diff --git a/.nojekyll b/.nojekyll index 0b7517b26..fc2ba7dc3 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -aea121d0 \ No newline at end of file +e3c6397b \ No newline at end of file diff --git a/docs/custom_integrations.html b/docs/custom_integrations.html index 5f97886c8..45fb54ec6 100644 --- a/docs/custom_integrations.html +++ b/docs/custom_integrations.html @@ -963,7 +963,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true}); -
pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@a668583"
+
pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@e8ad129"

Usage

diff --git a/examples/colab-notebooks/colab-axolotl-example.html b/examples/colab-notebooks/colab-axolotl-example.html index 13367e2e9..92cfa3323 100644 --- a/examples/colab-notebooks/colab-axolotl-example.html +++ b/examples/colab-notebooks/colab-axolotl-example.html @@ -810,7 +810,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
%%capture
 # This step can take ~5-10 minutes to install dependencies
 !pip install --no-build-isolation axolotl[flash-attn]>=0.9.1
-!pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@a668583"
+!pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@e8ad129"

Demo: Talk Like a Pirate

diff --git a/search.json b/search.json index cd25e44a6..dbb4fd340 100644 --- a/search.json +++ b/search.json @@ -3514,7 +3514,7 @@ "href": "docs/custom_integrations.html#cut-cross-entropy", "title": "Custom Integrations", "section": "Cut Cross Entropy", - "text": "Cut Cross Entropy\nCut Cross Entropy (CCE) reduces VRAM usage through optimization on the cross-entropy operation during loss calculation.\nSee https://github.com/apple/ml-cross-entropy\n\nRequirements\n\nPyTorch 2.4.0 or higher\n\n\n\nInstallation\nRun the following command to install cut_cross_entropy[transformers] if you don’t have it already.\n\nIf you are in dev environment\n\npython scripts/cutcrossentropy_install.py | sh\n\nIf you are installing from pip\n\npip3 uninstall -y cut-cross-entropy && pip3 install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@a668583\"\n\n\nUsage\nplugins:\n - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin\n\n\nSupported Models\n\nafmoe\napertus\narcee\ncohere\ncohere2\ndeepseek_v3\nexaone4\ngemma\ngemma2\ngemma3\ngemma3_text\ngemma3n\ngemma3n_text\nglm\nglm4\nglm4_moe\nglm4_moe_lite\nglm46v\nglm4v\nglm4v_moe\nglm_image\nglm_moe_dsa\ngpt_oss\ngranite\ngranitemoe\ngranitemoehybrid\ngranitemoeshared\nhunyuan_v1_dense\nhunyuan_v1_moe\ninternvl\nkimi_linear\nlfm2\nlfm2_moe\nlfm2_vl\nllama\nllama4\nllama4_text\nllava\nministral\nministral3\nmistral\nmistral3\nmixtral\nmllama\nolmo\nolmo2\nolmo3\nolmoe\nphi\nphi3\nphi4_multimodal\nqwen2\nqwen2_5_vl\nqwen2_moe\nqwen2_vl\nqwen3\nqwen3_5\nqwen3_5_text\nqwen3_5_moe\nqwen3_5_moe_text\nqwen3_moe\nqwen3_next\nqwen3_vl\nqwen3_vl_moe\nseed_oss\nsmollm3\nstep3p5\nvoxtral\n\n\n\nCitation\n@article{wijmans2024cut,\n author = {Erik Wijmans and\n Brody Huval and\n Alexander Hertzberg and\n Vladlen Koltun and\n Philipp Kr\\\"ahenb\\\"uhl},\n title = {Cut Your Losses in Large-Vocabulary Language Models},\n journal = {arXiv},\n year = {2024},\n url = {https://arxiv.org/abs/2411.09009},\n}\nPlease see reference here", + "text": "Cut Cross Entropy\nCut Cross Entropy (CCE) reduces VRAM usage through optimization on the cross-entropy operation during loss calculation.\nSee https://github.com/apple/ml-cross-entropy\n\nRequirements\n\nPyTorch 2.4.0 or higher\n\n\n\nInstallation\nRun the following command to install cut_cross_entropy[transformers] if you don’t have it already.