From 119056a34116e28ff722bfdfb647ae54b02ec19f Mon Sep 17 00:00:00 2001 From: Quarto GHA Workflow Runner Date: Thu, 25 Dec 2025 12:24:45 +0000 Subject: [PATCH] Built site for gh-pages --- .nojekyll | 2 +- FAQS.html | 265 ++- docs/amd_hpc.html | 265 ++- docs/api/cli.args.html | 265 ++- docs/api/cli.art.html | 265 ++- docs/api/cli.checks.html | 265 ++- docs/api/cli.cloud.base.html | 265 ++- docs/api/cli.cloud.modal_.html | 265 ++- docs/api/cli.config.html | 265 ++- docs/api/cli.delinearize_llama4.html | 265 ++- docs/api/cli.evaluate.html | 265 ++- docs/api/cli.inference.html | 265 ++- docs/api/cli.main.html | 265 ++- docs/api/cli.merge_lora.html | 265 ++- docs/api/cli.merge_sharded_fsdp_weights.html | 265 ++- docs/api/cli.preprocess.html | 265 ++- docs/api/cli.quantize.html | 265 ++- docs/api/cli.train.html | 265 ++- docs/api/cli.utils.args.html | 265 ++- docs/api/cli.utils.fetch.html | 265 ++- docs/api/cli.utils.html | 265 ++- docs/api/cli.utils.load.html | 265 ++- docs/api/cli.utils.sweeps.html | 265 ++- docs/api/cli.utils.train.html | 265 ++- docs/api/cli.vllm_serve.html | 265 ++- docs/api/common.architectures.html | 265 ++- docs/api/common.const.html | 265 ++- docs/api/common.datasets.html | 265 ++- docs/api/convert.html | 265 ++- docs/api/core.builders.base.html | 265 ++- docs/api/core.builders.causal.html | 265 ++- docs/api/core.builders.rl.html | 265 ++- docs/api/core.chat.format.chatml.html | 265 ++- docs/api/core.chat.format.llama3x.html | 265 ++- docs/api/core.chat.format.shared.html | 265 ++- docs/api/core.chat.messages.html | 265 ++- docs/api/core.datasets.chat.html | 265 ++- ...core.datasets.transforms.chat_builder.html | 265 ++- docs/api/core.trainers.base.html | 265 ++- docs/api/core.trainers.dpo.trainer.html | 265 ++- docs/api/core.trainers.grpo.sampler.html | 265 ++- docs/api/core.trainers.grpo.trainer.html | 265 ++- docs/api/core.trainers.mamba.html | 265 ++- docs/api/core.trainers.mixins.optimizer.html | 265 ++- ...core.trainers.mixins.rng_state_loader.html | 265 ++- docs/api/core.trainers.mixins.scheduler.html | 265 ++- docs/api/core.trainers.trl.html | 265 ++- docs/api/core.trainers.utils.html | 265 ++- docs/api/core.training_args.html | 265 ++- docs/api/datasets.html | 265 ++- docs/api/evaluate.html | 265 ++- docs/api/index.html | 265 ++- docs/api/integrations.base.html | 265 ++- .../integrations.cut_cross_entropy.args.html | 265 ++- docs/api/integrations.grokfast.optimizer.html | 265 ++- docs/api/integrations.kd.trainer.html | 265 ++- docs/api/integrations.liger.args.html | 265 ++- docs/api/integrations.lm_eval.args.html | 265 ++- docs/api/integrations.spectrum.args.html | 265 ++- docs/api/kernels.geglu.html | 265 ++- docs/api/kernels.lora.html | 265 ++- docs/api/kernels.quantize.html | 265 ++- docs/api/kernels.swiglu.html | 265 ++- docs/api/kernels.utils.html | 265 ++- docs/api/loaders.adapter.html | 265 ++- docs/api/loaders.constants.html | 265 ++- docs/api/loaders.model.html | 265 ++- docs/api/loaders.patch_manager.html | 265 ++- docs/api/loaders.processor.html | 265 ++- docs/api/loaders.tokenizer.html | 265 ++- docs/api/logging_config.html | 265 ++- docs/api/models.mamba.modeling_mamba.html | 265 ++- .../monkeypatch.btlm_attn_hijack_flash.html | 265 ++- ...onkeypatch.data.batch_dataset_fetcher.html | 265 ++- ...ch.gradient_checkpointing.offload_cpu.html | 265 ++- ...h.gradient_checkpointing.offload_disk.html | 265 ++- .../monkeypatch.llama_attn_hijack_flash.html | 265 ++- ...onkeypatch.llama_attn_hijack_xformers.html | 265 ++- docs/api/monkeypatch.llama_expand_mask.html | 265 ++- .../monkeypatch.llama_patch_multipack.html | 265 ++- docs/api/monkeypatch.lora_kernels.html | 265 ++- ...monkeypatch.mistral_attn_hijack_flash.html | 265 ++- docs/api/monkeypatch.mixtral.html | 265 ++- docs/api/monkeypatch.multipack.html | 265 ++- docs/api/monkeypatch.relora.html | 265 ++- ...onkeypatch.stablelm_attn_hijack_flash.html | 265 ++- docs/api/monkeypatch.trainer_fsdp_optim.html | 265 ++- .../monkeypatch.transformers_fa_utils.html | 265 ++- docs/api/monkeypatch.unsloth_.html | 265 ++- docs/api/monkeypatch.utils.html | 265 ++- docs/api/prompt_strategies.alpaca_chat.html | 265 ++- .../prompt_strategies.alpaca_instruct.html | 265 ++- .../prompt_strategies.alpaca_w_system.html | 265 ++- docs/api/prompt_strategies.base.html | 265 ++- ...rompt_strategies.bradley_terry.llama3.html | 265 ++- docs/api/prompt_strategies.chat_template.html | 265 ++- docs/api/prompt_strategies.completion.html | 265 ++- .../prompt_strategies.dpo.chat_template.html | 265 ++- docs/api/prompt_strategies.dpo.chatml.html | 265 ++- docs/api/prompt_strategies.dpo.llama3.html | 265 ++- .../prompt_strategies.dpo.passthrough.html | 265 ++- .../prompt_strategies.dpo.user_defined.html | 265 ++- docs/api/prompt_strategies.dpo.zephyr.html | 265 ++- docs/api/prompt_strategies.input_output.html | 265 ++- docs/api/prompt_strategies.kto.chatml.html | 265 ++- docs/api/prompt_strategies.kto.llama3.html | 265 ++- .../prompt_strategies.kto.user_defined.html | 265 ++- docs/api/prompt_strategies.llama2_chat.html | 265 ++- docs/api/prompt_strategies.messages.chat.html | 265 ++- docs/api/prompt_strategies.metharme.html | 265 ++- docs/api/prompt_strategies.orcamini.html | 265 ++- .../prompt_strategies.orpo.chat_template.html | 265 ++- docs/api/prompt_strategies.pygmalion.html | 265 ++- ...prompt_strategies.stepwise_supervised.html | 265 ++- docs/api/prompt_strategies.user_defined.html | 265 ++- docs/api/prompt_tokenizers.html | 265 ++- docs/api/train.html | 265 ++- docs/api/utils.bench.html | 265 ++- docs/api/utils.callbacks.comet_.html | 265 ++- docs/api/utils.callbacks.lisa.html | 265 ++- docs/api/utils.callbacks.mlflow_.html | 265 ++- docs/api/utils.callbacks.perplexity.html | 265 ++- docs/api/utils.callbacks.profiler.html | 265 ++- docs/api/utils.callbacks.qat.html | 265 ++- docs/api/utils.chat_templates.html | 265 ++- docs/api/utils.collators.batching.html | 265 ++- docs/api/utils.collators.core.html | 265 ++- docs/api/utils.collators.mamba.html | 265 ++- docs/api/utils.collators.mm_chat.html | 265 ++- .../utils.ctx_managers.sequence_parallel.html | 265 ++- docs/api/utils.data.sft.html | 265 ++- docs/api/utils.data.streaming.html | 265 ++- docs/api/utils.dict.html | 265 ++- docs/api/utils.distributed.html | 