nDictionary mapping axolotl config keys to values.\nrequired\n\n\ncli_args\nTrainerCliArgs\nCLI arguments.\nrequired" }, { - "objectID": "docs/api/cli.merge_sharded_fsdp_weights.html#classes", - "href": "docs/api/cli.merge_sharded_fsdp_weights.html#classes", - "title": "cli.merge_sharded_fsdp_weights", + "objectID": "docs/api/monkeypatch.multipack.html", + "href": "docs/api/monkeypatch.multipack.html", + "title": "monkeypatch.multipack", "section": "", - "text": "Name\nDescription\n\n\n\n\nBFloat16CastPlanner\nA custom planner to cast tensors to bfloat16 on the fly during loading.\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.BFloat16CastPlanner()\nA custom planner to cast tensors to bfloat16 on the fly during loading." + "text": "monkeypatch.multipack\nmonkeypatch.multipack\nmultipack patching for v2 of sample packing" }, { - "objectID": "docs/api/cli.merge_sharded_fsdp_weights.html#functions", - "href": "docs/api/cli.merge_sharded_fsdp_weights.html#functions", - "title": "cli.merge_sharded_fsdp_weights", + "objectID": "docs/api/cli.sweeps.html", + "href": "docs/api/cli.sweeps.html", + "title": "cli.sweeps", "section": "", - "text": "Name\nDescription\n\n\n\n\ndo_cli\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\nmerge_fsdp_weights\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.do_cli(config=Path('examples/'), **kwargs)\nParses axolotl config, CLI args, and calls merge_fsdp_weights.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nconfig\nUnion[Path, str]\nPath to axolotl config YAML file.\nPath('examples/')\n\n\nkwargs\n\nAdditional keyword arguments to override config file values.\n{}\n\n\n\n\n\n\n\ncli.merge_sharded_fsdp_weights.merge_fsdp_weights(\n checkpoint_dir,\n output_path,\n safe_serialization=False,\n remove_checkpoint_dir=False,\n)\nMerge the weights from sharded FSDP model checkpoints into a single combined checkpoint. Should be used if\nSHARDED_STATE_DICT was used for the model. Weights will be saved to {output_path}/model.safetensors if\nsafe_serialization else pytorch_model.bin.\nNote: this is a CPU-bound process.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncheckpoint_dir\nstr\nThe directory containing the FSDP checkpoints (can be either the model or optimizer).\nrequired\n\n\noutput_path\nstr\nThe path to save the merged checkpoint.\nrequired\n\n\nsafe_serialization\nbool, optional, defaults to True\nWhether to save the merged weights with safetensors (recommended).\nFalse\n\n\nremove_checkpoint_dir\nbool, optional, defaults to False\nWhether to remove the checkpoint directory after merging.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf torch version < 2.3.0, or if checkpoint_dir does not exist." + "text": "cli.sweeps\nUtilities for handling sweeps over configs for axolotl train CLI command\n\n\n\n\n\nName\nDescription\n\n\n\n\ngenerate_sweep_configs\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\ncli.sweeps.generate_sweep_configs(base_config, sweeps_config)\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_config\ndict\nThe original configuration dictionary\nrequired\n\n\nsweeps_config\ndict\nDictionary where keys are parameters and values are either: - lists of values to sweep independently - or for paired values, a list of dicts under the ’_’ key\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nlist\nlist[dict[str, list]]\nList of all possible configuration dictionaries\n\n\n\n\n\n\nsweeps_config = {\n‘learning_rate’: [0.1, 0.01],\n’_’: [\n{‘load_in_8bit’: True, ‘adapter’: ‘lora’},\n{‘load_in_4bit’: True, ‘adapter’: ‘qlora’}\n]\n}" }, { - "objectID": "docs/api/utils.collators.mamba.html", - "href": "docs/api/utils.collators.mamba.html", - "title": "utils.collators.mamba", + "objectID": "docs/api/cli.sweeps.html#functions", + "href": "docs/api/cli.sweeps.html#functions", + "title": "cli.sweeps", "section": "", - "text": "utils.collators.mamba\ncollators for Mamba\n\n\n\n\n\nName\nDescription\n\n\n\n\nMambaDataCollator\nCollator for State Space Models (Mamba)\n\n\n\n\n\nutils.collators.mamba.MambaDataCollator(self, tokenizer)\nCollator for State Space Models (Mamba)" + "text": "Name\nDescription\n\n\n\n\ngenerate_sweep_configs\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\ncli.sweeps.generate_sweep_configs(base_config, sweeps_config)\nRecursively generates all possible configurations by applying sweeps to the base config.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nbase_config\ndict\nThe original configuration dictionary\nrequired\n\n\nsweeps_config\ndict\nDictionary where keys are parameters and values are either: - lists of values to sweep independently - or for paired values, a list of dicts under the ’_’ key\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nlist\nlist[dict[str, list]]\nList of all possible configuration dictionaries\n\n\n\n\n\n\nsweeps_config = {\n‘learning_rate’: [0.1, 0.01],\n’_’: [\n{‘load_in_8bit’: True, ‘adapter’: ‘lora’},\n{‘load_in_4bit’: True, ‘adapter’: ‘qlora’}\n]\n}" }, { - "objectID": "docs/api/utils.collators.mamba.html#classes", - "href": "docs/api/utils.collators.mamba.html#classes", - "title": "utils.collators.mamba", + "objectID": "docs/api/prompt_strategies.kto.chatml.html", + "href": "docs/api/prompt_strategies.kto.chatml.html", + "title": "prompt_strategies.kto.chatml", "section": "", - "text": "Name\nDescription\n\n\n\n\nMambaDataCollator\nCollator for State Space Models (Mamba)\n\n\n\n\n\nutils.collators.mamba.MambaDataCollator(self, tokenizer)\nCollator for State Space Models (Mamba)" + "text": "prompt_strategies.kto.chatml\nKTO strategies for chatml\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.chatml.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" }, { - "objectID": "docs/api/utils.samplers.multipack.html", - "href": "docs/api/utils.samplers.multipack.html", - "title": "utils.samplers.multipack", + "objectID": "docs/api/prompt_strategies.kto.chatml.html#functions", + "href": "docs/api/prompt_strategies.kto.chatml.html#functions", + "title": "prompt_strategies.kto.chatml", "section": "", - "text": "utils.samplers.multipack\nMultipack Batch Sampler - An efficient batch sampler for packing variable-length sequences\ninto fixed-capacity batches to optimize memory usage and training throughput.\n\n\n\n\n\nName\nDescription\n\n\n\n\nMultipackBatchSampler\nBatch sampler class for efficient packing of variable-length sequences\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler(\n self,\n sampler,\n batch_size,\n batch_max_len,\n lengths,\n packing_efficiency_estimate=1.0,\n drop_last=False,\n num_count_samples=16,\n sequential=False,\n group_size=100000,\n bin_size=200,\n num_processes=None,\n safe_mode=True,\n **kwargs,\n)\nBatch sampler class for efficient packing of variable-length sequences\nThis sampler packs sequences into fixed-capacity bins (batches) to maximize\nGPU memory utilization and training throughput by reducing padding.\nIt supports both parallel packing (using FFD algorithm) and\nsequential packing (preserving original sequence order).\n\n\n\n\n\nName\nDescription\n\n\n\n\nefficiency\nCalculate the packing efficiency (ratio of tokens used to total token slots)\n\n\ngather_efficiency\nGather and synchronize packing efficiency estimates across all distributed ranks\n\n\ngather_len_batches\nGather and synchronize batch counts across all distributed ranks\n\n\ngenerate_batches\nGenerate packed batches for training\n\n\nset_epoch\nSet the epoch number, used for reproducible shuffling across epochs\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.efficiency()\nCalculate the packing efficiency (ratio of tokens used to total token slots)\nHigher is better - 1.0 would mean perfect packing with no wasted space\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_efficiency()\nGather and synchronize packing efficiency estimates across all distributed ranks\nReturns a conservative efficiency estimate based on the measurements\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_len_batches(num)\nGather and synchronize batch counts across all distributed ranks\nReturns the minimum number of batches available on any rank\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.generate_batches(set_stats=False)\nGenerate packed batches for training\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nset_stats\n\nWhether to update efficiency statistics\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of batches, where each batch contains multiple bins,\n\n\n\n\nand each bin contains multiple sequence indices\n\n\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.set_epoch(epoch)\nSet the epoch number, used for reproducible shuffling across epochs\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nallocate_sequentially\nSequential allocator that preserves example order\n\n\nffd_check\nFirst-fit-decreasing bin packing algorithm check\n\n\npack_group\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\npack_parallel\nPack sequences into bins using parallel processing\n\n\n\n\n\nutils.samplers.multipack.allocate_sequentially(\n sequence_lengths,\n rank,\n bin_capacity,\n num_ranks,\n)\nSequential allocator that preserves example order\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nThe lengths of all examples\nrequired\n\n\nrank\nint\nThe current rank (for distributed training)\nrequired\n\n\nbin_capacity\nint\nThe capacity of each bin (maximum sequence length)\nrequired\n\n\nnum_ranks\nint\nNumber of ranks (processes/GPUs)\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nrank_batches\n\nList of batches for the current rank\n\n\ntotal_tokens_used\n\nNumber of actual example tokens\n\n\ntotal_token_slots\n\nMaximum theoretical number of example tokens (number of bins * bin capacity)\n\n\n\n\n\n\n\nutils.samplers.multipack.ffd_check(sequence_lengths, bin_capacity, num_bins)\nFirst-fit-decreasing bin packing algorithm check\nChecks if sequences with the given lengths could fit in the specified number of bins\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nnum_bins\nint\nNumber of bins available\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nTrue if all sequences can be packed, False otherwise\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_group(\n sequence_lengths,\n group_offset,\n bin_capacity,\n max_bins,\n bin_size,\n safe_mode=True,\n)\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\ngroup_offset\nint\nOffset to apply to indices when returning results\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nmax_bins\nint\nMaximum number of bins to use\nrequired\n\n\nbin_size\nint\nMaximum number of sequences per bin\nrequired\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of bins, where each bin contains indices of sequences assigned to it\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_parallel(\n sequence_lengths,\n bin_capacity,\n group_size,\n bin_size,\n num_processes=None,\n safe_mode=True,\n mp_start_method='spawn',\n)\nPack sequences into bins using parallel processing\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin as total number of tokens\nrequired\n\n\ngroup_size\nint\nNumber of sequences to process in each group\nrequired\n\n\nbin_size\nint\nMaximum number of bins to use\nrequired\n\n\nnum_processes\nint | None\nNumber of parallel processes to use\nNone\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\nmp_start_method\nstr | None\nMultiprocessing start method (‘fork’, ‘spawn’, ‘forkserver’). ‘spawn’ is often safer with Numba/PyTorch. Set to None to use system default.\n'spawn'\n\n\n\nReturns:\nList of bins, where each bin contains indices of sequences assigned to it" + "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.chatml.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.chatml.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.chatml.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" }, { - "objectID": "docs/api/utils.samplers.multipack.html#classes", - "href": "docs/api/utils.samplers.multipack.html#classes", - "title": "utils.samplers.multipack", + "objectID": "docs/api/prompt_strategies.base.html", + "href": "docs/api/prompt_strategies.base.html", + "title": "prompt_strategies.base", "section": "", - "text": "Name\nDescription\n\n\n\n\nMultipackBatchSampler\nBatch sampler class for efficient packing of variable-length sequences\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler(\n self,\n sampler,\n batch_size,\n batch_max_len,\n lengths,\n packing_efficiency_estimate=1.0,\n drop_last=False,\n num_count_samples=16,\n sequential=False,\n group_size=100000,\n bin_size=200,\n num_processes=None,\n safe_mode=True,\n **kwargs,\n)\nBatch sampler class for efficient packing of variable-length sequences\nThis sampler packs sequences into fixed-capacity bins (batches) to maximize\nGPU memory utilization and training throughput by reducing padding.\nIt supports both parallel packing (using FFD algorithm) and\nsequential packing (preserving original sequence order).