\n\nIf you are in dev environment\n\npython scripts/cutcrossentropy_install.py | sh\n\nIf you are installing from pip\n\npip3 uninstall -y cut-cross-entropy && pip3 install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@e8ad129\"\n\n\nUsage\nplugins:\n - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin\n\n\nSupported Models\n\nafmoe\napertus\narcee\ncohere\ncohere2\ndeepseek_v3\nexaone4\ngemma\ngemma2\ngemma3\ngemma3_text\ngemma3n\ngemma3n_text\nglm\nglm4\nglm4_moe\nglm4_moe_lite\nglm46v\nglm4v\nglm4v_moe\nglm_image\nglm_moe_dsa\ngpt_oss\ngranite\ngranitemoe\ngranitemoehybrid\ngranitemoeshared\nhunyuan_v1_dense\nhunyuan_v1_moe\ninternvl\nkimi_linear\nlfm2\nlfm2_moe\nlfm2_vl\nllama\nllama4\nllama4_text\nllava\nministral\nministral3\nmistral\nmistral3\nmixtral\nmllama\nolmo\nolmo2\nolmo3\nolmoe\nphi\nphi3\nphi4_multimodal\nqwen2\nqwen2_5_vl\nqwen2_moe\nqwen2_vl\nqwen3\nqwen3_5\nqwen3_5_text\nqwen3_5_moe\nqwen3_5_moe_text\nqwen3_moe\nqwen3_next\nqwen3_vl\nqwen3_vl_moe\nseed_oss\nsmollm3\nstep3p5\nvoxtral\n\n\n\nCitation\n@article{wijmans2024cut,\n author = {Erik Wijmans and\n Brody Huval and\n Alexander Hertzberg and\n Vladlen Koltun and\n Philipp Kr\\\"ahenb\\\"uhl},\n title = {Cut Your Losses in Large-Vocabulary Language Models},\n journal = {arXiv},\n year = {2024},\n url = {https://arxiv.org/abs/2411.09009},\n}\nPlease see reference here", "crumbs": [ "Advanced Features", "Custom Integrations" diff --git a/sitemap.xml b/sitemap.xml index 17e0aa693..c56eb7d1f 100644 --- a/sitemap.xml +++ b/sitemap.xml @@ -2,950 +2,950 @@ https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html - 2026-03-06T14:31:29.659Z + 2026-03-06T17:41:58.501Z https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html - 2026-03-06T14:31:29.674Z + 2026-03-06T17:41:58.522Z https://docs.axolotl.ai/docs/inference.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/expert_quantization.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/installation.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/models/ministral3/think.html - 2026-03-06T14:34:59.466Z + 2026-03-06T17:45:35.982Z https://docs.axolotl.ai/docs/models/granite4.html - 2026-03-06T14:34:59.472Z + 2026-03-06T17:45:35.990Z https://docs.axolotl.ai/docs/models/seed-oss.html - 2026-03-06T14:34:59.472Z + 2026-03-06T17:45:35.988Z https://docs.axolotl.ai/docs/models/orpheus.html - 2026-03-06T14:34:59.474Z + 2026-03-06T17:45:35.992Z https://docs.axolotl.ai/docs/models/internvl3_5.html - 2026-03-06T14:34:59.465Z + 2026-03-06T17:45:35.979Z https://docs.axolotl.ai/docs/models/magistral/vision.html - 2026-03-06T14:34:59.468Z + 2026-03-06T17:45:35.984Z https://docs.axolotl.ai/docs/models/mimo.html - 2026-03-06T14:34:59.464Z + 2026-03-06T17:45:35.979Z https://docs.axolotl.ai/docs/models/gpt-oss.html - 2026-03-06T14:34:59.471Z + 2026-03-06T17:45:35.988Z https://docs.axolotl.ai/docs/models/qwen3-next.html - 2026-03-06T14:34:59.470Z + 2026-03-06T17:45:35.987Z https://docs.axolotl.ai/docs/models/llama-2.html - 2026-03-06T14:34:59.470Z + 2026-03-06T17:45:35.986Z https://docs.axolotl.ai/docs/models/kimi-linear.html - 2026-03-06T14:34:59.463Z + 2026-03-06T17:45:35.978Z https://docs.axolotl.ai/docs/models/smolvlm2.html - 2026-03-06T14:34:59.472Z + 2026-03-06T17:45:35.989Z https://docs.axolotl.ai/docs/models/olmo3.html - 2026-03-06T14:34:59.465Z + 2026-03-06T17:45:35.980Z https://docs.axolotl.ai/docs/models/jamba.html - 2026-03-06T14:34:59.473Z + 2026-03-06T17:45:35.991Z https://docs.axolotl.ai/docs/models/mistral-small.html - 2026-03-06T14:34:59.468Z + 2026-03-06T17:45:35.984Z https://docs.axolotl.ai/docs/models/devstral.html - 2026-03-06T14:34:59.469Z + 2026-03-06T17:45:35.985Z https://docs.axolotl.ai/docs/models/index.html - 2026-03-06T14:34:59.474Z + 2026-03-06T17:45:35.992Z https://docs.axolotl.ai/docs/lora_optims.