Merge branch 'main' into feat/glm45

examples/colab-notebooks/colab-axolotl-example.ipynb

@@ -40,7 +40,7 @@
     "%%capture\n",
     "# This step can take ~5-10 minutes to install dependencies\n",
     "!pip install --no-build-isolation axolotl[flash-attn]>=0.9.1\n",
-    "!pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@5eff953\""
+    "!pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@f643b88\""
    ]
   },
   {
@@ -253,7 +253,6 @@
    "source": [
     "from axolotl.utils import set_pytorch_cuda_alloc_conf\n",
     "\n",
-    "# Set \"PYTORCH_CUDA_ALLOC_CONF\" env to save memory\n",
     "set_pytorch_cuda_alloc_conf()"
    ]
   },

examples/gpt-oss/gpt-oss-120b-fft-fsdp2-offload.yaml

@@ -32,6 +32,10 @@ wandb_watch:
 wandb_name:
 wandb_log_model:
 
+trackio_project_name:
+trackio_run_name:
+trackio_space_id:
+
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1

examples/gpt-oss/gpt-oss-20b-fft-deepspeed-zero3.yaml

@@ -28,6 +28,10 @@ wandb_watch:
 wandb_name:
 wandb_log_model:
 
+trackio_project_name:
+trackio_run_name:
+trackio_space_id:
+
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1

examples/gpt-oss/gpt-oss-20b-fft-fsdp2-offload.yaml

@@ -29,6 +29,10 @@ wandb_watch:
 wandb_name:
 wandb_log_model:
 
+trackio_project_name:
+trackio_run_name:
+trackio_space_id:
+
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1

examples/gpt-oss/gpt-oss-20b-fft-fsdp2.yaml

@@ -28,6 +28,10 @@ wandb_watch:
 wandb_name:
 wandb_log_model:
 
+trackio_project_name:
+trackio_run_name:
+trackio_space_id:
+
 gradient_accumulation_steps: 2
 micro_batch_size: 1
 num_epochs: 1

examples/gpt-oss/gpt-oss-20b-sft-lora-singlegpu.yaml

@@ -41,6 +41,10 @@ wandb_watch:
 wandb_name:
 wandb_log_model:
 
+trackio_project_name:
+trackio_run_name:
+trackio_space_id:
+
 gradient_accumulation_steps: 8
 micro_batch_size: 1
 num_epochs: 1

examples/gpt-oss/gpt-oss-safeguard-20b-sft-lora-singlegpu.yaml

@@ -41,6 +41,10 @@ wandb_watch:
 wandb_name:
 wandb_log_model:
 
+trackio_project_name:
+trackio_run_name:
+trackio_space_id:
+
 gradient_accumulation_steps: 8
 micro_batch_size: 1
 num_epochs: 1

examples/llama-3/3b-fp8-fsdp2.yaml

@@ -29,7 +29,6 @@ flex_attention: true
 flex_attn_compile_kwargs:
   dynamic: false
   mode: max-autotune-no-cudagraphs
-save_strategy: no
 torch_compile: true
 
 wandb_project:

examples/magistral/README.md

@@ -13,7 +13,7 @@ Thanks to the team at MistralAI for giving us early access to prepare for these
     Here is an example of how to install from pip:
 
 ```bash
-# Ensure you have Pytorch installed (Pytorch 2.6.0 min)
+# Ensure you have Pytorch installed (Pytorch 2.7.0 min)
 pip3 install packaging==23.2 setuptools==75.8.0 wheel ninja
 pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
 ```

examples/ministral/README.md

@@ -0,0 +1,50 @@
+# Finetune Ministral with Axolotl
+
+Ministral is a family of openweight models from MistralAI found on [HuggingFace](mistralai/Ministral-8B-Instruct-2410). This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
+
+## Getting started
+
+1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
+
+2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
+
+3. Run the finetuning example:
+
+    ```bash
+    axolotl train examples/ministral/ministral-small-qlora.yaml
+    ```
+
+This config uses about 8.76 GiB VRAM.
+
+Let us know how it goes. Happy finetuning! 🚀
+
+### Tips
+
+- We recommend adding the same/similar SystemPrompt that the model is tuned for. You can find this within the repo's files titled `SYSTEM_PROMPT.txt`.
+- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
+- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
+- The text dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
+
+## Optimization Guides
+
+Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
+
+## Limitations
+
+We only support the `mistral-common` tokenizer for Supervised Fine-tuning at the moment and for `type: chat_template` only.
+
+In addition, we do not support overriding tokens yet.
+
+## Related Resources
+
+- [MistralAI Ministral Blog](https://mistral.ai/news/ministraux)
+- [Axolotl Docs](https://docs.axolotl.ai)
+- [Axolotl Website](https://axolotl.ai)
+- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
+- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
+
+
+## Future Work
+
+- Add parity to Preference Tuning, RL, etc.
+- Add parity to other tokenizer configs like overriding tokens.