\n\n\n\n\n\nName\nDescription\n\n\n\n\nefficiency\nCalculate the packing efficiency (ratio of tokens used to total token slots)\n\n\ngather_efficiency\nGather and synchronize packing efficiency estimates across all distributed ranks\n\n\ngather_len_batches\nGather and synchronize batch counts across all distributed ranks\n\n\ngenerate_batches\nGenerate packed batches for training\n\n\nset_epoch\nSet the epoch number, used for reproducible shuffling across epochs\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.efficiency()\nCalculate the packing efficiency (ratio of tokens used to total token slots)\nHigher is better - 1.0 would mean perfect packing with no wasted space\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_efficiency()\nGather and synchronize packing efficiency estimates across all distributed ranks\nReturns a conservative efficiency estimate based on the measurements\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.gather_len_batches(num)\nGather and synchronize batch counts across all distributed ranks\nReturns the minimum number of batches available on any rank\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.generate_batches(set_stats=False)\nGenerate packed batches for training\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nset_stats\n\nWhether to update efficiency statistics\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of batches, where each batch contains multiple bins,\n\n\n\n\nand each bin contains multiple sequence indices\n\n\n\n\n\n\n\nutils.samplers.multipack.MultipackBatchSampler.set_epoch(epoch)\nSet the epoch number, used for reproducible shuffling across epochs" + "text": "prompt_strategies.base\nprompt_strategies.base\nmodule for base dataset transform strategies" }, { - "objectID": "docs/api/utils.samplers.multipack.html#functions", - "href": "docs/api/utils.samplers.multipack.html#functions", - "title": "utils.samplers.multipack", + "objectID": "docs/api/kernels.utils.html", + "href": "docs/api/kernels.utils.html", + "title": "kernels.utils", "section": "", - "text": "Name\nDescription\n\n\n\n\nallocate_sequentially\nSequential allocator that preserves example order\n\n\nffd_check\nFirst-fit-decreasing bin packing algorithm check\n\n\npack_group\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\npack_parallel\nPack sequences into bins using parallel processing\n\n\n\n\n\nutils.samplers.multipack.allocate_sequentially(\n sequence_lengths,\n rank,\n bin_capacity,\n num_ranks,\n)\nSequential allocator that preserves example order\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nThe lengths of all examples\nrequired\n\n\nrank\nint\nThe current rank (for distributed training)\nrequired\n\n\nbin_capacity\nint\nThe capacity of each bin (maximum sequence length)\nrequired\n\n\nnum_ranks\nint\nNumber of ranks (processes/GPUs)\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nrank_batches\n\nList of batches for the current rank\n\n\ntotal_tokens_used\n\nNumber of actual example tokens\n\n\ntotal_token_slots\n\nMaximum theoretical number of example tokens (number of bins * bin capacity)\n\n\n\n\n\n\n\nutils.samplers.multipack.ffd_check(sequence_lengths, bin_capacity, num_bins)\nFirst-fit-decreasing bin packing algorithm check\nChecks if sequences with the given lengths could fit in the specified number of bins\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nnum_bins\nint\nNumber of bins available\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nTrue if all sequences can be packed, False otherwise\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_group(\n sequence_lengths,\n group_offset,\n bin_capacity,\n max_bins,\n bin_size,\n safe_mode=True,\n)\nPack a group of sequences into bins using First-Fit Decreasing algorithm\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\ngroup_offset\nint\nOffset to apply to indices when returning results\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin\nrequired\n\n\nmax_bins\nint\nMaximum number of bins to use\nrequired\n\n\nbin_size\nint\nMaximum number of sequences per bin\nrequired\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList of bins, where each bin contains indices of sequences assigned to it\n\n\n\n\n\n\n\nutils.samplers.multipack.pack_parallel(\n sequence_lengths,\n bin_capacity,\n group_size,\n bin_size,\n num_processes=None,\n safe_mode=True,\n mp_start_method='spawn',\n)\nPack sequences into bins using parallel processing\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nsequence_lengths\nnp.ndarray\nArray of sequence lengths\nrequired\n\n\nbin_capacity\nint\nMaximum capacity of each bin as total number of tokens\nrequired\n\n\ngroup_size\nint\nNumber of sequences to process in each group\nrequired\n\n\nbin_size\nint\nMaximum number of bins to use\nrequired\n\n\nnum_processes\nint | None\nNumber of parallel processes to use\nNone\n\n\nsafe_mode\nbool\nIf True, use a more conservative packing approach\nTrue\n\n\nmp_start_method\nstr | None\nMultiprocessing start method (‘fork’, ‘spawn’, ‘forkserver’). ‘spawn’ is often safer with Numba/PyTorch. Set to None to use system default.\n'spawn'\n\n\n\nReturns:\nList of bins, where each bin contains indices of sequences assigned to it" + "text": "kernels.utils\nkernels.utils\nUtilities for axolotl.kernels submodules." }, { - "objectID": "docs/api/prompt_strategies.dpo.user_defined.html", - "href": "docs/api/prompt_strategies.dpo.user_defined.html", - "title": "prompt_strategies.dpo.user_defined", + "objectID": "docs/api/utils.schemas.model.html", + "href": "docs/api/utils.schemas.model.html", + "title": "utils.schemas.model", "section": "", - "text": "prompt_strategies.dpo.user_defined\nprompt_strategies.dpo.user_defined\nUser-defined DPO strategies" + "text": "utils.schemas.model\nPydantic models for model input / output, etc. configuration\n\n\n\n\n\nName\nDescription\n\n\n\n\nModelInputConfig\nModel configuration subset\n\n\nModelOutputConfig\nmodel save configuration subset\n\n\nSpecialTokensConfig\nSpecial tokens configuration subset\n\n\n\n\n\nutils.schemas.model.ModelInputConfig()\nModel configuration subset\n\n\n\nutils.schemas.model.ModelOutputConfig()\nmodel save configuration subset\n\n\n\nutils.schemas.model.SpecialTokensConfig()\nSpecial tokens configuration subset" }, { - "objectID": "docs/api/utils.schemas.training.html", - "href": "docs/api/utils.schemas.training.html", - "title": "utils.schemas.training", + "objectID": "docs/api/utils.schemas.model.html#classes", + "href": "docs/api/utils.schemas.model.html#classes", + "title": "utils.schemas.model", "section": "", - "text": "utils.schemas.training\nPydantic models for training hyperparameters\n\n\n\n\n\nName\nDescription\n\n\n\n\nHyperparametersConfig\nTraining hyperparams configuration subset\n\n\nLrGroup\nCustom learning rate group configuration\n\n\n\n\n\nutils.schemas.training.HyperparametersConfig()\nTraining hyperparams configuration subset\n\n\n\nutils.schemas.training.LrGroup()\nCustom learning rate group configuration" + "text": "Name\nDescription\n\n\n\n\nModelInputConfig\nModel configuration subset\n\n\nModelOutputConfig\nmodel save configuration subset\n\n\nSpecialTokensConfig\nSpecial tokens configuration subset\n\n\n\n\n\nutils.schemas.model.ModelInputConfig()\nModel configuration subset\n\n\n\nutils.schemas.model.ModelOutputConfig()\nmodel save configuration subset\n\n\n\nutils.schemas.model.SpecialTokensConfig()\nSpecial tokens configuration subset" }, { - "objectID": "docs/api/utils.schemas.training.html#classes", - "href": "docs/api/utils.schemas.training.html#classes", - "title": "utils.schemas.training", + "objectID": "docs/api/utils.data.pretraining.html", + "href": "docs/api/utils.data.pretraining.html", + "title": "utils.data.pretraining", "section": "", - "text": "Name\nDescription\n\n\n\n\nHyperparametersConfig\nTraining hyperparams configuration subset\n\n\nLrGroup\nCustom learning rate group configuration\n\n\n\n\n\nutils.schemas.training.HyperparametersConfig()\nTraining hyperparams configuration subset\n\n\n\nutils.schemas.training.LrGroup()\nCustom learning rate group configuration" + "text": "utils.data.pretraining\nutils.data.pretraining\ndata handling specific to pretraining" }, { - "objectID": "docs/api/utils.callbacks.perplexity.html", - "href": "docs/api/utils.callbacks.perplexity.html", - "title": "utils.callbacks.perplexity", + "objectID": "docs/api/utils.callbacks.lisa.html", + "href": "docs/api/utils.callbacks.lisa.html", + "title": "utils.callbacks.lisa", "section": "", - "text": "utils.callbacks.perplexity\ncallback to calculate perplexity as an evaluation metric.\n\n\n\n\n\nName\nDescription\n\n\n\n\nPerplexity\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity(self, tokenizer, max_seq_len, stride=512)\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\nThis is a custom variant that doesn’t re-tokenize the input or re-load the model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncompute\nCompute perplexity in a fixed length sliding window across the sequence.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity.compute(model, references=None)\nCompute perplexity in a fixed length sliding window across the sequence." + "text": "utils.callbacks.lisa\nutils.callbacks.lisa\nmodule for LISA\nAdapted from https://github.com/OptimalScale/LMFlow/pull/701 for HF transformers & Axolotl\nArxiv: https://arxiv.org/abs/2403.17919\nLicense: Apache 2.0" }, { - "objectID": "docs/api/utils.callbacks.perplexity.html#classes", - "href": "docs/api/utils.callbacks.perplexity.html#classes", - "title": "utils.callbacks.perplexity", + "objectID": "docs/api/utils.optimizers.adopt.html", + "href": "docs/api/utils.optimizers.adopt.html", + "title": "utils.optimizers.adopt", "section": "", - "text": "Name\nDescription\n\n\n\n\nPerplexity\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity(self, tokenizer, max_seq_len, stride=512)\nCalculate perplexity as defined in https://huggingface.co/docs/transformers/en/perplexity.\nThis is a custom variant that doesn’t re-tokenize the input or re-load the model.\n\n\n\n\n\nName\nDescription\n\n\n\n\ncompute\nCompute perplexity in a fixed length sliding window across the sequence.\n\n\n\n\n\nutils.callbacks.perplexity.Perplexity.compute(model, references=None)\nCompute perplexity in a fixed length sliding window across the sequence." + "text": "utils.optimizers.adopt\nCopied from https://github.com/iShohei220/adopt\nADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate (2024)\nTaniguchi, Shohei and Harada, Keno and Minegishi, Gouki and Oshima, Yuta and Jeong, Seong Cheol and Nagahara, Go and Iiyama, Tomoshi and Suzuki, Masahiro and Iwasawa, Yusuke and Matsuo, Yutaka\n\n\n\n\n\nName\nDescription\n\n\n\n\nadopt\nFunctional API that performs ADOPT algorithm computation.\n\n\n\n\n\nutils.optimizers.adopt.adopt(\n params,\n grads,\n exp_avgs,\n exp_avg_sqs,\n state_steps,\n foreach=None,\n capturable=False,\n differentiable=False,\n fused=None,\n grad_scale=None,\n found_inf=None,\n has_complex=False,\n *,\n beta1,\n beta2,\n lr,\n clip_lambda,\n weight_decay,\n decouple,\n eps,\n maximize,\n)\nFunctional API that performs ADOPT algorithm computation." }, { - "objectID": "docs/api/kernels.lora.html", - "href": "docs/api/kernels.lora.html", - "title": "kernels.lora", + "objectID": "docs/api/utils.optimizers.adopt.html#functions", + "href": "docs/api/utils.optimizers.adopt.html#functions", + "title": "utils.optimizers.adopt", "section": "", - "text": "kernels.lora\nModule for definition of Low-Rank Adaptation (LoRA) Triton kernels.\nSee “LoRA: Low-Rank Adaptation of Large Language Models”\n(https://arxiv.org/abs/2106.09685).\nCredit to unsloth (https://unsloth.ai/) for inspiration for this implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nLoRA_MLP\nOptimized LoRA MLP implementation.\n\n\nLoRA_O\nOptimized LoRA implementation for output projection.\n\n\nLoRA_QKV\nOptimized LoRA QKV implementation with quantization support.\n\n\n\n\n\nkernels.lora.LoRA_MLP()\nOptimized LoRA MLP implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nPerforms backward pass computation for LoRA MLP.\n\n\nforward\nForward pass for LoRA MLP.\n\n\n\n\n\nkernels.lora.LoRA_MLP.backward(ctx, grad_output)\nPerforms backward pass computation for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nContext object storing tensors saved during forward pass\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to layer output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor | None\nTuple containing gradients for all inputs from forward pass:\n\n\n\nNone\n- Input gradient tensor (or None)\n\n\n\nNone\n- None for weights/quantization states\n\n\n\ntorch.Tensor | None\n- LoRA A/B matrix gradients (or None)\n\n\n\ntorch.Tensor | None\n- None for scaling factors\n\n\n\nNone\n- None for activation functions and flags\n\n\n\n\n\n\n\nkernels.lora.LoRA_MLP.forward(\n ctx,\n X,\n gate_weight,\n gate_quant,\n gate_A,\n gate_B,\n gate_scale,\n up_weight,\n up_quant,\n up_A,\n up_B,\n up_scale,\n down_weight,\n down_quant,\n down_A,\n down_B,\n down_scale,\n activation_fn,\n activation_fn_backward,\n inplace=True,\n)\nForward pass for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\n\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput features\nrequired\n\n\ngate_weight\ntorch.Tensor\nGate projection weight\nrequired\n\n\ngate_quant\nobject | None\nGate quantization state\nrequired\n\n\ngate_A\ntorch.Tensor | None\nGate LoRA A matrix\nrequired\n\n\ngate_B\ntorch.Tensor | None\nGate LoRA B matrix\nrequired\n\n\ngate_scale\nfloat\nGate LoRA scale\nrequired\n\n\nup_weight\ntorch.Tensor\nUp-projection weight\nrequired\n\n\nup_quant\nobject | None\nUp-projection quantization state\nrequired\n\n\nup_A\ntorch.Tensor | None\nUp-projection LoRA A matrix\nrequired\n\n\nup_B\ntorch.Tensor | None\nUp-projection LoRA B matrix\nrequired\n\n\nup_scale\nfloat\nUp-projection LoRA scale\nrequired\n\n\ndown_weight\ntorch.Tensor\nDown-projection weight\nrequired\n\n\ndown_quant\nobject | None\nDown-projection quantization state\nrequired\n\n\ndown_A\ntorch.Tensor | None\nDown-projection LoRA A matrix\nrequired\n\n\ndown_B\ntorch.Tensor | None\nDown-projection LoRA B matrix\nrequired\n\n\ndown_scale\nfloat\nDown-projection LoRA scale\nrequired\n\n\nactivation_fn\nCallable\nForward activation function\nrequired\n\n\nactivation_fn_backward\nCallable\nBackward activation function\nrequired\n\n\ninplace\nbool | None\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput transformed by multi-layer perceptron and activation function\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_O()\nOptimized LoRA implementation for output projection.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA output projection.\n\n\nforward\nForward pass for output projection with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_O.backward(ctx, dY)\nBackward pass computing gradients for LoRA output projection.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\ndY\ntorch.Tensor\nGradient of loss with respect to output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_O.forward(ctx, X, W, W_quant, A, B, S)\nForward pass for output projection with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nW\ntorch.Tensor\nOutput projection weight\nrequired\n\n\nW_quant\nQuantState | None\nWeight quantization state\nrequired\n\n\nA\ntorch.Tensor | None\nLoRA A matrix\nrequired\n\n\nB\ntorch.Tensor | None\nLoRA B matrix\nrequired\n\n\nS\nfloat\nLoRA scaling factor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput projection tensor\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV()\nOptimized LoRA QKV implementation with quantization support.\nImplements efficient computation of query, key, value projections with LoRA,\nsupporting quantization and memory optimization.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA QKV.\n\n\nforward\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_QKV.backward(ctx, q_grad, k_grad, v_grad)\nBackward pass computing gradients for LoRA QKV.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nq_grad\ntorch.Tensor\nGradient for query projection\nrequired\n\n\nk_grad\ntorch.Tensor\nGradient for key projection\nrequired\n\n\nv_grad\ntorch.Tensor\nGradient for value projection\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV.forward(\n ctx,\n X,\n q_weight,\n q_quant,\n q_A,\n q_B,\n q_scale,\n k_weight,\n k_quant,\n k_A,\n k_B,\n k_scale,\n v_weight,\n v_quant,\n v_A,\n v_B,\n v_scale,\n inplace=True,\n)\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nq_weight\ntorch.Tensor\nQuery projection weight\nrequired\n\n\nq_quant\nQuantState | None\nQuery quantization state\nrequired\n\n\nq_A\ntorch.Tensor | None\nQuery LoRA A matrix\nrequired\n\n\nq_B\ntorch.Tensor | None\nQuery LoRA B matrix\nrequired\n\n\nq_scale\nfloat\nQuery LoRA scale\nrequired\n\n\nk_weight\ntorch.Tensor\nKey projection weight\nrequired\n\n\nk_quant\nQuantState | None\nKey quantization state\nrequired\n\n\nk_A\ntorch.Tensor | None\nKey LoRA A matrix\nrequired\n\n\nk_B\ntorch.Tensor | None\nKey LoRA B matrix\nrequired\n\n\nk_scale\nfloat\nKey LoRA scale\nrequired\n\n\nv_weight\ntorch.Tensor\nValue projection weight\nrequired\n\n\nv_quant\nQuantState | None\nValue quantization state\nrequired\n\n\nv_A\ntorch.Tensor | None\nValue LoRA A matrix\nrequired\n\n\nv_B\ntorch.Tensor | None\nValue LoRA B matrix\nrequired\n\n\nv_scale\nfloat\nValue LoRA scale\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\napply_lora_mlp_geglu\nApplies LoRA to MLP layer with GEGLU activation.