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/cli.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/gradient_checkpointing.html - 2026-03-06T14:31:29.653Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset_preprocessing.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/docker.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/attention.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html - 2026-03-06T14:34:38.244Z + 2026-03-06T17:45:11.401Z https://docs.axolotl.ai/docs/api/loaders.adapter.html - 2026-03-06T14:34:38.068Z + 2026-03-06T17:45:11.208Z https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html - 2026-03-06T14:34:38.552Z + 2026-03-06T17:45:11.739Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html - 2026-03-06T14:34:38.554Z + 2026-03-06T17:45:11.741Z https://docs.axolotl.ai/docs/api/core.trainers.utils.html - 2026-03-06T14:34:38.039Z + 2026-03-06T17:45:11.177Z https://docs.axolotl.ai/docs/api/utils.data.sft.html - 2026-03-06T14:34:38.753Z + 2026-03-06T17:45:11.959Z https://docs.axolotl.ai/docs/api/utils.schemas.peft.html - 2026-03-06T14:34:38.838Z + 2026-03-06T17:45:12.051Z https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html - 2026-03-06T14:34:38.541Z + 2026-03-06T17:45:11.727Z https://docs.axolotl.ai/docs/api/utils.collators.mamba.html - 2026-03-06T14:34:39.115Z + 2026-03-06T17:45:12.353Z https://docs.axolotl.ai/docs/api/prompt_strategies.base.html - 2026-03-06T14:34:38.137Z + 2026-03-06T17:45:11.285Z https://docs.axolotl.ai/docs/api/loaders.processor.html - 2026-03-06T14:34:38.062Z + 2026-03-06T17:45:11.201Z https://docs.axolotl.ai/docs/api/core.training_args.html - 2026-03-06T14:34:37.680Z + 2026-03-06T17:45:10.691Z https://docs.axolotl.ai/docs/api/loaders.tokenizer.html - 2026-03-06T14:34:38.060Z + 2026-03-06T17:45:11.199Z https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html - 2026-03-06T14:34:38.237Z + 2026-03-06T17:45:11.394Z https://docs.axolotl.ai/docs/api/loaders.constants.html - 2026-03-06T14:34:38.091Z + 2026-03-06T17:45:11.233Z https://docs.axolotl.ai/docs/api/cli.utils.train.html - 2026-03-06T14:34:37.964Z + 2026-03-06T17:45:11.055Z https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html - 2026-03-06T14:34:38.561Z + 2026-03-06T17:45:11.748Z https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html - 2026-03-06T14:34:38.828Z + 2026-03-06T17:45:12.040Z https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html - 2026-03-06T14:34:38.230Z + 2026-03-06T17:45:11.386Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html - 2026-03-06T14:34:38.500Z + 2026-03-06T17:45:11.681Z https://docs.axolotl.ai/docs/api/common.datasets.html - 2026-03-06T14:34:39.087Z + 2026-03-06T17:45:12.323Z https://docs.axolotl.ai/docs/api/logging_config.html - 2026-03-06T14:34:37.647Z + 2026-03-06T17:45:10.653Z https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html - 2026-03-06T14:34:38.573Z + 2026-03-06T17:45:11.762Z https://docs.axolotl.ai/docs/api/integrations.liger.args.html - 2026-03-06T14:34:39.059Z + 2026-03-06T17:45:12.292Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html - 2026-03-06T14:34:38.293Z + 2026-03-06T17:45:11.456Z https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html - 2026-03-06T14:34:38.038Z + 2026-03-06T17:45:11.175Z https://docs.axolotl.ai/docs/api/core.chat.messages.html - 2026-03-06T14:34:37.706Z + 2026-03-06T17:45:10.721Z https://docs.axolotl.ai/docs/api/integrations.base.html - 2026-03-06T14:34:39.042Z + 2026-03-06T17:45:12.272Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html - 2026-03-06T14:34:38.281Z + 2026-03-06T17:45:11.443Z https://docs.axolotl.ai/docs/api/train.html - 2026-03-06T14:34:37.552Z + 2026-03-06T17:45:10.543Z https://docs.axolotl.ai/docs/api/utils.distributed.html - 2026-03-06T14:34:38.729Z + 2026-03-06T17:45:11.933Z https://docs.axolotl.ai/docs/api/core.builders.causal.html - 2026-03-06T14:34:37.660Z + 2026-03-06T17:45:10.668Z https://docs.axolotl.ai/docs/api/core.builders.rl.html - 2026-03-06T14:34:37.665Z + 2026-03-06T17:45:10.674Z https://docs.axolotl.ai/docs/api/utils.collators.core.html - 2026-03-06T14:34:39.090Z + 2026-03-06T17:45:12.326Z https://docs.axolotl.ai/docs/api/utils.schemas.model.html - 2026-03-06T14:34:38.799Z + 2026-03-06T17:45:12.008Z https://docs.axolotl.ai/docs/api/kernels.quantize.html - 2026-03-06T14:34:38.490Z + 2026-03-06T17:45:11.671Z https://docs.axolotl.ai/docs/api/utils.schemas.enums.html - 2026-03-06T14:34:38.877Z + 2026-03-06T17:45:12.093Z https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html - 2026-03-06T14:34:38.257Z + 2026-03-06T17:45:11.416Z https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html - 2026-03-06T14:34:39.179Z + 2026-03-06T17:45:12.425Z https://docs.axolotl.ai/docs/api/cli.preprocess.html - 2026-03-06T14:34:37.891Z + 2026-03-06T17:45:10.953Z https://docs.axolotl.ai/docs/api/loaders.model.html - 2026-03-06T14:34:38.050Z + 2026-03-06T17:45:11.189Z https://docs.axolotl.ai/docs/api/cli.merge_lora.html - 2026-03-06T14:34:37.869Z + 2026-03-06T17:45:10.927Z https://docs.axolotl.ai/docs/api/cli.utils.sweeps.html - 2026-03-06T14:34:37.950Z + 2026-03-06T17:45:11.029Z https://docs.axolotl.ai/docs/api/utils.bench.html - 2026-03-06T14:34:38.645Z + 2026-03-06T17:45:11.841Z https://docs.axolotl.ai/docs/api/core.trainers.mamba.html - 2026-03-06T14:34:38.003Z + 2026-03-06T17:45:11.118Z https://docs.axolotl.ai/docs/api/cli.vllm_serve.html - 2026-03-06T14:34:37.905Z + 2026-03-06T17:45:10.972Z https://docs.axolotl.ai/docs/api/kernels.utils.html - 2026-03-06T14:34:38.491Z + 2026-03-06T17:45:11.673Z https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html - 2026-03-06T14:34:38.175Z + 2026-03-06T17:45:11.326Z https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html - 2026-03-06T14:34:39.173Z + 2026-03-06T17:45:12.418Z https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html - 2026-03-06T14:34:39.120Z + 2026-03-06T17:45:12.359Z https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html - 2026-03-06T14:34:38.867Z + 2026-03-06T17:45:12.082Z https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html - 2026-03-06T14:34:38.355Z + 2026-03-06T17:45:11.524Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html - 2026-03-06T14:34:38.206Z + 2026-03-06T17:45:11.360Z https://docs.axolotl.ai/docs/api/cli.evaluate.html - 2026-03-06T14:34:37.783Z + 2026-03-06T17:45:10.814Z https://docs.axolotl.ai/docs/api/core.datasets.chat.html - 2026-03-06T14:34:37.717Z + 2026-03-06T17:45:10.734Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html - 2026-03-06T14:34:38.191Z + 2026-03-06T17:45:11.343Z https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html - 2026-03-06T14:34:38.261Z + 2026-03-06T17:45:11.421Z https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html - 2026-03-06T14:34:38.572Z + 2026-03-06T17:45:11.760Z https://docs.axolotl.ai/docs/api/kernels.lora.html - 2026-03-06T14:34:38.457Z + 2026-03-06T17:45:11.636Z https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html - 2026-03-06T14:34:39.177Z + 2026-03-06T17:45:12.423Z https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html - 2026-03-06T14:34:39.183Z + 2026-03-06T17:45:12.429Z https://docs.axolotl.ai/docs/api/utils.freeze.html - 2026-03-06T14:34:38.655Z + 2026-03-06T17:45:11.851Z https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html - 2026-03-06T14:34:39.055Z + 2026-03-06T17:45:12.288Z https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html - 2026-03-06T14:34:38.620Z + 2026-03-06T17:45:11.813Z https://docs.axolotl.ai/docs/api/utils.data.streaming.html - 2026-03-06T14:34:38.746Z + 2026-03-06T17:45:11.951Z https://docs.axolotl.ai/docs/api/prompt_tokenizers.html - 2026-03-06T14:34:37.636Z + 2026-03-06T17:45:10.641Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html - 2026-03-06T14:34:38.101Z + 2026-03-06T17:45:11.244Z https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html - 2026-03-06T14:34:37.916Z + 2026-03-06T17:45:10.990Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html - 2026-03-06T14:34:38.108Z + 2026-03-06T17:45:11.253Z https://docs.axolotl.ai/docs/api/convert.html - 2026-03-06T14:34:37.587Z + 2026-03-06T17:45:10.582Z https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html - 2026-03-06T14:34:39.088Z + 2026-03-06T17:45:12.324Z https://docs.axolotl.ai/docs/api/cli.args.html - 2026-03-06T14:34:37.806Z + 2026-03-06T17:45:10.846Z https://docs.axolotl.ai/docs/api/core.chat.format.shared.html - 2026-03-06T14:34:37.712Z + 2026-03-06T17:45:10.727Z https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html - 2026-03-06T14:34:38.360Z + 2026-03-06T17:45:11.529Z https://docs.axolotl.ai/docs/api/index.html - 2026-03-06T14:34:37.482Z + 2026-03-06T17:45:10.463Z https://docs.axolotl.ai/docs/fsdp_qlora.html - 2026-03-06T14:31:29.653Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset-formats/template_free.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset-formats/index.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/telemetry.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.497Z https://docs.axolotl.ai/docs/config-reference.html - 2026-03-06T14:34:58.509Z + 2026-03-06T17:45:35.104Z https://docs.axolotl.ai/docs/ray-integration.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/streaming.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.497Z https://docs.axolotl.ai/docs/sequence_parallelism.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.497Z https://docs.axolotl.ai/docs/unsloth.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.497Z https://docs.axolotl.ai/docs/mixed_precision.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/amd_hpc.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/lr_groups.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/optimizations.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/mac.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/index.html - 2026-03-06T14:31:29.670Z + 2026-03-06T17:41:58.517Z https://docs.axolotl.ai/docs/optimizers.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/getting-started.html - 2026-03-06T14:31:29.653Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/multi-node.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/input_output.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/nd_parallelism.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/dataset_loading.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/quantize.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/rlhf.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.496Z https://docs.axolotl.ai/docs/custom_integrations.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/qat.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/checkpoint_saving.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset-formats/conversation.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset-formats/tokenized.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/dataset-formats/pretraining.