examples/ministral/ministral-small-qlora.yaml

@@ -0,0 +1,67 @@
+base_model: mistralai/Ministral-8B-Instruct-2410
+
+# Enable to use mistral-common tokenizer
+tokenizer_use_mistral_common: true
+
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+load_in_8bit: false
+load_in_4bit: true
+
+datasets:
+  - path: fozziethebeat/alpaca_messages_2k_test
+    type: chat_template
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./outputs/lora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: false
+
+gradient_checkpointing: true
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 1
+saves_per_epoch: 1
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/ministral3/README.md

@@ -0,0 +1,79 @@
+# Finetune Ministral3 with Axolotl
+
+Ministral3 is a family of open-weight models from MistralAI found on [HuggingFace](https://huggingface.co/collections/mistralai/ministral-3). This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
+
+Please see [Thinking](#thinking) and [Vision](#vision) for their respective fine-tuning.
+
+Thanks to the team at MistralAI for giving us early access to prepare for these releases.
+
+Note: This is still experimental given it is based on transformers v5 RC.
+
+## Getting started
+
+1. Install Axolotl from source following the [installation guide](https://docs.axolotl.ai/docs/installation.html#sec-edge-build).
+
+2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
+
+3. Swap to the Axolotl transformers v5 branch
+
+    ```bash
+    cp examples/ministral3/ministral3-3b-qlora.yaml ministral3-3b-qlora.yaml
+
+    git fetch
+    git checkout transformers-v5
+
+    # Install packages for transformers v5
+    pip install -e .
+    ```
+
+4. Run the fine-tuning:
+
+    ```bash
+    axolotl train ministral3-3b-qlora.yaml
+    ```
+
+Let us know how it goes. Happy finetuning! 🚀
+
+
+### Tips
+
+- We recommend adding the same/similar SystemPrompt that the model is tuned for. You can find this within the repo's files titled `SYSTEM_PROMPT.txt`.
+- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
+- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
+- The text dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
+
+### Thinking
+
+Ministral3 2512 model supports thinking capabilities, enabling Chain-of-Thought reasoning with explicit thinking steps.
+
+📚 **[See the Thinking fine-tuning guide →](./think/README.md)**
+
+### Vision
+
+Ministral3 2512 model also supports vision capabilities.
+
+📚 **[See the Vision fine-tuning guide →](./vision/README.md)**
+
+## Optimization Guides
+
+Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
+
+## Limitations
+
+We only support the `mistral-common` tokenizer for Supervised Fine-tuning at the moment and for `type: chat_template` only.
+
+In addition, we do not support overriding tokens yet.
+
+## Related Resources
+
+- [MistralAI Mistral3 Blog](https://mistral.ai/news/mistral-3)
+- [Axolotl Docs](https://docs.axolotl.ai)
+- [Axolotl Website](https://axolotl.ai)
+- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
+- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)
+
+
+## Future Work
+
+- Add parity to Preference Tuning, RL, etc.
+- Add parity to other tokenizer configs like overriding tokens.

examples/ministral3/ministral3-3b-qlora.yaml

@@ -0,0 +1,67 @@
+base_model: mistralai/Ministral-3-3B-Reasoning-2512
+
+# Enable to use mistral-common tokenizer
+tokenizer_use_mistral_common: true
+
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+load_in_8bit: false
+load_in_4bit: true
+
+datasets:
+  - path: fozziethebeat/alpaca_messages_2k_test
+    type: chat_template
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./outputs/lora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: false
+
+gradient_checkpointing: true
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 1
+saves_per_epoch: 1
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/ministral3/think/README.md