\n\n\napply_lora_mlp_swiglu\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\napply_lora_o\nApplies LoRA to output projection layer.\n\n\napply_lora_qkv\nApplies LoRA to compute Query, Key, Value projections.\n\n\nget_lora_parameters\nGets LoRA parameters from a projection module.\n\n\nmatmul_lora\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\nkernels.lora.apply_lora_mlp_geglu(self, X, inplace=True)\nApplies LoRA to MLP layer with GEGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with GEGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_mlp_swiglu(self, X, inplace=True)\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with SwiGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_o(self, X)\nApplies LoRA to output projection layer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTransformed output tensor\n\n\n\n\n\n\n\nkernels.lora.apply_lora_qkv(self, X, inplace=True)\nApplies LoRA to compute Query, Key, Value projections.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors\n\n\n\n\n\n\n\nkernels.lora.get_lora_parameters(proj)\nGets LoRA parameters from a projection module.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nproj\nnn.Module\nThe projection module to extract parameters from.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nA tuple containing the base weight matrix, quantization state, LoRA A matrix,\n\n\n\nQuantState | None\nLoRA B matrix, and scaling factor. States and matrices may be None if not\n\n\n\ntorch.Tensor | None\navailable.\n\n\n\n\n\n\n\nkernels.lora.matmul_lora(X, W, W_quant, A, B, s, out=None)\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor [*, in_features]\nrequired\n\n\nW\ntorch.Tensor\nBase weight matrix [out_features, in_features]\nrequired\n\n\nW_quant\nQuantState\nQuantization state for W\nrequired\n\n\nA\ntorch.Tensor\nLoRA A matrix [rank, in_features]\nrequired\n\n\nB\ntorch.Tensor\nLoRA B matrix [out_features, rank]\nrequired\n\n\ns\nfloat\nLoRA scaling factor\nrequired\n\n\nout\ntorch.Tensor | None\nOptional output tensor for inplace operations\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nResult of X @ W + X @ A @ B" + "text": "Name\nDescription\n\n\n\n\nadopt\nFunctional API that performs ADOPT algorithm computation.\n\n\n\n\n\nutils.optimizers.adopt.adopt(\n params,\n grads,\n exp_avgs,\n exp_avg_sqs,\n state_steps,\n foreach=None,\n capturable=False,\n differentiable=False,\n fused=None,\n grad_scale=None,\n found_inf=None,\n has_complex=False,\n *,\n beta1,\n beta2,\n lr,\n clip_lambda,\n weight_decay,\n decouple,\n eps,\n maximize,\n)\nFunctional API that performs ADOPT algorithm computation." }, { - "objectID": "docs/api/kernels.lora.html#classes", - "href": "docs/api/kernels.lora.html#classes", - "title": "kernels.lora", + "objectID": "docs/api/common.architectures.html", + "href": "docs/api/common.architectures.html", + "title": "common.architectures", "section": "", - "text": "Name\nDescription\n\n\n\n\nLoRA_MLP\nOptimized LoRA MLP implementation.\n\n\nLoRA_O\nOptimized LoRA implementation for output projection.\n\n\nLoRA_QKV\nOptimized LoRA QKV implementation with quantization support.\n\n\n\n\n\nkernels.lora.LoRA_MLP()\nOptimized LoRA MLP implementation.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nPerforms backward pass computation for LoRA MLP.\n\n\nforward\nForward pass for LoRA MLP.\n\n\n\n\n\nkernels.lora.LoRA_MLP.backward(ctx, grad_output)\nPerforms backward pass computation for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nContext object storing tensors saved during forward pass\nrequired\n\n\ngrad_output\ntorch.Tensor\nGradient of loss with respect to layer output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor | None\nTuple containing gradients for all inputs from forward pass:\n\n\n\nNone\n- Input gradient tensor (or None)\n\n\n\nNone\n- None for weights/quantization states\n\n\n\ntorch.Tensor | None\n- LoRA A/B matrix gradients (or None)\n\n\n\ntorch.Tensor | None\n- None for scaling factors\n\n\n\nNone\n- None for activation functions and flags\n\n\n\n\n\n\n\nkernels.lora.LoRA_MLP.forward(\n ctx,\n X,\n gate_weight,\n gate_quant,\n gate_A,\n gate_B,\n gate_scale,\n up_weight,\n up_quant,\n up_A,\n up_B,\n up_scale,\n down_weight,\n down_quant,\n down_A,\n down_B,\n down_scale,\n activation_fn,\n activation_fn_backward,\n inplace=True,\n)\nForward pass for LoRA MLP.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\n\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput features\nrequired\n\n\ngate_weight\ntorch.Tensor\nGate projection weight\nrequired\n\n\ngate_quant\nobject | None\nGate quantization state\nrequired\n\n\ngate_A\ntorch.Tensor | None\nGate LoRA A matrix\nrequired\n\n\ngate_B\ntorch.Tensor | None\nGate LoRA B matrix\nrequired\n\n\ngate_scale\nfloat\nGate LoRA scale\nrequired\n\n\nup_weight\ntorch.Tensor\nUp-projection weight\nrequired\n\n\nup_quant\nobject | None\nUp-projection quantization state\nrequired\n\n\nup_A\ntorch.Tensor | None\nUp-projection LoRA A matrix\nrequired\n\n\nup_B\ntorch.Tensor | None\nUp-projection LoRA B matrix\nrequired\n\n\nup_scale\nfloat\nUp-projection LoRA scale\nrequired\n\n\ndown_weight\ntorch.Tensor\nDown-projection weight\nrequired\n\n\ndown_quant\nobject | None\nDown-projection quantization state\nrequired\n\n\ndown_A\ntorch.Tensor | None\nDown-projection LoRA A matrix\nrequired\n\n\ndown_B\ntorch.Tensor | None\nDown-projection LoRA B matrix\nrequired\n\n\ndown_scale\nfloat\nDown-projection LoRA scale\nrequired\n\n\nactivation_fn\nCallable\nForward activation function\nrequired\n\n\nactivation_fn_backward\nCallable\nBackward activation function\nrequired\n\n\ninplace\nbool | None\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput transformed by multi-layer perceptron and activation function\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_O()\nOptimized LoRA implementation for output projection.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA output projection.\n\n\nforward\nForward pass for output projection with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_O.backward(ctx, dY)\nBackward pass computing gradients for LoRA output projection.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\ndY\ntorch.Tensor\nGradient of loss with respect to output\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_O.forward(ctx, X, W, W_quant, A, B, S)\nForward pass for output projection with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nW\ntorch.Tensor\nOutput projection weight\nrequired\n\n\nW_quant\nQuantState | None\nWeight quantization state\nrequired\n\n\nA\ntorch.Tensor | None\nLoRA A matrix\nrequired\n\n\nB\ntorch.Tensor | None\nLoRA B matrix\nrequired\n\n\nS\nfloat\nLoRA scaling factor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput projection tensor\n\n\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV()\nOptimized LoRA QKV implementation with quantization support.\nImplements efficient computation of query, key, value projections with LoRA,\nsupporting quantization and memory optimization.\n\n\n\n\n\nName\nDescription\n\n\n\n\nbackward\nBackward pass computing gradients for LoRA QKV.\n\n\nforward\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\nkernels.lora.LoRA_QKV.backward(ctx, q_grad, k_grad, v_grad)\nBackward pass computing gradients for LoRA QKV.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nq_grad\ntorch.Tensor\nGradient for query projection\nrequired\n\n\nk_grad\ntorch.Tensor\nGradient for key projection\nrequired\n\n\nv_grad\ntorch.Tensor\nGradient for value projection\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None, None, torch.Tensor | None, torch.Tensor | None, None, None]\nTuple containing gradients for all forward inputs\n\n\n\n\n\n\n\nkernels.lora.LoRA_QKV.forward(\n ctx,\n X,\n q_weight,\n q_quant,\n q_A,\n q_B,\n q_scale,\n k_weight,\n k_quant,\n k_A,\n k_B,\n k_scale,\n v_weight,\n v_quant,\n v_A,\n v_B,\n v_scale,\n inplace=True,\n)\nForward pass computing Q, K, V projections with LoRA.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nctx\ntorch.autograd.function.FunctionCtx\nAutograd context\nrequired\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\nq_weight\ntorch.Tensor\nQuery projection weight\nrequired\n\n\nq_quant\nQuantState | None\nQuery quantization state\nrequired\n\n\nq_A\ntorch.Tensor | None\nQuery LoRA A matrix\nrequired\n\n\nq_B\ntorch.Tensor | None\nQuery LoRA B matrix\nrequired\n\n\nq_scale\nfloat\nQuery LoRA scale\nrequired\n\n\nk_weight\ntorch.Tensor\nKey projection weight\nrequired\n\n\nk_quant\nQuantState | None\nKey quantization state\nrequired\n\n\nk_A\ntorch.Tensor | None\nKey LoRA A matrix\nrequired\n\n\nk_B\ntorch.Tensor | None\nKey LoRA B matrix\nrequired\n\n\nk_scale\nfloat\nKey LoRA scale\nrequired\n\n\nv_weight\ntorch.Tensor\nValue projection weight\nrequired\n\n\nv_quant\nQuantState | None\nValue quantization state\nrequired\n\n\nv_A\ntorch.Tensor | None\nValue LoRA A matrix\nrequired\n\n\nv_B\ntorch.Tensor | None\nValue LoRA B matrix\nrequired\n\n\nv_scale\nfloat\nValue LoRA scale\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors" - }, - { - "objectID": "docs/api/kernels.lora.html#functions", - "href": "docs/api/kernels.lora.html#functions", - "title": "kernels.lora", - "section": "", - "text": "Name\nDescription\n\n\n\n\napply_lora_mlp_geglu\nApplies LoRA to MLP layer with GEGLU activation.\n\n\napply_lora_mlp_swiglu\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\napply_lora_o\nApplies LoRA to output projection layer.\n\n\napply_lora_qkv\nApplies LoRA to compute Query, Key, Value projections.\n\n\nget_lora_parameters\nGets LoRA parameters from a projection module.\n\n\nmatmul_lora\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\nkernels.lora.apply_lora_mlp_geglu(self, X, inplace=True)\nApplies LoRA to MLP layer with GEGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with GEGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_mlp_swiglu(self, X, inplace=True)\nApplies LoRA to MLP layer with SwiGLU activation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor for the MLP layer\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place to save memory\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nOutput tensor after applying LoRA-adapted MLP with SwiGLU activation\n\n\n\n\n\n\n\nkernels.lora.apply_lora_o(self, X)\nApplies LoRA to output projection layer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nTransformed output tensor\n\n\n\n\n\n\n\nkernels.lora.apply_lora_qkv(self, X, inplace=True)\nApplies LoRA to compute Query, Key, Value projections.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor\nrequired\n\n\ninplace\nbool\nWhether to perform operations in-place\nTrue\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntuple[torch.Tensor, torch.Tensor, torch.Tensor]\nTuple of (Query, Key, Value) projection tensors\n\n\n\n\n\n\n\nkernels.lora.get_lora_parameters(proj)\nGets LoRA parameters from a projection module.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nproj\nnn.Module\nThe projection module to extract parameters from.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nA tuple containing the base weight matrix, quantization state, LoRA A matrix,\n\n\n\nQuantState | None\nLoRA B matrix, and scaling factor. States and matrices may be None if not\n\n\n\ntorch.Tensor | None\navailable.\n\n\n\n\n\n\n\nkernels.lora.matmul_lora(X, W, W_quant, A, B, s, out=None)\nEfficient fused matmul + LoRA computation.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\nX\ntorch.Tensor\nInput tensor [*, in_features]\nrequired\n\n\nW\ntorch.Tensor\nBase weight matrix [out_features, in_features]\nrequired\n\n\nW_quant\nQuantState\nQuantization state for W\nrequired\n\n\nA\ntorch.Tensor\nLoRA A matrix [rank, in_features]\nrequired\n\n\nB\ntorch.Tensor\nLoRA B matrix [out_features, rank]\nrequired\n\n\ns\nfloat\nLoRA scaling factor\nrequired\n\n\nout\ntorch.Tensor | None\nOptional output tensor for inplace operations\nNone\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ntorch.Tensor\nResult of X @ W + X @ A @ B" - }, - { - "objectID": "docs/api/core.chat.messages.html", - "href": "docs/api/core.chat.messages.html", - "title": "core.chat.messages", - "section": "", - "text": "core.chat.messages\ninternal message representations of chat messages\n\n\n\n\n\nName\nDescription\n\n\n\n\nChatFormattedChats\nChat formatted chats with formatter and optional train on inputs\n\n\nChats\ntop level data structure for chat conversations\n\n\nMessageContentTypes\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\nMessageContents\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\nMessageRoles\nMessage roles for the system, user, assistant, and tools\n\n\nMessages\nMessages with role, content, metadata, weight, and chat formatting\n\n\nPreferenceChats\nrepresentation for preference data for chat\n\n\nSpecialToken\nSpecial tokens for beginning of string and end of string\n\n\nTool\nTool with description, function, and parameters\n\n\nToolCallContents\nTool call contents with name, arguments, and optional id\n\n\nToolCallFunction\nTool call function with name and arguments\n\n\nToolResponseContents\nTool response contents with name, content, and optional id\n\n\n\n\n\ncore.chat.messages.ChatFormattedChats()\nChat formatted chats with formatter and optional train on inputs\n\n\n\ncore.chat.messages.Chats()\ntop level data structure for chat conversations\n\n\n\ncore.chat.messages.MessageContentTypes()\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\n\ncore.chat.messages.MessageContents()\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\n\ncore.chat.messages.MessageRoles()\nMessage roles for the system, user, assistant, and tools\n\n\n\ncore.chat.messages.Messages()\nMessages with role, content, metadata, weight, and chat formatting\n\n\n\ncore.chat.messages.PreferenceChats()\nrepresentation for preference data for chat\n\n\n\ncore.chat.messages.SpecialToken()\nSpecial tokens for beginning of string and end of string\n\n\n\ncore.chat.messages.Tool()\nTool with description, function, and parameters\n\n\n\ncore.chat.messages.ToolCallContents()\nTool call contents with name, arguments, and optional