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/api/cli.main.html - 2026-03-06T14:34:37.764Z + 2026-03-06T17:45:10.793Z https://docs.axolotl.ai/docs/api/utils.schemas.trl.html - 2026-03-06T14:34:38.842Z + 2026-03-06T17:45:12.055Z https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html - 2026-03-06T14:34:37.726Z + 2026-03-06T17:45:10.746Z https://docs.axolotl.ai/docs/api/common.const.html - 2026-03-06T14:34:39.070Z + 2026-03-06T17:45:12.304Z https://docs.axolotl.ai/docs/api/cli.utils.load.html - 2026-03-06T14:34:37.943Z + 2026-03-06T17:45:11.020Z https://docs.axolotl.ai/docs/api/loaders.patch_manager.html - 2026-03-06T14:34:38.089Z + 2026-03-06T17:45:11.231Z https://docs.axolotl.ai/docs/api/utils.quantization.html - 2026-03-06T14:34:38.775Z + 2026-03-06T17:45:11.983Z https://docs.axolotl.ai/docs/api/monkeypatch.utils.html - 2026-03-06T14:34:38.550Z + 2026-03-06T17:45:11.737Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html - 2026-03-06T14:34:38.309Z + 2026-03-06T17:45:11.473Z https://docs.axolotl.ai/docs/api/cli.quantize.html - 2026-03-06T14:34:37.897Z + 2026-03-06T17:45:10.959Z https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html - 2026-03-06T14:34:38.216Z + 2026-03-06T17:45:11.370Z https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html - 2026-03-06T14:34:39.063Z + 2026-03-06T17:45:12.296Z https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html - 2026-03-06T14:34:38.589Z + 2026-03-06T17:45:11.780Z https://docs.axolotl.ai/docs/api/utils.schedulers.html - 2026-03-06T14:34:38.705Z + 2026-03-06T17:45:11.907Z https://docs.axolotl.ai/docs/api/kernels.geglu.html - 2026-03-06T14:34:38.470Z + 2026-03-06T17:45:11.649Z https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html - 2026-03-06T14:34:38.564Z + 2026-03-06T17:45:11.752Z https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html - 2026-03-06T14:34:38.269Z + 2026-03-06T17:45:11.429Z https://docs.axolotl.ai/docs/api/common.architectures.html - 2026-03-06T14:34:39.068Z + 2026-03-06T17:45:12.302Z https://docs.axolotl.ai/docs/api/cli.utils.html - 2026-03-06T14:34:37.918Z + 2026-03-06T17:45:10.991Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html - 2026-03-06T14:34:38.509Z + 2026-03-06T17:45:11.692Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html - 2026-03-06T14:34:38.498Z + 2026-03-06T17:45:11.680Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html - 2026-03-06T14:34:38.332Z + 2026-03-06T17:45:11.498Z https://docs.axolotl.ai/docs/api/cli.checks.html - 2026-03-06T14:34:37.817Z + 2026-03-06T17:45:10.859Z https://docs.axolotl.ai/docs/api/core.trainers.trl.html - 2026-03-06T14:34:37.997Z + 2026-03-06T17:45:11.106Z https://docs.axolotl.ai/docs/api/utils.tokenization.html - 2026-03-06T14:34:38.627Z + 2026-03-06T17:45:11.822Z https://docs.axolotl.ai/docs/api/cli.utils.fetch.html - 2026-03-06T14:34:37.937Z + 2026-03-06T17:45:11.013Z https://docs.axolotl.ai/docs/api/core.builders.base.html - 2026-03-06T14:34:37.654Z + 2026-03-06T17:45:10.661Z https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html - 2026-03-06T14:34:38.501Z + 2026-03-06T17:45:11.683Z https://docs.axolotl.ai/docs/api/utils.trainer.html - 2026-03-06T14:34:38.674Z + 2026-03-06T17:45:11.873Z https://docs.axolotl.ai/docs/api/cli.train.html - 2026-03-06T14:34:37.773Z + 2026-03-06T17:45:10.804Z https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html - 2026-03-06T14:34:37.710Z + 2026-03-06T17:45:10.725Z https://docs.axolotl.ai/docs/api/utils.lora.html - 2026-03-06T14:34:38.635Z + 2026-03-06T17:45:11.830Z https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html - 2026-03-06T14:34:38.848Z + 2026-03-06T17:45:12.061Z https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html - 