265 ++- docs/api/utils.freeze.html | 265 ++- docs/api/utils.lora.html | 265 ++- docs/api/utils.model_shard_quant.html | 265 ++- docs/api/utils.optimizers.adopt.html | 265 ++- docs/api/utils.quantization.html | 265 ++- docs/api/utils.samplers.multipack.html | 265 ++- docs/api/utils.schedulers.html | 265 ++- docs/api/utils.schemas.config.html | 265 ++- docs/api/utils.schemas.datasets.html | 265 ++- docs/api/utils.schemas.enums.html | 265 ++- docs/api/utils.schemas.integrations.html | 265 ++- docs/api/utils.schemas.model.html | 265 ++- docs/api/utils.schemas.multimodal.html | 265 ++- docs/api/utils.schemas.peft.html | 265 ++- docs/api/utils.schemas.training.html | 265 ++- docs/api/utils.schemas.trl.html | 265 ++- docs/api/utils.schemas.utils.html | 265 ++- docs/api/utils.tokenization.html | 265 ++- docs/api/utils.trainer.html | 265 ++- docs/batch_vs_grad.html | 265 ++- docs/cli.html | 265 ++- docs/config-reference.html | 265 ++- docs/custom_integrations.html | 265 ++- docs/dataset-formats/conversation.html | 265 ++- docs/dataset-formats/index.html | 265 ++- docs/dataset-formats/inst_tune.html | 265 ++- docs/dataset-formats/pretraining.html | 265 ++- docs/dataset-formats/stepwise_supervised.html | 265 ++- docs/dataset-formats/template_free.html | 265 ++- docs/dataset-formats/tokenized.html | 265 ++- docs/dataset_loading.html | 265 ++- docs/dataset_preprocessing.html | 265 ++- docs/debugging.html | 265 ++- docs/docker.html | 265 ++- docs/faq.html | 265 ++- docs/fsdp_qlora.html | 265 ++- docs/getting-started.html | 265 ++- docs/gradient_checkpointing.html | 265 ++- docs/inference.html | 265 ++- docs/input_output.html | 265 ++- docs/installation.html | 265 ++- docs/lora_optims.html | 265 ++- docs/lr_groups.html | 265 ++- docs/mac.html | 265 ++- docs/mixed_precision.html | 265 ++- docs/models/LiquidAI.html | 1241 ++++++++++++ docs/models/apertus.html | 1278 +++++++++++++ docs/models/arcee.html | 1237 ++++++++++++ docs/models/devstral.html | 1253 ++++++++++++ docs/models/gemma3n.html | 1249 ++++++++++++ docs/models/gpt-oss.html | 1304 +++++++++++++ docs/models/granite4.html | 1242 ++++++++++++ docs/models/hunyuan.html | 1263 ++++++++++++ docs/models/index.html | 1168 ++++++++++++ docs/models/internvl3_5.html | 1221 ++++++++++++ docs/models/jamba.html | 1151 +++++++++++ docs/models/kimi-linear.html | 1228 ++++++++++++ docs/models/llama-2.html | 1149 +++++++++++ docs/models/llama-4.html | 1211 ++++++++++++ docs/models/magistral.html | 1262 ++++++++++++ docs/models/magistral/think.html | 1252 ++++++++++++ docs/models/magistral/vision.html | 1236 ++++++++++++ docs/models/mimo.html | 1223 ++++++++++++ docs/models/ministral.html | 1234 ++++++++++++ docs/models/ministral3.html | 1256 ++++++++++++ docs/models/ministral3/think.html | 1252 ++++++++++++ docs/models/ministral3/vision.html | 1234 ++++++++++++ docs/models/mistral-small.html | 1225 ++++++++++++ docs/models/mistral.html | 1145 +++++++++++ docs/models/olmo3.html | 1220 ++++++++++++ docs/models/orpheus.html | 1516 +++++++++++++++ docs/models/phi.html | 1145 +++++++++++ docs/models/plano.html | 1225 ++++++++++++ docs/models/qwen3-next.html | 1244 ++++++++++++ docs/models/qwen3.html | 1226 ++++++++++++ docs/models/seed-oss.html | 1227 ++++++++++++ docs/models/smolvlm2.html | 1221 ++++++++++++ docs/models/trinity.html | 1225 ++++++++++++ docs/models/voxtral.html | 1263 ++++++++++++ docs/multi-gpu.html | 265 ++- docs/multi-node.html | 265 ++- docs/multimodal.html | 265 ++- docs/multipack.html | 265 ++- docs/nccl.html | 265 ++- docs/nd_parallelism.html | 265 ++- docs/optimizations.html | 265 ++- docs/optimizers.html | 265 ++- docs/qat.html | 265 ++- docs/quantize.html | 265 ++- docs/ray-integration.html | 265 ++- docs/reward_modelling.html | 265 ++- docs/rlhf.html | 265 ++- docs/sequence_parallelism.html | 265 ++- docs/streaming.html | 265 ++- docs/telemetry.html | 265 ++- docs/torchao.html | 265 ++- docs/unsloth.html | 265 ++- .../colab-axolotl-example.html | 265 ++- index.html | 277 ++- search.json | 1695 ++++++++++++++++- sitemap.xml | 536 ++++-- src/axolotl/integrations/LICENSE.html | 265 ++- .../cut_cross_entropy/ACKNOWLEDGEMENTS.html | 265 ++- 237 files changed, 93663 insertions(+), 3608 deletions(-) create mode 100644 docs/models/LiquidAI.html create mode 100644 docs/models/apertus.html create mode 100644 docs/models/arcee.html create mode 100644 docs/models/devstral.html create mode 100644 docs/models/gemma3n.html create mode 100644 docs/models/gpt-oss.html create mode 100644 docs/models/granite4.html create mode 100644 docs/models/hunyuan.html create mode 100644 docs/models/index.html create mode 100644 docs/models/internvl3_5.html create mode 100644 docs/models/jamba.html create mode 100644 docs/models/kimi-linear.html create mode 100644 docs/models/llama-2.html create mode 100644 docs/models/llama-4.html create mode 100644 docs/models/magistral.html create mode 100644 docs/models/magistral/think.html create mode 100644 docs/models/magistral/vision.html create mode 100644 docs/models/mimo.html create mode 100644 docs/models/ministral.html create mode 100644 docs/models/ministral3.html create mode 100644 docs/models/ministral3/think.html create mode 100644 docs/models/ministral3/vision.html create mode 100644 docs/models/mistral-small.html create mode 100644 docs/models/mistral.html create mode 100644 docs/models/olmo3.html create mode 100644 docs/models/orpheus.html create mode 100644 docs/models/phi.html create mode 100644 docs/models/plano.html create mode 100644 docs/models/qwen3-next.html create mode 100644 docs/models/qwen3.html create mode 100644 docs/models/seed-oss.html create mode 100644 docs/models/smolvlm2.html create mode 100644 docs/models/trinity.html create mode 100644 docs/models/voxtral.html diff --git a/.nojekyll b/.nojekyll index f4c9b0725..8bb98c46b 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -3bacccbc \ No newline at end of file +ff4d5e1c \ No newline at end of file diff --git a/FAQS.html b/FAQS.html index e7f98c9cb..d408b752e 100644 --- a/FAQS.html +++ b/FAQS.html @@ -152,6 +152,237 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true}); Inference and Merging +
  • +
    + + +
    + +
  • @@ -182,11 +413,11 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
    Dataset Formats - +
    -