id\n\n\n\ncore.chat.messages.ToolCallFunction()\nTool call function with name and arguments\n\n\n\ncore.chat.messages.ToolResponseContents()\nTool response contents with name, content, and optional id" - }, - { - "objectID": "docs/api/core.chat.messages.html#classes", - "href": "docs/api/core.chat.messages.html#classes", - "title": "core.chat.messages", - "section": "", - "text": "Name\nDescription\n\n\n\n\nChatFormattedChats\nChat formatted chats with formatter and optional train on inputs\n\n\nChats\ntop level data structure for chat conversations\n\n\nMessageContentTypes\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\nMessageContents\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\nMessageRoles\nMessage roles for the system, user, assistant, and tools\n\n\nMessages\nMessages with role, content, metadata, weight, and chat formatting\n\n\nPreferenceChats\nrepresentation for preference data for chat\n\n\nSpecialToken\nSpecial tokens for beginning of string and end of string\n\n\nTool\nTool with description, function, and parameters\n\n\nToolCallContents\nTool call contents with name, arguments, and optional id\n\n\nToolCallFunction\nTool call function with name and arguments\n\n\nToolResponseContents\nTool response contents with name, content, and optional id\n\n\n\n\n\ncore.chat.messages.ChatFormattedChats()\nChat formatted chats with formatter and optional train on inputs\n\n\n\ncore.chat.messages.Chats()\ntop level data structure for chat conversations\n\n\n\ncore.chat.messages.MessageContentTypes()\nMessage content types for text, image, audio, tool calls, and tool responses\n\n\n\ncore.chat.messages.MessageContents()\nMessage contents with type, value, metadata, weight, newline, and end of contents\n\n\n\ncore.chat.messages.MessageRoles()\nMessage roles for the system, user, assistant, and tools\n\n\n\ncore.chat.messages.Messages()\nMessages with role, content, metadata, weight, and chat formatting\n\n\n\ncore.chat.messages.PreferenceChats()\nrepresentation for preference data for chat\n\n\n\ncore.chat.messages.SpecialToken()\nSpecial tokens for beginning of string and end of string\n\n\n\ncore.chat.messages.Tool()\nTool with description, function, and parameters\n\n\n\ncore.chat.messages.ToolCallContents()\nTool call contents with name, arguments, and optional id\n\n\n\ncore.chat.messages.ToolCallFunction()\nTool call function with name and arguments\n\n\n\ncore.chat.messages.ToolResponseContents()\nTool response contents with name, content, and optional id" - }, - { - "objectID": "docs/api/integrations.base.html", - "href": "docs/api/integrations.base.html", - "title": "integrations.base", - "section": "", - "text": "integrations.base\nBase class for all plugins.\nA plugin is a reusable, modular, and self-contained piece of code that extends the functionality of Axolotl.\nPlugins can be used to integrate third-party models, modify the training process, or add new features.\nTo create a new plugin, you need to inherit from the BasePlugin class and implement the required methods.\n\n\n\n\n\nName\nDescription\n\n\n\n\nBaseOptimizerFactory\nBase class for factories to create custom optimizers\n\n\nBasePlugin\nBase class for all plugins. Defines the interface for plugin methods.\n\n\nPluginManager\nThe PluginManager class is responsible for loading and managing plugins.\n\n\n\n\n\nintegrations.base.BaseOptimizerFactory()\nBase class for factories to create custom optimizers\n\n\n\nintegrations.base.BasePlugin(self)\nBase class for all plugins. Defines the interface for plugin methods.\nAttributes:\nNone\nMethods:\nregister(cfg): Registers the plugin with the given configuration.\nload_datasets(cfg): Loads and preprocesses the dataset for training.\npre_model_load(cfg): Performs actions before the model is loaded.\npost_model_build(cfg, model): Performs actions after the model is loaded, but before LoRA adapters are applied.\npre_lora_load(cfg, model): Performs actions before LoRA weights are loaded.\npost_lora_load(cfg, model): Performs actions after LoRA weights are loaded.\npost_model_load(cfg, model): Performs actions after the model is loaded, inclusive of any adapters.\npost_trainer_create(cfg, trainer): Performs actions after the trainer is created.\ncreate_optimizer(cfg, trainer): Creates and returns an optimizer for training.\ncreate_lr_scheduler(cfg, trainer, optimizer, num_training_steps): Creates and returns a learning rate scheduler.\nadd_callbacks_pre_trainer(cfg, model): Adds callbacks to the trainer before training.\nadd_callbacks_post_trainer(cfg, trainer): Adds callbacks to the trainer after training.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nAdds callbacks to the trainer after creating the trainer.\n\n\nadd_callbacks_pre_trainer\nsetup callbacks before creating the trainer.\n\n\ncreate_lr_scheduler\nCreates and returns a learning rate scheduler.\n\n\ncreate_optimizer\nCreates and returns an optimizer for training.\n\n\nget_input_args\nReturns a pydantic model for the plugin’s input arguments.\n\n\nget_trainer_cls\nReturns a custom class for the trainer.\n\n\nload_datasets\nLoads and preprocesses the dataset for training.\n\n\npost_lora_load\nPerforms actions after LoRA weights are loaded.\n\n\npost_model_build\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\npost_model_load\nPerforms actions after the model is loaded.\n\n\npost_train\nPerforms actions after training is complete.\n\n\npost_train_unload\nPerforms actions after training is complete and the model is unloaded.\n\n\npost_trainer_create\nPerforms actions after the trainer is created.\n\n\npre_lora_load\nPerforms actions before LoRA weights are loaded.\n\n\npre_model_load\nPerforms actions before the model is loaded.\n\n\nregister\nRegisters the plugin with the given configuration.\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_post_trainer(cfg, trainer)\nAdds callbacks to the trainer after creating the trainer.\nThis is useful for callbacks that require access to the model or trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_pre_trainer(cfg, model)\nsetup callbacks before creating the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added to the TrainingArgs\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_lr_scheduler(\n cfg,\n trainer,\n optimizer,\n num_training_steps,\n)\nCreates and returns a learning rate scheduler.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\noptimizer\nobject\nThe optimizer for training.\nrequired\n\n\nnum_training_steps\nint\nTotal number of training steps\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\nLRScheduler\nThe created learning rate scheduler.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_optimizer(cfg, trainer)\nCreates and returns an optimizer for training.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\n\nThe created optimizer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.get_input_args()\nReturns a pydantic model for the plugin’s input arguments.\n\n\n\nintegrations.base.BasePlugin.get_trainer_cls(cfg)\nReturns a custom class for the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe global axolotl configuration.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nclass\n\nThe class for the trainer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.load_datasets(cfg, preprocess=False)\nLoads and preprocesses the dataset for training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration for the plugin.\nrequired\n\n\npreprocess\nbool\nWhether this is the preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe metadata for the training dataset.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_lora_load(cfg, model)\nPerforms actions after LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_build(cfg, model)\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_load(cfg, model)\nPerforms actions after the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train(cfg, model)\nPerforms actions after training is complete.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe axolotl configuration\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train_unload(cfg)\nPerforms actions after training is complete and the model is unloaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_trainer_create(cfg, trainer)\nPerforms actions after the trainer is created.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_lora_load(cfg, model)\nPerforms actions before LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_model_load(cfg)\nPerforms actions before the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.register(cfg)\nRegisters the plugin with the given configuration.\nParameters:\ncfg (dict): The configuration for the plugin.\nReturns:\nNone\n\n\n\n\n\nintegrations.base.PluginManager()\nThe PluginManager class is responsible for loading and managing plugins.\nIt should be a singleton so it can be accessed from anywhere in the codebase.\nAttributes:\nplugins (ListBasePlugin): A list of loaded plugins.\nMethods:\nget_instance(): Static method to get the singleton instance of PluginManager.\nregister(plugin_name: str): Registers a new plugin by its name.\npre_model_load(cfg): Calls the pre_model_load method of all registered plugins.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nCalls the add_callbacks_post_trainer method of all registered plugins.\n\n\nadd_callbacks_pre_trainer\nCalls the add_callbacks_pre_trainer method of all registered plugins.\n\n\ncreate_lr_scheduler\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\n\n\ncreate_optimizer\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\n\n\nget_input_args\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\n\n\nget_instance\nReturns the singleton instance of PluginManager.\n\n\nget_trainer_cls\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\n\n\nload_datasets\nCalls the load_datasets method of each registered plugin.\n\n\npost_lora_load\nCalls the post_lora_load method of all registered plugins.\n\n\npost_model_build\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\n\n\npost_model_load\nCalls the post_model_load method of all registered plugins after the model has been loaded\n\n\npost_train\nCalls the post_train method of all registered plugins.\n\n\npost_train_unload\nCalls the post_train_unload method of all registered plugins.\n\n\npost_trainer_create\nCalls the post_trainer_create method of all registered plugins.\n\n\npre_lora_load\nCalls the pre_lora_load method of all registered plugins.\n\n\npre_model_load\nCalls the pre_model_load method of all registered plugins.\n\n\nregister\nRegisters a new plugin by its name.\n\n\n\n\n\nintegrations.base.PluginManager.add_callbacks_post_trainer(cfg, trainer)\nCalls the add_callbacks_post_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.add_callbacks_pre_trainer(cfg, model)\nCalls the add_callbacks_pre_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.create_lr_scheduler(\n trainer,\n optimizer,\n num_training_steps,\n)\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\nParameters:\ntrainer (object): The trainer object for training.\noptimizer (object): The optimizer for training.\nReturns:\nobject: The created learning rate scheduler, or None if none was found.\n\n\n\nintegrations.base.PluginManager.create_optimizer(trainer)\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\nParameters:\ntrainer (object): The trainer object for training.\nReturns:\nobject: The created optimizer, or None if none was found.\n\n\n\nintegrations.base.PluginManager.get_input_args()\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\nReturns:\nlist[str]: A list of Pydantic classes for all registered plugins’ input arguments.’\n\n\n\nintegrations.base.PluginManager.get_instance()\nReturns the singleton instance of PluginManager.\nIf the instance doesn’t exist, it creates a new one.\n\n\n\nintegrations.base.PluginManager.get_trainer_cls(cfg)\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nobject: The trainer class, or None if none was found.\n\n\n\nintegrations.base.PluginManager.load_datasets(cfg, preprocess=False)\nCalls the load_datasets method of each registered plugin.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nThe configuration for the plugins.\nrequired\n\n\npreprocess\n\nWhether this is preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe dataset metadata loaded from all registered plugins.\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_lora_load(cfg, model)\nCalls the post_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_model_build(cfg, model)\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\nbut before any adapters have been applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugins.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_model_load(cfg, model)\nCalls the post_model_load method of all registered plugins after the model has been loaded\ninclusive of any adapters\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train(cfg, model)\nCalls the post_train method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train_unload(cfg)\nCalls the post_train_unload method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_trainer_create(cfg, trainer)\nCalls the post_trainer_create method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_lora_load(cfg, model)\nCalls the pre_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_model_load(cfg)\nCalls the pre_model_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.register(plugin_name)\nRegisters a new plugin by its name.\nParameters:\nplugin_name (str): The name of the plugin to be registered.\nReturns:\nNone\nRaises:\nImportError: If the plugin module cannot be imported.\n\n\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nload_plugin\nLoads a plugin based on the given plugin name.\n\n\n\n\n\nintegrations.base.load_plugin(plugin_name)\nLoads a plugin based on the given plugin name.\nThe plugin name should be in the format “module_name.class_name”.\nThis function splits the plugin name into module and class, imports the module,\nretrieves the class from the module, and creates an instance of the class.\nParameters:\nplugin_name (str): The name of the plugin to be loaded. The name should be in the format “module_name.class_name”.\nReturns:\nBasePlugin: An instance of the loaded plugin.\nRaises:\nImportError: If the plugin module cannot be imported." - }, - { - "objectID": "docs/api/integrations.base.html#classes", - "href": "docs/api/integrations.base.html#classes", - "title": "integrations.base", - "section": "", - "text": "Name\nDescription\n\n\n\n\nBaseOptimizerFactory\nBase class for factories to create custom optimizers\n\n\nBasePlugin\nBase class for all plugins. Defines the interface for plugin methods.\n\n\nPluginManager\nThe PluginManager class is responsible for loading and managing plugins.