2026-03-06T14:34:38.586Z + 2026-03-06T17:45:11.776Z https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html - 2026-03-06T14:34:38.011Z + 2026-03-06T17:45:11.132Z https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html - 2026-03-06T14:34:39.166Z + 2026-03-06T17:45:12.410Z https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html - 2026-03-06T14:34:38.024Z + 2026-03-06T17:45:11.156Z https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html - 2026-03-06T14:34:38.135Z + 2026-03-06T17:45:11.283Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html - 2026-03-06T14:34:38.330Z + 2026-03-06T17:45:11.496Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html - 2026-03-06T14:34:38.320Z + 2026-03-06T17:45:11.485Z https://docs.axolotl.ai/docs/api/datasets.html - 2026-03-06T14:34:37.571Z + 2026-03-06T17:45:10.564Z https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html - 2026-03-06T14:34:39.047Z + 2026-03-06T17:45:12.278Z https://docs.axolotl.ai/docs/api/cli.art.html - 2026-03-06T14:34:37.810Z + 2026-03-06T17:45:10.851Z https://docs.axolotl.ai/docs/api/utils.callbacks.qat.html - 2026-03-06T14:34:39.195Z + 2026-03-06T17:45:12.443Z https://docs.axolotl.ai/docs/api/monkeypatch.relora.html - 2026-03-06T14:34:38.507Z + 2026-03-06T17:45:11.690Z https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html - 2026-03-06T14:34:38.274Z + 2026-03-06T17:45:11.434Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html - 2026-03-06T14:34:38.311Z + 2026-03-06T17:45:11.475Z https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html - 2026-03-06T14:34:37.708Z + 2026-03-06T17:45:10.723Z https://docs.axolotl.ai/docs/api/cli.utils.args.html - 2026-03-06T14:34:37.931Z + 2026-03-06T17:45:11.006Z https://docs.axolotl.ai/docs/api/core.trainers.base.html - 2026-03-06T14:34:37.980Z + 2026-03-06T17:45:11.074Z https://docs.axolotl.ai/docs/api/utils.schemas.training.html - 2026-03-06T14:34:38.808Z + 2026-03-06T17:45:12.017Z https://docs.axolotl.ai/docs/api/evaluate.html - 2026-03-06T14:34:37.564Z + 2026-03-06T17:45:10.556Z https://docs.axolotl.ai/docs/api/cli.config.html - 2026-03-06T14:34:37.837Z + 2026-03-06T17:45:10.887Z https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html - 2026-03-06T14:34:39.067Z + 2026-03-06T17:45:12.300Z https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html - 2026-03-06T14:34:38.249Z + 2026-03-06T17:45:11.407Z https://docs.axolotl.ai/docs/api/utils.collators.batching.html - 2026-03-06T14:34:39.111Z + 2026-03-06T17:45:12.349Z https://docs.axolotl.ai/docs/api/cli.cloud.base.html - 2026-03-06T14:34:37.909Z + 2026-03-06T17:45:10.979Z https://docs.axolotl.ai/docs/api/utils.schemas.config.html - 2026-03-06T14:34:38.792Z + 2026-03-06T17:45:12.000Z https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html - 2026-03-06T14:34:38.503Z + 2026-03-06T17:45:11.685Z https://docs.axolotl.ai/docs/api/utils.dict.html - 2026-03-06T14:34:38.735Z + 2026-03-06T17:45:11.939Z https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html - 2026-03-06T14:34:39.046Z + 2026-03-06T17:45:12.277Z https://docs.axolotl.ai/docs/api/cli.delinearize_llama4.html - 2026-03-06T14:34:37.843Z + 2026-03-06T17:45:10.893Z https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html - 2026-03-06T14:34:37.882Z + 2026-03-06T17:45:10.943Z https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html - 2026-03-06T14:34:38.641Z + 2026-03-06T17:45:11.837Z https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html - 2026-03-06T14:34:38.584Z + 2026-03-06T17:45:11.774Z https://docs.axolotl.ai/docs/api/utils.schemas.utils.html - 2026-03-06T14:34:38.883Z + 2026-03-06T17:45:12.100Z https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html - 2026-03-06T14:34:39.187Z + 2026-03-06T17:45:12.434Z https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html - 2026-03-06T14:34:38.744Z + 2026-03-06T17:45:11.949Z https://docs.axolotl.ai/docs/api/kernels.swiglu.html - 2026-03-06T14:34:38.481Z + 2026-03-06T17:45:11.661Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html - 2026-03-06T14:34:38.097Z + 2026-03-06T17:45:11.240Z https://docs.axolotl.ai/docs/api/cli.inference.html - 2026-03-06T14:34:37.859Z + 2026-03-06T17:45:10.911Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html - 2026-03-06T14:34:38.306Z + 2026-03-06T17:45:11.469Z https://docs.axolotl.ai/docs/api/utils.chat_templates.html - 2026-03-06T14:34:38.629Z + 2026-03-06T17:45:11.823Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html - 2026-03-06T14:34:38.193Z + 2026-03-06T17:45:11.345Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html - 2026-03-06T14:34:38.307Z + 2026-03-06T17:45:11.471Z https://docs.axolotl.ai/docs/multipack.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/torchao.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.497Z https://docs.axolotl.ai/docs/reward_modelling.html - 2026-03-06T14:31:29.656Z + 2026-03-06T17:41:58.496Z https://docs.axolotl.ai/docs/nccl.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/multi-gpu.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/batch_vs_grad.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/multimodal.html - 2026-03-06T14:31:29.655Z + 2026-03-06T17:41:58.495Z https://docs.axolotl.ai/docs/models/LiquidAI.html - 2026-03-06T14:34:59.473Z + 2026-03-06T17:45:35.990Z https://docs.axolotl.ai/docs/models/mistral.html - 2026-03-06T14:34:59.469Z + 2026-03-06T17:45:35.985Z https://docs.axolotl.ai/docs/models/trinity.html - 2026-03-06T14:34:59.465Z + 2026-03-06T17:45:35.980Z https://docs.axolotl.ai/docs/models/hunyuan.html - 2026-03-06T14:34:59.473Z + 2026-03-06T17:45:35.991Z https://docs.axolotl.ai/docs/models/phi.html - 2026-03-06T14:34:59.472Z + 2026-03-06T17:45:35.989Z https://docs.axolotl.ai/docs/models/apertus.html - 2026-03-06T14:34:59.471Z + 2026-03-06T17:45:35.988Z https://docs.axolotl.ai/docs/models/plano.html - 2026-03-06T14:34:59.464Z + 2026-03-06T17:45:35.979Z https://docs.axolotl.ai/docs/models/gemma3n.html - 2026-03-06T14:34:59.471Z + 2026-03-06T17:45:35.987Z https://docs.axolotl.ai/docs/models/arcee.html - 2026-03-06T14:34:59.465Z + 2026-03-06T17:45:35.980Z https://docs.axolotl.ai/docs/models/ministral3.html - 2026-03-06T14:34:59.466Z + 2026-03-06T17:45:35.982Z https://docs.axolotl.ai/docs/models/magistral/think.html - 2026-03-06T14:34:59.467Z + 2026-03-06T17:45:35.983Z https://docs.axolotl.ai/docs/models/llama-4.html - 2026-03-06T14:34:59.470Z + 2026-03-06T17:45:35.986Z https://docs.axolotl.ai/docs/models/voxtral.html - 2026-03-06T14:34:59.469Z + 2026-03-06T17:45:35.985Z https://docs.axolotl.ai/docs/models/magistral.html - 2026-03-06T14:34:59.467Z + 2026-03-06T17:45:35.983Z https://docs.axolotl.ai/docs/models/qwen3.html - 2026-03-06T14:34:59.470Z + 2026-03-06T17:45:35.987Z https://docs.axolotl.ai/docs/models/ministral.html - 2026-03-06T14:34:59.468Z + 2026-03-06T17:45:35.984Z https://docs.axolotl.ai/docs/models/ministral3/vision.html - 2026-03-06T14:34:59.467Z + 2026-03-06T17:45:35.982Z https://docs.axolotl.ai/docs/debugging.html - 2026-03-06T14:31:29.652Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/docs/faq.html - 2026-03-06T14:31:29.653Z + 2026-03-06T17:41:58.492Z https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html - 2026-03-06T14:31:29.673Z + 2026-03-06T17:41:58.522Z https://docs.axolotl.ai/FAQS.html - 2026-03-06T14:31:29.651Z + 2026-03-06T17:41:58.490Z