@@ -0,0 +1,73 @@
+# Ministral3 2512 Thinking Fine-tuning
+
+This guide covers fine-tuning [Ministral3 2512](https://huggingface.co/collections/mistralai/ministral-3) with thinking capabilities using Axolotl. The thinking model enables explicit Chain-of-Thought reasoning with separate thinking and response sections.
+
+## Prerequisites
+
+Before starting, ensure you have:
+- Installed Axolotl (see [main README](../README.md))
+
+## Getting Started
+
+Run the thinking model fine-tuning:
+
+```bash
+axolotl train examples/ministral3/think/ministral3-3b-think-qlora.yaml
+```
+
+This config uses about 4.76 GiB VRAM.
+
+### Tips
+
+- Dataset uses multi-content format with `type: thinking` support. See [Dataset Format](#dataset-format) below.
+- You cannot mix `content: str` and `content: list[dict]`, otherwise, dataset loading will fail. Keep it consistent.
+
+## Dataset Format
+
+The thinking model requires the multi-content dataset format with support for an extra `role: thinking` within system and assistant messages.
+
+Example format:
+
+```json
+{
+    "messages": [
+        {
+            "role": "system",
+            "content": [
+                { "type": "text", "text": "{SYSTEM_PROMPT}"}
+            ]
+        },
+        {
+            "role": "user",
+            "content": [
+                { "type": "text", "text": "Solve this step by step: What is 15% of 240?"}
+            ]
+        },
+        {
+            "role": "assistant",
+            "content": [
+                {
+                    "type": "thinking",
+                    "thinking": "I need to calculate 15% of 240. First, I'll convert 15% to decimal: 0.15. Then multiply: 0.15 × 240 = 36."
+                },
+                {
+                    "type": "text",
+                    "text": "To find 15% of 240, I'll multiply 240 by 0.15:\n\n240 × 0.15 = 36\n\nTherefore, 15% of 240 is 36."
+                }
+            ]
+        }
+    ]
+}
+```
+
+### Advanced Options
+
+The `thinking` section supports an optional `closed` parameter:
+
+```json
+{
+    "type": "thinking",
+    "thinking": "Internal reasoning here...",
+    "closed": true  // Default: true, controls adding the closing [/THINK] tag
+}
+```

examples/ministral3/think/ministral3-3b-think-qlora.yaml

@@ -0,0 +1,67 @@
+base_model: mistralai/Ministral-3-3B-Reasoning-2512
+
+# Enable to use mistral-common tokenizer
+tokenizer_use_mistral_common: true
+
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+load_in_8bit: false
+load_in_4bit: true
+
+datasets:
+  - path: Nanobit/text-think-2k-test
+    type: chat_template
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0
+output_dir: ./outputs/lora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: false
+
+gradient_checkpointing: true
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 1
+saves_per_epoch: 1
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/ministral3/vision/README.md

@@ -0,0 +1,57 @@
+# Ministral3 2512 Vision Fine-tuning
+
+This guide covers fine-tuning [Ministral3 2512](https://huggingface.co/collections/mistralai/ministral-3) with vision capabilities using Axolotl.
+
+## Prerequisites
+
+Before starting, ensure you have:
+- Installed Axolotl from source (see [main README](../README.md#getting-started))
+
+## Getting started
+
+1. Install the required vision lib:
+    ```bash
+    pip install 'mistral-common[opencv]==1.8.6'
+    ```
+
+2. Download the example dataset image:
+   ```bash
+   wget https://huggingface.co/datasets/Nanobit/text-vision-2k-test/resolve/main/African_elephant.jpg
+   ```
+
+3. Run the fine-tuning:
+   ```bash
+   axolotl train examples/ministral3/vision/ministral3-3b-vision-qlora.yml
+   ```
+
+WARNING: The loss and grad norm will be much higher than normal at first. We suspect this to be inherent to the model as of the moment. If anyone would like to submit a fix for this, we are happy to take a look.
+
+### Tips
+
+Key differences from text-only model:
+- Multi-modal dataset format required
+- Sample packing not supported
+
+## Dataset Format
+
+The vision model requires multi-modal dataset format as documented [here](https://docs.axolotl.ai/docs/multimodal.html#dataset-format).
+
+One exception is that, passing `"image": PIL.Image` is not supported. MistralTokenizer only supports `path`, `url`, and `base64` for now.
+
+Example:
+```json
+{
+    "messages": [
+        {"role": "system", "content": [{ "type": "text", "text": "{SYSTEM_PROMPT}"}]},
+        {"role": "user", "content": [
+            { "type": "text", "text": "What's in this image?"},
+            {"type": "image", "path": "path/to/image.jpg" }
+        ]},
+        {"role": "assistant", "content": [{ "type": "text", "text": "..." }]},
+    ],
+}
+```
+
+## Limitations
+
+- Sample Packing is not supported for multi-modality training currently.