\n\n\n\n\n\nintegrations.base.BaseOptimizerFactory()\nBase class for factories to create custom optimizers\n\n\n\nintegrations.base.BasePlugin(self)\nBase class for all plugins. Defines the interface for plugin methods.\nAttributes:\nNone\nMethods:\nregister(cfg): Registers the plugin with the given configuration.\nload_datasets(cfg): Loads and preprocesses the dataset for training.\npre_model_load(cfg): Performs actions before the model is loaded.\npost_model_build(cfg, model): Performs actions after the model is loaded, but before LoRA adapters are applied.\npre_lora_load(cfg, model): Performs actions before LoRA weights are loaded.\npost_lora_load(cfg, model): Performs actions after LoRA weights are loaded.\npost_model_load(cfg, model): Performs actions after the model is loaded, inclusive of any adapters.\npost_trainer_create(cfg, trainer): Performs actions after the trainer is created.\ncreate_optimizer(cfg, trainer): Creates and returns an optimizer for training.\ncreate_lr_scheduler(cfg, trainer, optimizer, num_training_steps): Creates and returns a learning rate scheduler.\nadd_callbacks_pre_trainer(cfg, model): Adds callbacks to the trainer before training.\nadd_callbacks_post_trainer(cfg, trainer): Adds callbacks to the trainer after training.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nAdds callbacks to the trainer after creating the trainer.\n\n\nadd_callbacks_pre_trainer\nsetup callbacks before creating the trainer.\n\n\ncreate_lr_scheduler\nCreates and returns a learning rate scheduler.\n\n\ncreate_optimizer\nCreates and returns an optimizer for training.\n\n\nget_input_args\nReturns a pydantic model for the plugin’s input arguments.\n\n\nget_trainer_cls\nReturns a custom class for the trainer.\n\n\nload_datasets\nLoads and preprocesses the dataset for training.\n\n\npost_lora_load\nPerforms actions after LoRA weights are loaded.\n\n\npost_model_build\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\npost_model_load\nPerforms actions after the model is loaded.\n\n\npost_train\nPerforms actions after training is complete.\n\n\npost_train_unload\nPerforms actions after training is complete and the model is unloaded.\n\n\npost_trainer_create\nPerforms actions after the trainer is created.\n\n\npre_lora_load\nPerforms actions before LoRA weights are loaded.\n\n\npre_model_load\nPerforms actions before the model is loaded.\n\n\nregister\nRegisters the plugin with the given configuration.\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_post_trainer(cfg, trainer)\nAdds callbacks to the trainer after creating the trainer.\nThis is useful for callbacks that require access to the model or trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.add_callbacks_pre_trainer(cfg, model)\nsetup callbacks before creating the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nList[callable]: A list of callback functions to be added to the TrainingArgs\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_lr_scheduler(\n cfg,\n trainer,\n optimizer,\n num_training_steps,\n)\nCreates and returns a learning rate scheduler.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\noptimizer\nobject\nThe optimizer for training.\nrequired\n\n\nnum_training_steps\nint\nTotal number of training steps\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\nLRScheduler\nThe created learning rate scheduler.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.create_optimizer(cfg, trainer)\nCreates and returns an optimizer for training.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nobject\n\nThe created optimizer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.get_input_args()\nReturns a pydantic model for the plugin’s input arguments.\n\n\n\nintegrations.base.BasePlugin.get_trainer_cls(cfg)\nReturns a custom class for the trainer.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe global axolotl configuration.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\nclass\n\nThe class for the trainer.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.load_datasets(cfg, preprocess=False)\nLoads and preprocesses the dataset for training.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\nDictDefault\nThe configuration for the plugin.\nrequired\n\n\npreprocess\nbool\nWhether this is the preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe metadata for the training dataset.\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_lora_load(cfg, model)\nPerforms actions after LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_build(cfg, model)\nPerforms actions after the model is built/loaded, but before any adapters are applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_model_load(cfg, model)\nPerforms actions after the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train(cfg, model)\nPerforms actions after training is complete.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe axolotl configuration\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_train_unload(cfg)\nPerforms actions after training is complete and the model is unloaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.post_trainer_create(cfg, trainer)\nPerforms actions after the trainer is created.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\ntrainer\nobject\nThe trainer object for training.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_lora_load(cfg, model)\nPerforms actions before LoRA weights are loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.pre_model_load(cfg)\nPerforms actions before the model is loaded.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugin.\nrequired\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\n\nNone\n\n\n\n\n\n\n\nintegrations.base.BasePlugin.register(cfg)\nRegisters the plugin with the given configuration.\nParameters:\ncfg (dict): The configuration for the plugin.\nReturns:\nNone\n\n\n\n\n\nintegrations.base.PluginManager()\nThe PluginManager class is responsible for loading and managing plugins.\nIt should be a singleton so it can be accessed from anywhere in the codebase.\nAttributes:\nplugins (ListBasePlugin): A list of loaded plugins.\nMethods:\nget_instance(): Static method to get the singleton instance of PluginManager.\nregister(plugin_name: str): Registers a new plugin by its name.\npre_model_load(cfg): Calls the pre_model_load method of all registered plugins.\n\n\n\n\n\nName\nDescription\n\n\n\n\nadd_callbacks_post_trainer\nCalls the add_callbacks_post_trainer method of all registered plugins.\n\n\nadd_callbacks_pre_trainer\nCalls the add_callbacks_pre_trainer method of all registered plugins.\n\n\ncreate_lr_scheduler\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\n\n\ncreate_optimizer\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\n\n\nget_input_args\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\n\n\nget_instance\nReturns the singleton instance of PluginManager.\n\n\nget_trainer_cls\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\n\n\nload_datasets\nCalls the load_datasets method of each registered plugin.\n\n\npost_lora_load\nCalls the post_lora_load method of all registered plugins.\n\n\npost_model_build\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\n\n\npost_model_load\nCalls the post_model_load method of all registered plugins after the model has been loaded\n\n\npost_train\nCalls the post_train method of all registered plugins.\n\n\npost_train_unload\nCalls the post_train_unload method of all registered plugins.\n\n\npost_trainer_create\nCalls the post_trainer_create method of all registered plugins.\n\n\npre_lora_load\nCalls the pre_lora_load method of all registered plugins.\n\n\npre_model_load\nCalls the pre_model_load method of all registered plugins.\n\n\nregister\nRegisters a new plugin by its name.\n\n\n\n\n\nintegrations.base.PluginManager.add_callbacks_post_trainer(cfg, trainer)\nCalls the add_callbacks_post_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.add_callbacks_pre_trainer(cfg, model)\nCalls the add_callbacks_pre_trainer method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nList[callable]: A list of callback functions to be added to the TrainingArgs.\n\n\n\nintegrations.base.PluginManager.create_lr_scheduler(\n trainer,\n optimizer,\n num_training_steps,\n)\nCalls the create_lr_scheduler method of all registered plugins and returns the first non-None scheduler.\nParameters:\ntrainer (object): The trainer object for training.\noptimizer (object): The optimizer for training.\nReturns:\nobject: The created learning rate scheduler, or None if none was found.\n\n\n\nintegrations.base.PluginManager.create_optimizer(trainer)\nCalls the create_optimizer method of all registered plugins and returns the first non-None optimizer.\nParameters:\ntrainer (object): The trainer object for training.\nReturns:\nobject: The created optimizer, or None if none was found.\n\n\n\nintegrations.base.PluginManager.get_input_args()\nReturns a list of Pydantic classes for all registered plugins’ input arguments.’\nReturns:\nlist[str]: A list of Pydantic classes for all registered plugins’ input arguments.’\n\n\n\nintegrations.base.PluginManager.get_instance()\nReturns the singleton instance of PluginManager.\nIf the instance doesn’t exist, it creates a new one.\n\n\n\nintegrations.base.PluginManager.get_trainer_cls(cfg)\nCalls the get_trainer_cls method of all registered plugins and returns the first non-None trainer class.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nobject: The trainer class, or None if none was found.\n\n\n\nintegrations.base.PluginManager.load_datasets(cfg, preprocess=False)\nCalls the load_datasets method of each registered plugin.\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\n\nThe configuration for the plugins.\nrequired\n\n\npreprocess\n\nWhether this is preprocess step of the datasets.\nFalse\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\ndataset_meta\n\nThe dataset metadata loaded from all registered plugins.\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_lora_load(cfg, model)\nCalls the post_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_model_build(cfg, model)\nCalls the post_model_build method of all registered plugins after the model has been built/loaded,\nbut before any adapters have been applied.\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ncfg\ndict\nThe configuration for the plugins.\nrequired\n\n\nmodel\nobject\nThe loaded model.\nrequired\n\n\n\n\n\n\n\nintegrations.base.PluginManager.post_model_load(cfg, model)\nCalls the post_model_load method of all registered plugins after the model has been loaded\ninclusive of any adapters\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train(cfg, model)\nCalls the post_train method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_train_unload(cfg)\nCalls the post_train_unload method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.post_trainer_create(cfg, trainer)\nCalls the post_trainer_create method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\ntrainer (object): The trainer object for training.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_lora_load(cfg, model)\nCalls the pre_lora_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nmodel (object): The loaded model.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.pre_model_load(cfg)\nCalls the pre_model_load method of all registered plugins.\nParameters:\ncfg (dict): The configuration for the plugins.\nReturns:\nNone\n\n\n\nintegrations.base.PluginManager.register(plugin_name)\nRegisters a new plugin by its name.\nParameters:\nplugin_name (str): The name of the plugin to be registered.\nReturns:\nNone\nRaises:\nImportError: If the plugin module cannot be imported." - }, - { - "objectID": "docs/api/integrations.base.html#functions", - "href": "docs/api/integrations.base.html#functions", - "title": "integrations.base", - "section": "", - "text": "Name\nDescription\n\n\n\n\nload_plugin\nLoads a plugin based on the given plugin name.\n\n\n\n\n\nintegrations.base.load_plugin(plugin_name)\nLoads a plugin based on the given plugin name.\nThe plugin name should be in the format “module_name.class_name”.\nThis function splits the plugin name into module and class, imports the module,\nretrieves the class from the module, and creates an instance of the class.\nParameters:\nplugin_name (str): The name of the plugin to be loaded. The name should be in the format “module_name.class_name”.\nReturns:\nBasePlugin: An instance of the loaded plugin.\nRaises:\nImportError: If the plugin module cannot be imported." - }, - { - "objectID": "docs/api/prompt_strategies.alpaca_w_system.html", - "href": "docs/api/prompt_strategies.alpaca_w_system.html", - "title": "prompt_strategies.alpaca_w_system", - "section": "", - "text": "prompt_strategies.alpaca_w_system\nPrompt strategies loader for alpaca instruction datasets with system prompts\n\n\n\n\n\nName\nDescription\n\n\n\n\nInstructionWSystemPromptTokenizingStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nOpenOrcaPromptTokenizingStrategy\nTokenizing strategy for OpenOrca datasets\n\n\nOpenOrcaSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\nSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset\n\n\n\n\n\nprompt_strategies.alpaca_w_system.InstructionWSystemPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for OpenOrca datasets\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaSystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\n\nprompt_strategies.alpaca_w_system.SystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset" - }, - { - "objectID": "docs/api/prompt_strategies.alpaca_w_system.html#classes", - "href": "docs/api/prompt_strategies.alpaca_w_system.html#classes", - "title": "prompt_strategies.alpaca_w_system", - "section": "", - "text": "Name\nDescription\n\n\n\n\nInstructionWSystemPromptTokenizingStrategy\nTokenizing strategy for instruction-based prompts.\n\n\nOpenOrcaPromptTokenizingStrategy\nTokenizing strategy for OpenOrca datasets\n\n\nOpenOrcaSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\nSystemDataPrompter\nAlpaca Style Prompter that uses system prompts from the dataset\n\n\n\n\n\nprompt_strategies.alpaca_w_system.InstructionWSystemPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for instruction-based prompts.\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for OpenOrca datasets\n\n\n\nprompt_strategies.alpaca_w_system.OpenOrcaSystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts\n\n\n\nprompt_strategies.alpaca_w_system.SystemDataPrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Style Prompter that uses system prompts from the dataset" - }, - { - "objectID": "docs/api/utils.collators.batching.html", - "href": "docs/api/utils.collators.batching.html", - "title": "utils.collators.batching", - "section": "", - "text": "utils.collators.batching\nData collators for axolotl to pad labels and position_ids for packed sequences\n\n\n\n\n\nName\nDescription\n\n\n\n\nBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nDataCollatorForSeq2Seq\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\nPretrainingBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nV2BatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\n\n\n\nutils.collators.batching.BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.DataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer\n[PreTrainedTokenizer] or [PreTrainedTokenizerFast]\nThe tokenizer used for encoding the data.\nrequired\n\n\nmodel\n[PreTrainedModel]\nThe model that is being trained. If set and has the prepare_decoder_input_ids_from_labels, use it to prepare the decoder_input_ids This is useful when using label_smoothing to avoid calculating loss twice.\nNone\n\n\npadding\nbool, str or [~utils.PaddingStrategy], optional, defaults to True\nSelect a strategy to pad the returned sequences (according to the model’s padding side and padding index) among: - True or 'longest' (default): Pad to the longest sequence in the batch (or no padding if only a single sequence is provided). - 'max_length': Pad to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. - False or 'do_not_pad': No padding (i.e., can output a batch with sequences of different lengths).\nTrue\n\n\nmax_length\nint, optional\nMaximum length of the returned list and optionally padding length (see above).\nNone\n\n\npad_to_multiple_of\nint, optional\nIf set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta).\nNone\n\n\nlabel_pad_token_id\nint, optional, defaults to -100\nThe id to use when padding the labels (-100 will be automatically ignored by PyTorch loss functions).\n-100\n\n\nreturn_tensors\nstr\nThe type of Tensor to return. Allowable values are “np”, “pt” and “tf”.\n'pt'\n\n\n\n\n\n\n\nutils.collators.batching.PretrainingBatchSamplerDataCollatorForSeq2Seq(\n self,\n *args,\n multipack_attn=True,\n **kwargs,\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.V2BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler" - }, - { - "objectID": "docs/api/utils.collators.batching.html#classes", - "href": "docs/api/utils.collators.batching.html#classes", - "title": "utils.collators.batching", - "section": "", - "text": "Name\nDescription\n\n\n\n\nBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nDataCollatorForSeq2Seq\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\nPretrainingBatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\nV2BatchSamplerDataCollatorForSeq2Seq\nCollator for multipack specific to the using the BatchSampler\n\n\n\n\n\nutils.collators.batching.BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.DataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nData collator that will dynamically pad the inputs received, as well as the labels and position_ids\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ntokenizer\n[PreTrainedTokenizer] or [PreTrainedTokenizerFast]\nThe tokenizer used for encoding the data.\nrequired\n\n\nmodel\n[PreTrainedModel]\nThe model that is being trained. If set and has the prepare_decoder_input_ids_from_labels, use it to prepare the decoder_input_ids This is useful when using label_smoothing to avoid calculating loss twice.\nNone\n\n\npadding\nbool, str or [~utils.PaddingStrategy], optional, defaults to True\nSelect a strategy to pad the returned sequences (according to the model’s padding side and padding index) among: - True or 'longest' (default): Pad to the longest sequence in the batch (or no padding if only a single sequence is provided). - 'max_length': Pad to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. - False or 'do_not_pad': No padding (i.e., can output a batch with sequences of different lengths).\nTrue\n\n\nmax_length\nint, optional\nMaximum length of the returned list and optionally padding length (see above).\nNone\n\n\npad_to_multiple_of\nint, optional\nIf set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta).\nNone\n\n\nlabel_pad_token_id\nint, optional, defaults to -100\nThe id to use when padding the labels (-100 will be automatically ignored by PyTorch loss functions).\n-100\n\n\nreturn_tensors\nstr\nThe type of Tensor to return. Allowable values are “np”, “pt” and “tf”.\n'pt'\n\n\n\n\n\n\n\nutils.collators.batching.PretrainingBatchSamplerDataCollatorForSeq2Seq(\n self,\n *args,\n multipack_attn=True,\n **kwargs,\n)\nCollator for multipack specific to the using the BatchSampler\n\n\n\nutils.collators.batching.V2BatchSamplerDataCollatorForSeq2Seq(\n self,\n tokenizer,\n model=None,\n padding=True,\n max_length=None,\n pad_to_multiple_of=None,\n label_pad_token_id=-100,\n position_pad_token_id=0,\n return_tensors='pt',\n)\nCollator for multipack specific to the using the BatchSampler" - }, - { - "objectID": "docs/api/core.trainers.trl.html", - "href": "docs/api/core.trainers.trl.html", - "title": "core.trainers.trl", - "section": "", - "text": "core.trainers.trl\nModule for TRL PPO trainer\n\n\n\n\n\nName\nDescription\n\n\n\n\nAxolotlCPOTrainer\nExtend the base CPOTrainer for axolotl helpers\n\n\nAxolotlKTOTrainer\nExtend the base KTOTrainer for axolotl helpers\n\n\nAxolotlORPOTrainer\nExtend the base ORPOTrainer for axolotl helpers\n\n\nAxolotlPRMTrainer\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\nAxolotlRewardTrainer\nExtend the base RewardTrainer for axolotl helpers\n\n\nTRLPPOTrainer\nWrapper for TRL PPO trainer to handle customizations\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer()\nExtend the base CPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlKTOTrainer()\nExtend the base KTOTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer()\nExtend the base ORPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlPRMTrainer()\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlRewardTrainer()\nExtend the base RewardTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.TRLPPOTrainer()\nWrapper for TRL PPO trainer to handle customizations" - }, - { - "objectID": "docs/api/core.trainers.trl.html#classes", - "href": "docs/api/core.trainers.trl.html#classes", - "title": "core.trainers.trl", - "section": "", - "text": "Name\nDescription\n\n\n\n\nAxolotlCPOTrainer\nExtend the base CPOTrainer for axolotl helpers\n\n\nAxolotlKTOTrainer\nExtend the base KTOTrainer for axolotl helpers\n\n\nAxolotlORPOTrainer\nExtend the base ORPOTrainer for axolotl helpers\n\n\nAxolotlPRMTrainer\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\nAxolotlRewardTrainer\nExtend the base RewardTrainer for axolotl helpers\n\n\nTRLPPOTrainer\nWrapper for TRL PPO trainer to handle customizations\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer()\nExtend the base CPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlCPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the CPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlKTOTrainer()\nExtend the base KTOTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer()\nExtend the base ORPOTrainer for axolotl helpers\n\n\n\n\n\nName\nDescription\n\n\n\n\nget_batch_loss_metrics\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlORPOTrainer.get_batch_loss_metrics(\n model,\n batch,\n train_eval='train',\n)\nCompute the ORPO loss and other metrics for the given batch of inputs for train or test.\n\n\n\n\n\ncore.trainers.trl.AxolotlPRMTrainer()\nExtend the base trl.PRMTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.AxolotlRewardTrainer()\nExtend the base RewardTrainer for axolotl helpers\n\n\n\ncore.trainers.trl.TRLPPOTrainer()\nWrapper for TRL PPO trainer to handle customizations" - }, - { - "objectID": "docs/api/utils.schemas.utils.html", - "href": "docs/api/utils.schemas.utils.html", - "title": "utils.schemas.utils", - "section": "", - "text": "utils.schemas.utils\nUtilities for Axolotl Pydantic models\n\n\n\n\n\nName\nDescription\n\n\n\n\nhandle_legacy_message_fields_logic\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.utils.handle_legacy_message_fields_logic(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\nPreviously, the config only supported mapping ‘role’ and ‘content’ fields via dedicated config options:\n- message_field_role: Mapped to the role field\n- message_field_content: Mapped to the content field\nThe new system uses message_property_mappings to support arbitrary field mappings:\nmessage_property_mappings:\nrole: source_role_field\ncontent: source_content_field\nadditional_field: source_field\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndata\ndict\nDictionary containing configuration data\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ndict\nUpdated dictionary with message field mappings consolidated\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf there are conflicts between legacy and new mappings" - }, - { - "objectID": "docs/api/utils.schemas.utils.html#functions", - "href": "docs/api/utils.schemas.utils.html#functions", - "title": "utils.schemas.utils", - "section": "", - "text": "Name\nDescription\n\n\n\n\nhandle_legacy_message_fields_logic\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\n\n\n\n\n\nutils.schemas.utils.handle_legacy_message_fields_logic(data)\nHandle backwards compatibility between legacy message field mapping and new property mapping system.\nPreviously, the config only supported mapping ‘role’ and ‘content’ fields via dedicated config options:\n- message_field_role: Mapped to the role field\n- message_field_content: Mapped to the content field\nThe new system uses message_property_mappings to support arbitrary field mappings:\nmessage_property_mappings:\nrole: source_role_field\ncontent: source_content_field\nadditional_field: source_field\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\nDefault\n\n\n\n\ndata\ndict\nDictionary containing configuration data\nrequired\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\ndict\nUpdated dictionary with message field mappings consolidated\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nName\nType\nDescription\n\n\n\n\n\nValueError\nIf there are conflicts between legacy and new mappings" - }, - { - "objectID": "docs/api/utils.model_shard_quant.html", - "href": "docs/api/utils.model_shard_quant.html", - "title": "utils.model_shard_quant", - "section": "", - "text": "utils.model_shard_quant\nmodule to handle loading model on cpu/meta device for FSDP\n\n\n\n\n\nName\nDescription\n\n\n\n\nload_and_quantize\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\n\n\n\n\n\nutils.model_shard_quant.load_and_quantize(\n module,\n name,\n value,\n device=None,\n dtype=None,\n skip_names=None,\n to_cpu=False,\n to_meta=False,\n verbose=False,\n quant_method='bnb',\n)\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\nQuantizes Params4bit on device then places on “cpu” if to_cpu=True or “meta” if to_meta=True." - }, - { - "objectID": "docs/api/utils.model_shard_quant.html#functions", - "href": "docs/api/utils.model_shard_quant.html#functions", - "title": "utils.model_shard_quant", - "section": "", - "text": "Name\nDescription\n\n\n\n\nload_and_quantize\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\n\n\n\n\n\nutils.model_shard_quant.load_and_quantize(\n module,\n name,\n value,\n device=None,\n dtype=None,\n skip_names=None,\n to_cpu=False,\n to_meta=False,\n verbose=False,\n quant_method='bnb',\n)\nLoads value tensor into submodule of module, optionally skipping skip_names and converting to dtype.\nQuantizes Params4bit on device then places on “cpu” if to_cpu=True or “meta” if to_meta=True." - }, - { - "objectID": "docs/api/integrations.lm_eval.args.html", - "href": "docs/api/integrations.lm_eval.args.html", - "title": "integrations.lm_eval.args", - "section": "", - "text": "integrations.lm_eval.args\nModule for handling lm eval harness input arguments.\n\n\n\n\n\nName\nDescription\n\n\n\n\nLMEvalArgs\nInput args for lm eval harness\n\n\n\n\n\nintegrations.lm_eval.args.LMEvalArgs()\nInput args for lm eval harness" - }, - { - "objectID": "docs/api/integrations.lm_eval.args.html#classes", - "href": "docs/api/integrations.lm_eval.args.html#classes", - "title": "integrations.lm_eval.args", - "section": "", - "text": "Name\nDescription\n\n\n\n\nLMEvalArgs\nInput args for lm eval harness\n\n\n\n\n\nintegrations.lm_eval.args.LMEvalArgs()\nInput args for lm eval harness" - }, - { - "objectID": "docs/api/monkeypatch.mixtral.html", - "href": "docs/api/monkeypatch.mixtral.html", - "title": "monkeypatch.mixtral", - "section": "", - "text": "monkeypatch.mixtral\nmonkeypatch.mixtral\nPatches to support multipack for mixtral" - }, - { - "objectID": "docs/api/logging_config.html", - "href": "docs/api/logging_config.html", - "title": "logging_config", - "section": "", - "text": "logging_config\nCommon logging module for axolotl\n\n\n\n\n\nName\nDescription\n\n\n\n\nColorfulFormatter\nFormatter to add coloring to log messages by log type\n\n\n\n\n\nlogging_config.ColorfulFormatter()\nFormatter to add coloring to log messages by log type\n\n\n\n\n\n\n\nName\nDescription\n\n\n\n\nconfigure_logging\nConfigure with default logging\n\n\n\n\n\nlogging_config.configure_logging()\nConfigure with default logging" - }, - { - "objectID": "docs/api/logging_config.html#classes", - "href": "docs/api/logging_config.html#classes", - "title": "logging_config", - "section": "", - "text": "Name\nDescription\n\n\n\n\nColorfulFormatter\nFormatter to add coloring to log messages by log type\n\n\n\n\n\nlogging_config.ColorfulFormatter()\nFormatter to add coloring to log messages by log type" - }, - { - "objectID": "docs/api/logging_config.html#functions", - "href": "docs/api/logging_config.html#functions", - "title": "logging_config", - "section": "", - "text": "Name\nDescription\n\n\n\n\nconfigure_logging\nConfigure with default logging\n\n\n\n\n\nlogging_config.configure_logging()\nConfigure with default logging" - }, - { - "objectID": "docs/api/prompt_strategies.alpaca_chat.html", - "href": "docs/api/prompt_strategies.alpaca_chat.html", - "title": "prompt_strategies.alpaca_chat", - "section": "", - "text": "prompt_strategies.alpaca_chat\nModule for Alpaca prompt strategy classes\n\n\n\n\n\nName\nDescription\n\n\n\n\nAlpacaChatPrompter\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\nAlpacaConcisePrompter\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\nAlpacaQAPromptTokenizingStrategy\nTokenizing strategy for AlpacaQA\n\n\nCamelAIPromptTokenizingStrategy\nTokenizing strategy for CamelAI datasets\n\n\nNoSystemPrompter\nNull Prompter with no system prompts\n\n\n\n\n\nprompt_strategies.alpaca_chat.AlpacaChatPrompter(self)\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaConcisePrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaQAPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for AlpacaQA\n\n\n\nprompt_strategies.alpaca_chat.CamelAIPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for CamelAI datasets\n\n\n\nprompt_strategies.alpaca_chat.NoSystemPrompter(self)\nNull Prompter with no system prompts" - }, - { - "objectID": "docs/api/prompt_strategies.alpaca_chat.html#classes", - "href": "docs/api/prompt_strategies.alpaca_chat.html#classes", - "title": "prompt_strategies.alpaca_chat", - "section": "", - "text": "Name\nDescription\n\n\n\n\nAlpacaChatPrompter\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\nAlpacaConcisePrompter\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\nAlpacaQAPromptTokenizingStrategy\nTokenizing strategy for AlpacaQA\n\n\nCamelAIPromptTokenizingStrategy\nTokenizing strategy for CamelAI datasets\n\n\nNoSystemPrompter\nNull Prompter with no system prompts\n\n\n\n\n\nprompt_strategies.alpaca_chat.AlpacaChatPrompter(self)\nAlpaca Chat Prompter extending the system prompt to for chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaConcisePrompter(\n self,\n prompt_style=PromptStyle.INSTRUCT.value,\n)\nAlpaca Prompter extending the system prompt to ask for concise chat-instruct answers\n\n\n\nprompt_strategies.alpaca_chat.AlpacaQAPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for AlpacaQA\n\n\n\nprompt_strategies.alpaca_chat.CamelAIPromptTokenizingStrategy(\n self,\n prompter,\n tokenizer,\n train_on_inputs=False,\n sequence_len=2048,\n)\nTokenizing strategy for CamelAI datasets\n\n\n\nprompt_strategies.alpaca_chat.NoSystemPrompter(self)\nNull Prompter with no system prompts" - }, - { - "objectID": "docs/api/prompt_strategies.kto.llama3.html", - "href": "docs/api/prompt_strategies.kto.llama3.html", - "title": "prompt_strategies.kto.llama3", - "section": "", - "text": "prompt_strategies.kto.llama3\nKTO strategies for llama-3 chat template\n\n\n\n\n\nName\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.llama3.