examples/ministral3/vision/ministral3-3b-vision-qlora.yml

@@ -0,0 +1,64 @@
+base_model: mistralai/Ministral-3-3B-Reasoning-2512
+processor_type: AutoProcessor
+
+# Enable to use mistral-common tokenizer
+tokenizer_use_mistral_common: true
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+load_in_4bit: true
+
+# these 3 lines are needed for now to handle vision chat templates w images
+skip_prepare_dataset: true
+remove_unused_columns: false
+sample_packing: false
+
+# sample dataset below requires downloading image in advance
+# wget https://huggingface.co/datasets/Nanobit/text-vision-2k-test/resolve/main/African_elephant.jpg
+datasets:
+  - path: Nanobit/text-vision-2k-test
+    type: chat_template
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
+output_dir: ./outputs/out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: true
+fp16:
+tf32: true
+
+gradient_checkpointing: true
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 1
+saves_per_epoch: 1
+weight_decay: 0.0
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/olmo3/README.md

@@ -6,24 +6,16 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations
 
 ## Getting started
 
-1.  Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
+1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
+
+2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
+
+3. Run the finetuning example:
 
-    Here is an example of how to install from pip:
     ```bash
-    # Ensure you have a compatible version of Pytorch installed
-    pip3 install packaging setuptools wheel ninja
-    pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
-
-    # Install Cut Cross Entropy
-    python scripts/cutcrossentropy_install.py | sh
+    axolotl train examples/olmo3/olmo3-7b-qlora.yaml
     ```
 
-2. Run the finetuning example:
-
-```bash
-axolotl train examples/olmo3/olmo3-7b-qlora.yaml
-```
-
 Let us know how it goes. Happy finetuning! 🚀
 
 ### TIPS

examples/qat_nvfp4/Gemma3-12B_baseline.yml

@@ -0,0 +1,67 @@
+base_model: google/gemma-3-12b-it
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: gemma3
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+
+output_dir: ./outputs/out_gemma/
+
+sequence_len: 8096
+sample_packing: true
+flash_attention: true
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 4e-5
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Gemma3DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Gemma3-12B_qat.yml

@@ -0,0 +1,72 @@
+base_model: google/gemma-3-12b-it
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: gemma3
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+
+output_dir: ./outputs/qat_out_gemma/
+
+sequence_len: 8096
+sample_packing: true
+flash_attention: true
+
+qat:
+  activation_dtype: nvfp4
+  weight_dtype: nvfp4
+  group_size: 16 # only group_size of 16 is supported with nvfp4
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 4e-5
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Gemma3DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Math-Gemma3-12B_baseline.yml

@@ -0,0 +1,67 @@
+base_model: google/gemma-3-12b-it
+# Math finetuning configuration for Gemma3-12B
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: gemma3
+datasets:
+  - path: AI-MO/NuminaMath-CoT
+    type: chat_template
+
+output_dir: ./outputs/out_math_gemma/
+
+sequence_len: 4096
+sample_packing: true
+flash_attention: true
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 8
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 3e-5
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Gemma3DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Math-Gemma3-12B_qat.yml

@@ -0,0 +1,72 @@
+base_model: google/gemma-3-12b-it
+# Math finetuning configuration for Gemma3-12B
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: gemma3
+datasets:
+  - path: AI-MO/NuminaMath-CoT
+    type: chat_template
+
+output_dir: ./outputs/qat_out_math_gemma/
+
+sequence_len: 4096
+sample_packing: true
+flash_attention: true
+
+qat:
+  activation_dtype: nvfp4
+  weight_dtype: nvfp4
+  group_size: 16 # only group_size of 16 is supported with nvfp4
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 8
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 3e-5
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Gemma3DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Math-Gemma3-27B_baseline.yml

@@ -0,0 +1,68 @@
+base_model: google/gemma-3-27b-it
+# Math finetuning configuration for Gemma3-27B
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: gemma3
+datasets:
+  - path: AI-MO/NuminaMath-CoT
+    type: chat_template
+
+output_dir: ./outputs/out_math_gemma27/
+
+sequence_len: 4096
+sample_packing: true
+flash_attention: true
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 5e-6
+eta_min: 7e-7
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Gemma3DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Math-Gemma3-27B_qat.yml