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" - }, - { - "objectID": "docs/api/prompt_strategies.kto.llama3.html#functions", - "href": "docs/api/prompt_strategies.kto.llama3.html#functions", - "title": "prompt_strategies.kto.llama3", - "section": "", - "text": "Name\nDescription\n\n\n\n\nargilla_chat\nfor argilla/kto-mix-15k conversations\n\n\nintel\nFor Intel Orca KTO\n\n\nultra\nfor ultrafeedback binarized conversations\n\n\n\n\n\nprompt_strategies.kto.llama3.argilla_chat(cfg, **kwargs)\nfor argilla/kto-mix-15k conversations\n\n\n\nprompt_strategies.kto.llama3.intel(cfg, **kwargs)\nFor Intel Orca KTO\nex: argilla/distilabel-intel-orca-kto\n\n\n\nprompt_strategies.kto.llama3.ultra(cfg, **kwargs)\nfor ultrafeedback binarized conversations\nex: argilla/ultrafeedback-binarized-preferences-cleaned-kto" + "text": "common.architectures\ncommon.architectures\nCommon architecture specific constants" }, { "objectID": "docs/api/cli.cloud.base.html", diff --git a/sitemap.xml b/sitemap.xml index 4d00f0a44..c5cc386db 100644 --- a/sitemap.xml +++ b/sitemap.xml @@ -2,722 +2,718 @@ https://docs.axolotl.ai/TODO.html - 2025-05-16T19:47:14.865Z + 2025-05-21T15:20:33.330Z https://docs.axolotl.ai/docs/debugging.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/rlhf.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/input_output.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/lr_groups.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/dataset-formats/template_free.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/dataset-formats/pretraining.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/dataset-formats/conversation.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/fsdp_qlora.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/torchao.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/dataset_preprocessing.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/batch_vs_grad.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/dataset_loading.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/amd_hpc.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/docker.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/multi-node.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/sequence_parallelism.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/multi-gpu.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/api/utils.collators.core.html - 2025-05-16T19:47:45.279Z + 2025-05-21T15:21:17.468Z https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html - 2025-05-16T19:47:45.307Z + 2025-05-21T15:21:17.495Z https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html - 2025-05-16T19:47:45.245Z - - - https://docs.axolotl.ai/docs/api/core.trainers.mixins.sequence_parallel.html - 2025-05-16T19:47:44.425Z - - - https://docs.axolotl.ai/docs/api/common.architectures.html - 2025-05-16T19:47:45.257Z - - - https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html - 2025-05-16T19:47:45.008Z - - - https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html - 2025-05-16T19:47:45.361Z - - - https://docs.axolotl.ai/docs/api/utils.data.pretraining.html - 2025-05-16T19:47:45.009Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.model.html - 2025-05-16T19:47:45.057Z - - - https://docs.axolotl.ai/docs/api/kernels.utils.html - 2025-05-16T19:47:44.743Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.base.html - 2025-05-16T19:47:44.452Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html - 2025-05-16T19:47:44.602Z - - - https://docs.axolotl.ai/docs/api/cli.sweeps.html - 2025-05-16T19:47:44.285Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html - 2025-05-16T19:47:44.788Z - - - https://docs.axolotl.ai/docs/api/cli.evaluate.html - 2025-05-16T19:47:44.193Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html - 2025-05-16T19:47:44.548Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html - 2025-05-16T19:47:44.586Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html - 2025-05-16T19:47:44.851Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.config.html - 2025-05-16T19:47:45.049Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html - 2025-05-16T19:47:44.583Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.attention.mllama.html - 2025-05-16T19:47:44.858Z - - - https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html - 2025-05-16T19:47:44.126Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html - 2025-05-16T19:47:44.486Z - - - https://docs.axolotl.ai/docs/api/common.datasets.html - 2025-05-16T19:47:45.276Z - - - https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html - 2025-05-16T19:47:44.143Z - - - https://docs.axolotl.ai/docs/api/cli.vllm_serve.html - 2025-05-16T19:47:44.323Z - - - https://docs.axolotl.ai/docs/api/cli.config.html - 2025-05-16T19:47:44.235Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.trl.html - 2025-05-16T19:47:45.092Z - - - https://docs.axolotl.ai/docs/api/core.trainers.mamba.html - 2025-05-16T19:47:44.371Z - - - https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html - 2025-05-16T19:47:45.237Z - - - https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html - 2025-05-16T19:47:44.385Z - - - https://docs.axolotl.ai/docs/api/cli.inference.html - 2025-05-16T19:47:44.249Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html - 2025-05-16T19:47:44.532Z - - - https://docs.axolotl.ai/docs/api/utils.bench.html - 2025-05-16T19:47:44.927Z - - - https://docs.axolotl.ai/docs/api/core.trainers.relora.html - 2025-05-16T19:47:44.375Z - - - https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html - 2025-05-16T19:47:45.255Z - - - https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html - 2025-05-16T19:47:44.394Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html - 2025-05-16T19:47:44.796Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.peft.html - 2025-05-16T19:47:45.089Z - - - https://docs.axolotl.ai/docs/api/cli.main.html - 2025-05-16T19:47:44.175Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html - 2025-05-16T19:47:44.581Z - - - https://docs.axolotl.ai/docs/api/core.trainer_builder.html - 2025-05-16T19:47:44.009Z - - - https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html - 2025-05-16T19:47:45.277Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html - 2025-05-16T19:47:44.561Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html - 2025-05-16T19:47:44.840Z - - - https://docs.axolotl.ai/docs/api/utils.gradient_checkpointing.offload_disk.html - 2025-05-16T19:47:45.041Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html - 2025-05-16T19:47:44.571Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html - 2025-05-16T19:47:44.544Z - - - https://docs.axolotl.ai/docs/api/kernels.swiglu.html - 2025-05-16T19:47:44.733Z - - - https://docs.axolotl.ai/docs/api/core.trainers.base.html - 2025-05-16T19:47:44.348Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.relora.html - 2025-05-16T19:47:44.795Z - - - https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html - 2025-05-16T19:47:44.333Z - - - https://docs.axolotl.ai/docs/api/core.training_args.html - 2025-05-16T19:47:44.102Z - - - https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html - 2025-05-16T19:47:45.368Z - - - https://docs.axolotl.ai/docs/api/core.chat.format.shared.html - 2025-05-16T19:47:44.130Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html - 2025-05-16T19:47:44.823Z - - - https://docs.axolotl.ai/docs/api/cli.merge_lora.html - 2025-05-16T19:47:44.258Z - - - https://docs.axolotl.ai/docs/api/utils.trainer.html - 2025-05-16T19:47:44.952Z - - - https://docs.axolotl.ai/docs/api/utils.dict.html - 2025-05-16T19:47:45.000Z - - - https://docs.axolotl.ai/docs/api/kernels.quantize.html - 2025-05-16T19:47:44.741Z - - - https://docs.axolotl.ai/docs/api/core.trainers.utils.html - 2025-05-16T19:47:44.408Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html - 2025-05-16T19:47:44.860Z - - - https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html - 2025-05-16T19:47:44.450Z - - - https://docs.axolotl.ai/docs/api/evaluate.html - 2025-05-16T19:47:43.924Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html - 2025-05-16T19:47:44.526Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html - 2025-05-16T19:47:44.769Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html - 2025-05-16T19:47:44.624Z - - - https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html - 2025-05-16T19:47:44.412Z - - - https://docs.axolotl.ai/docs/api/cli.utils.html - 2025-05-16T19:47:44.318Z - - - https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html - 2025-05-16T19:47:14.886Z - - - https://docs.axolotl.ai/FAQS.html - 2025-05-16T19:47:14.865Z - - - https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html - 2025-05-16T19:47:14.871Z - - - https://docs.axolotl.ai/index.html - 2025-05-16T19:47:14.883Z - - - https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html - 2025-05-16T19:47:14.887Z - - - https://docs.axolotl.ai/docs/api/datasets.html - 2025-05-16T19:47:43.932Z - - - https://docs.axolotl.ai/docs/api/cli.train.html - 2025-05-16T19:47:44.184Z - - - https://docs.axolotl.ai/docs/api/utils.lora_embeddings.html - 2025-05-16T19:47:44.917Z - - - https://docs.axolotl.ai/docs/api/utils.models.html - 2025-05-16T19:47:44.891Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html - 2025-05-16T19:47:44.507Z - - - https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html - 2025-05-16T19:47:44.407Z - - - https://docs.axolotl.ai/docs/api/common.const.html - 2025-05-16T19:47:45.258Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html - 2025-05-16T19:47:44.628Z - - - https://docs.axolotl.ai/docs/api/utils.distributed.html - 2025-05-16T19:47:44.997Z - - - https://docs.axolotl.ai/docs/api/utils.tokenization.html - 2025-05-16T19:47:44.898Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html - 2025-05-16T19:47:45.110Z - - - https://docs.axolotl.ai/docs/api/utils.schedulers.html - 2025-05-16T19:47:44.977Z - - - https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html - 2025-05-16T19:47:44.422Z - - - https://docs.axolotl.ai/docs/api/core.datasets.chat.html - 2025-05-16T19:47:44.135Z - - - https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html - 2025-05-16T19:47:45.365Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html - 2025-05-16T19:47:44.786Z - - - https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html - 2025-05-16T19:47:44.128Z - - - https://docs.axolotl.ai/docs/api/cli.checks.html - 2025-05-16T19:47:44.217Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html - 2025-05-16T19:47:44.850Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html - 2025-05-16T19:47:44.520Z - - - https://docs.axolotl.ai/docs/api/convert.html - 2025-05-16T19:47:43.946Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html - 2025-05-16T19:47:45.080Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.enums.html - 2025-05-16T19:47:45.119Z - - - https://docs.axolotl.ai/docs/api/cli.args.html - 2025-05-16T19:47:44.210Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html - 2025-05-16T19:47:44.771Z - - - https://docs.axolotl.ai/docs/api/train.html - 2025-05-16T19:47:43.914Z - - - https://docs.axolotl.ai/docs/api/utils.gradient_checkpointing.offload_cpu.html - 2025-05-16T19:47:45.014Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html - 2025-05-16T19:47:44.559Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html - 2025-05-16T19:47:44.834Z - - - https://docs.axolotl.ai/docs/api/index.html - 2025-05-16T19:47:43.852Z - - - https://docs.axolotl.ai/docs/api/cli.preprocess.html - 2025-05-16T19:47:44.279Z - - - https://docs.axolotl.ai/docs/api/utils.freeze.html - 2025-05-16T19:47:44.935Z - - - https://docs.axolotl.ai/docs/api/utils.data.sft.html - 2025-05-16T19:47:45.011Z - - - https://docs.axolotl.ai/docs/api/integrations.liger.args.html - 2025-05-16T19:47:45.248Z - - - https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html - 2025-05-16T19:47:44.415Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html - 2025-05-16T19:47:44.603Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.utils.html - 2025-05-16T19:47:44.831Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html - 2025-05-16T19:47:45.098Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html - 2025-05-16T19:47:44.470Z - - - https://docs.axolotl.ai/docs/api/utils.lora.html - 2025-05-16T19:47:44.914Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html - 2025-05-16T19:47:44.832Z - - - https://docs.axolotl.ai/docs/api/utils.chat_templates.html - 2025-05-16T19:47:44.909Z - - - https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html - 2025-05-16T19:47:45.236Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html - 2025-05-16T19:47:44.843Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html - 2025-05-16T19:47:44.537Z - - - https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html - 2025-05-16T19:47:45.359Z - - - https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html - 2025-05-16T19:47:44.270Z - - - https://docs.axolotl.ai/docs/api/utils.collators.mamba.html - 2025-05-16T19:47:45.302Z - - - https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html - 2025-05-16T19:47:45.349Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html - 2025-05-16T19:47:44.584Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.training.html - 2025-05-16T19:47:45.062Z - - - https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html - 2025-05-16T19:47:45.355Z - - - https://docs.axolotl.ai/docs/api/kernels.lora.html - 2025-05-16T19:47:44.712Z - - - https://docs.axolotl.ai/docs/api/core.chat.messages.html - 2025-05-16T19:47:44.125Z - - - https://docs.axolotl.ai/docs/api/integrations.base.html - 2025-05-16T19:47:45.232Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html - 2025-05-16T19:47:44.498Z - - - https://docs.axolotl.ai/docs/api/utils.collators.batching.html - 2025-05-16T19:47:45.298Z - - - https://docs.axolotl.ai/docs/api/core.trainers.trl.html - 2025-05-16T19:47:44.366Z - - - https://docs.axolotl.ai/docs/api/utils.schemas.utils.html - 2025-05-16T19:47:45.124Z - - - https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html - 2025-05-16T19:47:44.923Z - - - https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html - 2025-05-16T19:47:45.252Z - - - https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html - 2025-05-16T19:47:44.861Z - - - https://docs.axolotl.ai/docs/api/logging_config.html - 2025-05-16T19:47:43.994Z - - - https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html - 2025-05-16T19:47:44.484Z + 2025-05-21T15:21:17.435Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html - 2025-05-16T19:47:44.594Z + 2025-05-21T15:21:16.775Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html + 2025-05-21T15:21:16.667Z + + + https://docs.axolotl.ai/docs/api/logging_config.html + 2025-05-21T15:21:16.198Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html + 2025-05-21T15:21:17.034Z + + + https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html + 2025-05-21T15:21:17.442Z + + + https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html + 2025-05-21T15:21:17.115Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.utils.html + 2025-05-21T15:21:17.315Z + + + https://docs.axolotl.ai/docs/api/core.trainers.trl.html + 2025-05-21T15:21:16.558Z + + + https://docs.axolotl.ai/docs/api/utils.collators.batching.html + 2025-05-21T15:21:17.487Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html + 2025-05-21T15:21:16.681Z + + + https://docs.axolotl.ai/docs/api/integrations.base.html + 2025-05-21T15:21:17.423Z + + + https://docs.axolotl.ai/docs/api/core.chat.messages.html + 2025-05-21T15:21:16.324Z + + + https://docs.axolotl.ai/docs/api/kernels.lora.html + 2025-05-21T15:21:16.890Z + + + https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html + 2025-05-21T15:21:17.543Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.training.html + 2025-05-21T15:21:17.254Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html + 2025-05-21T15:21:16.765Z + + + https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html + 2025-05-21T15:21:17.537Z + + + https://docs.axolotl.ai/docs/api/utils.collators.mamba.html + 2025-05-21T15:21:17.491Z + + + https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html + 2025-05-21T15:21:16.466Z + + + https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html + 2025-05-21T15:21:17.547Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html + 2025-05-21T15:21:16.719Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html + 2025-05-21T15:21:17.016Z + + + https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html + 2025-05-21T15:21:17.426Z + + + https://docs.axolotl.ai/docs/api/utils.chat_templates.html + 2025-05-21T15:21:17.096Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html + 2025-05-21T15:21:17.006Z + + + https://docs.axolotl.ai/docs/api/utils.lora.html + 2025-05-21T15:21:17.105Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html + 2025-05-21T15:21:16.653Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html + 2025-05-21T15:21:17.289Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.utils.html + 2025-05-21T15:21:17.004Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html + 2025-05-21T15:21:16.784Z + + + https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html + 2025-05-21T15:21:16.603Z + + + https://docs.axolotl.ai/docs/api/integrations.liger.args.html + 2025-05-21T15:21:17.438Z + + + https://docs.axolotl.ai/docs/api/utils.data.sft.html + 2025-05-21T15:21:17.203Z + + + https://docs.axolotl.ai/docs/api/utils.freeze.html + 2025-05-21T15:21:17.126Z + + + https://docs.axolotl.ai/docs/api/cli.preprocess.html + 2025-05-21T15:21:16.474Z + + + https://docs.axolotl.ai/docs/api/index.html + 2025-05-21T15:21:16.058Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html + 2025-05-21T15:21:17.007Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html + 2025-05-21T15:21:16.740Z + + + https://docs.axolotl.ai/docs/api/utils.gradient_checkpointing.offload_cpu.html + 2025-05-21T15:21:17.207Z + + + https://docs.axolotl.ai/docs/api/train.html + 2025-05-21T15:21:16.119Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html + 2025-05-21T15:21:16.947Z + + + https://docs.axolotl.ai/docs/api/cli.args.html + 2025-05-21T15:21:16.407Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.enums.html + 2025-05-21T15:21:17.310Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html + 2025-05-21T15:21:17.272Z + + + https://docs.axolotl.ai/docs/api/convert.html + 2025-05-21T15:21:16.151Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html + 2025-05-21T15:21:16.702Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html + 2025-05-21T15:21:17.023Z + + + https://docs.axolotl.ai/docs/api/cli.checks.html + 2025-05-21T15:21:16.414Z + + + https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html + 2025-05-21T15:21:16.327Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html + 2025-05-21T15:21:16.961Z + + + https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html + 2025-05-21T15:21:17.552Z + + + https://docs.axolotl.ai/docs/api/core.datasets.chat.html + 2025-05-21T15:21:16.334Z + + + https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html + 2025-05-21T15:21:16.610Z + + + https://docs.axolotl.ai/docs/api/utils.schedulers.html + 2025-05-21T15:21:17.170Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html + 2025-05-21T15:21:17.301Z + + + https://docs.axolotl.ai/docs/api/utils.tokenization.html + 2025-05-21T15:21:17.084Z + + + https://docs.axolotl.ai/docs/api/utils.distributed.html + 2025-05-21T15:21:17.189Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html + 2025-05-21T15:21:16.808Z + + + https://docs.axolotl.ai/docs/api/common.const.html + 2025-05-21T15:21:17.448Z + + + https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html + 2025-05-21T15:21:16.595Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html + 2025-05-21T15:21:16.689Z + + + https://docs.axolotl.ai/docs/api/utils.models.html + 2025-05-21T15:21:17.076Z + + + https://docs.axolotl.ai/docs/api/utils.lora_embeddings.html + 2025-05-21T15:21:17.109Z + + + https://docs.axolotl.ai/docs/api/cli.train.html + 2025-05-21T15:21:16.382Z + + + https://docs.axolotl.ai/docs/api/datasets.html + 2025-05-21T15:21:16.137Z + + + https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html + 2025-05-21T15:20:33.352Z + + + https://docs.axolotl.ai/index.html + 2025-05-21T15:20:33.348Z + + + https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html + 2025-05-21T15:20:33.336Z + + + https://docs.axolotl.ai/FAQS.html + 2025-05-21T15:20:33.329Z + + + https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html + 2025-05-21T15:20:33.351Z + + + https://docs.axolotl.ai/docs/api/cli.utils.html + 2025-05-21T15:21:16.512Z + + + https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html + 2025-05-21T15:21:16.600Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html + 2025-05-21T15:21:16.805Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html + 2025-05-21T15:21:16.945Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html + 2025-05-21T15:21:16.708Z + + + https://docs.axolotl.ai/docs/api/evaluate.html + 2025-05-21T15:21:16.130Z + + + https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html + 2025-05-21T15:21:16.634Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html + 2025-05-21T15:21:17.033Z + + + https://docs.axolotl.ai/docs/api/core.trainers.utils.html + 2025-05-21T15:21:16.596Z + + + https://docs.axolotl.ai/docs/api/kernels.quantize.html + 2025-05-21T15:21:16.918Z + + + https://docs.axolotl.ai/docs/api/utils.dict.html + 2025-05-21T15:21:17.193Z + + + https://docs.axolotl.ai/docs/api/utils.trainer.html + 2025-05-21T15:21:17.144Z + + + https://docs.axolotl.ai/docs/api/cli.merge_lora.html + 2025-05-21T15:21:16.454Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html + 2025-05-21T15:21:16.996Z + + + https://docs.axolotl.ai/docs/api/core.chat.format.shared.html + 2025-05-21T15:21:16.329Z + + + https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html + 2025-05-21T15:21:17.556Z + + + https://docs.axolotl.ai/docs/api/core.training_args.html + 2025-05-21T15:21:16.302Z + + + https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html + 2025-05-21T15:21:16.527Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.relora.html + 2025-05-21T15:21:16.970Z + + + https://docs.axolotl.ai/docs/api/core.trainers.base.html + 2025-05-21T15:21:16.541Z + + + https://docs.axolotl.ai/docs/api/kernels.swiglu.html + 2025-05-21T15:21:16.911Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html + 2025-05-21T15:21:16.725Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html + 2025-05-21T15:21:16.752Z + + + https://docs.axolotl.ai/docs/api/utils.gradient_checkpointing.offload_disk.html + 2025-05-21T15:21:17.233Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html + 2025-05-21T15:21:17.013Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html + 2025-05-21T15:21:16.742Z + + + https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html + 2025-05-21T15:21:17.466Z + + + https://docs.axolotl.ai/docs/api/core.trainer_builder.html + 2025-05-21T15:21:16.214Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html + 2025-05-21T15:21:16.762Z + + + https://docs.axolotl.ai/docs/api/cli.main.html + 2025-05-21T15:21:16.373Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.peft.html + 2025-05-21T15:21:17.280Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html + 2025-05-21T15:21:16.971Z + + + https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html + 2025-05-21T15:21:16.583Z + + + https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html + 2025-05-21T15:21:17.445Z + + + https://docs.axolotl.ai/docs/api/core.trainers.relora.html + 2025-05-21T15:21:16.567Z + + + https://docs.axolotl.ai/docs/api/utils.bench.html + 2025-05-21T15:21:17.118Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html + 2025-05-21T15:21:16.714Z + + + https://docs.axolotl.ai/docs/api/cli.inference.html + 2025-05-21T15:21:16.446Z + + + https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html + 2025-05-21T15:21:16.573Z + + + https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html + 2025-05-21T15:21:17.428Z + + + https://docs.axolotl.ai/docs/api/core.trainers.mamba.html + 2025-05-21T15:21:16.563Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.trl.html + 2025-05-21T15:21:17.283Z + + + https://docs.axolotl.ai/docs/api/cli.config.html + 2025-05-21T15:21:16.431Z + + + https://docs.axolotl.ai/docs/api/cli.vllm_serve.html + 2025-05-21T15:21:16.517Z + + + https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html + 2025-05-21T15:21:16.342Z + + + https://docs.axolotl.ai/docs/api/common.datasets.html + 2025-05-21T15:21:17.465Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html + 2025-05-21T15:21:16.669Z + + + https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html + 2025-05-21T15:21:16.326Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.attention.mllama.html + 2025-05-21T15:21:17.031Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html + 2025-05-21T15:21:16.764Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.config.html + 2025-05-21T15:21:17.242Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html + 2025-05-21T15:21:17.024Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html + 2025-05-21T15:21:16.767Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html + 2025-05-21T15:21:16.729Z + + + https://docs.axolotl.ai/docs/api/cli.evaluate.html + 2025-05-21T15:21:16.390Z + + + https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html + 2025-05-21T15:21:16.963Z + + + https://docs.axolotl.ai/docs/api/cli.sweeps.html + 2025-05-21T15:21:16.480Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html + 2025-05-21T15:21:16.783Z + + + https://docs.axolotl.ai/docs/api/prompt_strategies.base.html + 2025-05-21T15:21:16.635Z + + + https://docs.axolotl.ai/docs/api/kernels.utils.html + 2025-05-21T15:21:16.920Z + + + https://docs.axolotl.ai/docs/api/utils.schemas.model.html + 2025-05-21T15:21:17.249Z + + + https://docs.axolotl.ai/docs/api/utils.data.pretraining.html + 2025-05-21T15:21:17.202Z + + + https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html + 2025-05-21T15:21:17.549Z + + + https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html + 2025-05-21T15:21:17.200Z + + + https://docs.axolotl.ai/docs/api/common.architectures.html + 2025-05-21T15:21:17.447Z https://docs.axolotl.ai/docs/api/cli.cloud.base.html - 2025-05-16T19:47:44.327Z + 2025-05-21T15:21:16.520Z https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html - 2025-05-16T19:47:44.555Z + 2025-05-21T15:21:16.736Z https://docs.axolotl.ai/docs/api/prompt_tokenizers.html - 2025-05-16T19:47:43.988Z + 2025-05-21T15:21:16.193Z https://docs.axolotl.ai/docs/api/kernels.geglu.html - 2025-05-16T19:47:44.723Z + 2025-05-21T15:21:16.901Z https://docs.axolotl.ai/docs/custom_integrations.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/multimodal.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/faq.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/multipack.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/lora_optims.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/nccl.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/cli.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/config.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/unsloth.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/ray-integration.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/dataset-formats/index.html - 2025-05-16T19:47:14.866Z + 2025-05-21T15:20:33.331Z https://docs.axolotl.ai/docs/dataset-formats/tokenized.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/installation.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/inference.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.334Z https://docs.axolotl.ai/docs/mac.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z https://docs.axolotl.ai/docs/getting-started.html - 2025-05-16T19:47:14.867Z + 2025-05-21T15:20:33.332Z https://docs.axolotl.ai/docs/reward_modelling.html - 2025-05-16T19:47:14.870Z + 2025-05-21T15:20:33.335Z