@@ -0,0 +1,73 @@
+base_model: google/gemma-3-27b-it
+# Math finetuning configuration for Gemma3-27B
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: gemma3
+datasets:
+  - path: AI-MO/NuminaMath-CoT
+    type: chat_template
+
+output_dir: ./outputs/qat_out_math_gemma27/
+
+sequence_len: 4096
+sample_packing: true
+flash_attention: true
+
+qat:
+  activation_dtype: nvfp4
+  weight_dtype: nvfp4
+  group_size: 16 # only group_size of 16 is supported with nvfp4
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 5e-6
+eta_min: 7e-7
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Gemma3DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Math-Qwen2.5-72B_baseline.yml

@@ -0,0 +1,67 @@
+base_model: Qwen/Qwen2.5-72B
+# Math finetuning configuration for Qwen2.5-72B (non-instruct)
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: qwen_25
+datasets:
+  - path: AI-MO/NuminaMath-CoT
+    type: chat_template
+
+output_dir: ./outputs/out_math_72b/
+
+sequence_len: 4096
+sample_packing: true
+flash_attention: true
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 8
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 5e-6
+eta_min: 7e-7
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Math-Qwen2.5-72B_qat.yml

@@ -0,0 +1,72 @@
+base_model: Qwen/Qwen2.5-72B
+# Math finetuning configuration for Qwen2.5-72B (non-instruct)
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: qwen_25
+datasets:
+  - path: AI-MO/NuminaMath-CoT
+    type: chat_template
+
+output_dir: ./outputs/qat_out_math_72b/
+
+sequence_len: 4096
+sample_packing: true
+flash_attention: true
+
+qat:
+  activation_dtype: nvfp4
+  weight_dtype: nvfp4
+  group_size: 16 # only group_size of 16 is supported with nvfp4
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 8
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 5e-6
+eta_min: 7e-7
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Qwen2.5-72B_baseline.yml

@@ -0,0 +1,67 @@
+base_model: Qwen/Qwen2.5-72B
+# Alpaca finetuning configuration for Qwen2.5-72B
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: qwen_25
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+
+output_dir: ./outputs/out_qwen72b/
+
+sequence_len: 8096
+sample_packing: true
+flash_attention: true
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 2e-5
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qat_nvfp4/Qwen2.5-72B_qat.yml

@@ -0,0 +1,72 @@
+base_model: Qwen/Qwen2.5-72B
+# Alpaca finetuning configuration for Qwen2.5-72B
+# hub_model_id: username/custom_model_name
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+seed: 42
+chat_template: qwen_25
+datasets:
+  - path: tatsu-lab/alpaca
+    type: alpaca
+
+output_dir: ./outputs/qat_out_qwen72b/
+
+sequence_len: 8096
+sample_packing: true
+flash_attention: true
+
+qat:
+  activation_dtype: nvfp4
+  weight_dtype: nvfp4
+  group_size: 16 # only group_size of 16 is supported with nvfp4
+
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+
+num_epochs: 1
+optimizer: adamw_torch_fused
+lr_scheduler: cosine
+learning_rate: 2e-5
+
+bf16: true
+tf32: true
+
+resume_from_checkpoint:
+logging_steps: 1
+
+# evals_per_epoch: 1
+saves_per_epoch: 1
+
+warmup_ratio: 0.1
+weight_decay: 0.0
+fsdp_version: 2
+
+fsdp_config:
+  offload_params: false
+  cpu_ram_efficient_loading: true
+  auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  state_dict_type: FULL_STATE_DICT
+  sharding_strategy: FULL_SHARD
+  reshard_after_forward: true
+  activation_checkpointing: true
+
+special_tokens:
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/qwen2/adamw-pretrain-fsdp2.yaml

@@ -0,0 +1,70 @@
+base_model: Qwen/Qwen2.5-0.5B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+# Use random initialization for fair comparison
+reinit_weights: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+# Pretraining dataset
+pretraining_dataset:
+  - path: allenai/c4
+    name: en
+    type: pretrain
+    split: train
+
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./outputs/compare-adamw-pretrain
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project: dist_muon
+wandb_entity:
+wandb_watch:
+wandb_name: adamw
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 1
+max_steps: 305
+
+# AdamW optimizer settings (standard LR for AdamW)
+optimizer: adamw_torch_fused
+learning_rate: 0.0002
+weight_decay: 0.01
+lr_scheduler: cosine
+
+train_on_inputs: true
+group_by_length: false
+bf16: auto
+fp16: false
+tf32: false
+
+gradient_checkpointing: false
+logging_steps: 1
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 0
+saves_per_epoch: 1
+
+# Reproducibility
+seed: 42
+
+fsdp_config:
+  fsdp_version: 2
+  fsdp_offload_params: false
+  fsdp_state_dict_type: FULL_STATE_DICT
+  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  fsdp_cpu_ram_efficient_loading: false
+  fsdp_reshard_after_forward: true
+
+special_tokens:

examples/qwen2/muon-pretrain-fsdp2.yaml

@@ -0,0 +1,70 @@
+base_model: Qwen/Qwen2.5-0.5B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+# Use random initialization for fair comparison
+reinit_weights: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+# Pretraining dataset
+pretraining_dataset:
+  - path: allenai/c4
+    name: en
+    type: pretrain
+    split: train
+
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./outputs/compare-muon-pretrain
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project: dist_muon
+wandb_entity:
+wandb_watch:
+wandb_name: muon
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 1
+max_steps: 305
+
+# Muon optimizer settings
+optimizer: muon
+learning_rate: 0.02
+weight_decay: 0.01
+lr_scheduler: cosine
+
+train_on_inputs: true
+group_by_length: false
+bf16: auto
+fp16: false
+tf32: false
+
+gradient_checkpointing: false
+logging_steps: 1
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 0
+saves_per_epoch: 1
+
+# Reproducibility
+seed: 42
+
+fsdp_config:
+  fsdp_version: 2
+  fsdp_offload_params: false
+  fsdp_state_dict_type: FULL_STATE_DICT
+  fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
+  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  fsdp_cpu_ram_efficient_loading: false
+  fsdp_reshard_after_forward: true
+
+special_tokens:

examples/qwen3/README.md

@@ -0,0 +1,46 @@
+# Finetune Qwen3 with Axolotl
+
+[Qwen3](https://huggingface.co/collections/Qwen/qwen3) are a family of open source models trained by Alibaba.
+
+This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
+
+## Getting started
+
+1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
+
+2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
+
+3. Run the finetuning example:
+
+    ```bash
+    axolotl train examples/qwen3/32b-qlora.yaml
+    ```
+
+Let us know how it goes. Happy finetuning! 🚀
+
+### Chat template masking a few tokens off
+
+If you notice that the `chat_template` masking for assistant prompts are off by a few tokens, please ensure that you are adding the below to the yaml.
+
+```yaml
+chat_template: qwen3
+```
+
+### TIPS
+
+- For inference, please check the official model card as it depends on your reasoning mode.
+- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
+- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
+- The dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
+
+## Optimization Guides
+
+Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
+
+## Related Resources
+
+- [Qwen3 Blog](https://qwenlm.github.io/blog/qwen3/)
+- [Axolotl Docs](https://docs.axolotl.ai)
+- [Axolotl Website](https://axolotl.ai)
+- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
+- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)

examples/trinity/README.md

@@ -0,0 +1,38 @@
+# Finetune ArceeAI's Trinity with Axolotl
+
+[Trinity](https://huggingface.co/collections/arcee-ai/trinity) is a family of open weight MoE models trained by Arcee.ai.
+
+This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
+
+## Getting started
+
+1. Install Axolotl following the main from the [installation guide](https://docs.axolotl.ai/docs/installation.html#sec-edge-build).
+
+2. Run the finetuning example:
+
+    ```bash
+    axolotl train examples/trinity/trinity-nano-preview-qlora.yaml
+    ```
+
+This config uses about 24.9 GiB VRAM.
+
+Let us know how it goes. Happy finetuning! 🚀
+
+### TIPS
+
+- For inference, the official Arcee.ai team recommends `top_p: 0.75`, `temperature: 0.15`, `top_k: 50`, and `min_p: 0.06`.
+- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
+- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
+- The dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
+
+## Optimization Guides
+
+Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
+
+## Related Resources
+
+- [Trinity Blog](https://www.arcee.ai/blog/the-trinity-manifesto)
+- [Axolotl Docs](https://docs.axolotl.ai)
+- [Axolotl Website](https://axolotl.ai)
+- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
+- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)

examples/trinity/trinity-nano-preview-qlora.yaml

@@ -0,0 +1,67 @@
+base_model: arcee-ai/Trinity-Nano-Preview
+trust_remote_code: true
+
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+# CCE - N/A as of now
+# plugins:
+#   - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+load_in_8bit: false
+load_in_4bit: true
+
+datasets:
+  - path: fozziethebeat/alpaca_messages_2k_test
+    type: chat_template
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./outputs/lora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: false
+
+gradient_checkpointing: true
+resume_from_checkpoint:
+logging_steps: 1
+# flash_attention: true  # Not supported
+sdp_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 1
+saves_per_epoch: 1
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config