diff --git a/.nojekyll b/.nojekyll
index 38a0e9abb..4d66c1372 100644
--- a/.nojekyll
+++ b/.nojekyll
@@ -1 +1 @@
-6339b6ce
\ No newline at end of file
+848a9a1a
\ No newline at end of file
diff --git a/docs/custom_integrations.html b/docs/custom_integrations.html
index 2cad39191..e86ba3b06 100644
--- a/docs/custom_integrations.html
+++ b/docs/custom_integrations.html
@@ -954,7 +954,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
If you are installing from pip
-pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@0d4ce4b"
+pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@58d6572"
Usage
@@ -964,6 +964,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
Supported Models
+afmoe
apertus
arcee
cohere
@@ -984,6 +985,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
glm4v
glm4v_moe
glm_image
+glm_moe_dsa
gpt_oss
granite
granitemoe
@@ -1009,14 +1011,19 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
olmo
olmo2
olmo3
+olmoe
phi
phi3
phi4_multimodal
qwen2
+qwen2_5_vl
qwen2_moe
qwen2_vl
-qwen2_5_vl
qwen3
+qwen3_5
+qwen3_5_moe
+qwen3_5_moe_vl
+qwen3_5_vl
qwen3_moe
qwen3_next
qwen3_vl
diff --git a/examples/colab-notebooks/colab-axolotl-example.html b/examples/colab-notebooks/colab-axolotl-example.html
index 1322307e5..2c4383136 100644
--- a/examples/colab-notebooks/colab-axolotl-example.html
+++ b/examples/colab-notebooks/colab-axolotl-example.html
@@ -804,7 +804,7 @@ 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@0d4ce4b"
+! pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@58d6572"
Demo: Talk Like a Pirate
diff --git a/search.json b/search.json
index 22737d9d3..80cfde27a 100644
--- a/search.json
+++ b/search.json
@@ -3192,7 +3192,7 @@
"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@0d4ce4b\"\n\n\nUsage\nplugins:\n - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin\n\n\nSupported Models\n\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\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\nphi\nphi3\nphi4_multimodal\nqwen2\nqwen2_moe\nqwen2_vl\nqwen2_5_vl\nqwen3\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@58d6572\"\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_moe\nqwen3_5_moe_vl\nqwen3_5_vl\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 5f09a59e8..7088686f7 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -2,946 +2,946 @@
https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html
- 2026-02-19T23:33:26.136Z
+ 2026-02-20T19:25:56.553Z
https://docs.axolotl.ai/docs/mac.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/cli.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/mixed_precision.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/installation.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/dataset_loading.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/sequence_parallelism.html
- 2026-02-19T23:33:26.110Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/optimizations.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/gradient_checkpointing.html
- 2026-02-19T23:33:26.106Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/streaming.html
- 2026-02-19T23:33:26.110Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/lora_optims.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/amd_hpc.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.524Z
https://docs.axolotl.ai/docs/debugging.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/dataset-formats/conversation.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/dataset-formats/index.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/config-reference.html
- 2026-02-19T23:37:23.227Z
+ 2026-02-20T19:29:56.897Z
https://docs.axolotl.ai/docs/multimodal.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/ray-integration.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/faq.html
- 2026-02-19T23:33:26.106Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/dataset_preprocessing.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/fsdp_qlora.html
- 2026-02-19T23:33:26.106Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/quantize.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/reward_modelling.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/models/plano.html
- 2026-02-19T23:37:24.200Z
+ 2026-02-20T19:29:57.743Z
https://docs.axolotl.ai/docs/models/ministral3/vision.html
- 2026-02-19T23:37:24.205Z
+ 2026-02-20T19:29:57.746Z
https://docs.axolotl.ai/docs/models/ministral3.html
- 2026-02-19T23:37:24.205Z
+ 2026-02-20T19:29:57.746Z
https://docs.axolotl.ai/docs/models/devstral.html
- 2026-02-19T23:37:24.209Z
+ 2026-02-20T19:29:57.749Z
https://docs.axolotl.ai/docs/models/llama-4.html
- 2026-02-19T23:37:24.210Z
+ 2026-02-20T19:29:57.749Z
https://docs.axolotl.ai/docs/models/ministral.html
- 2026-02-19T23:37:24.207Z
+ 2026-02-20T19:29:57.748Z
https://docs.axolotl.ai/docs/models/trinity.html
- 2026-02-19T23:37:24.203Z
+ 2026-02-20T19:29:57.744Z
https://docs.axolotl.ai/docs/models/voxtral.html
- 2026-02-19T23:37:24.208Z
+ 2026-02-20T19:29:57.748Z
https://docs.axolotl.ai/docs/models/magistral.html
- 2026-02-19T23:37:24.206Z
+ 2026-02-20T19:29:57.747Z
https://docs.axolotl.ai/docs/models/LiquidAI.html
- 2026-02-19T23:37:24.214Z
+ 2026-02-20T19:29:57.753Z
https://docs.axolotl.ai/docs/models/arcee.html
- 2026-02-19T23:37:24.203Z
+ 2026-02-20T19:29:57.745Z
https://docs.axolotl.ai/docs/models/internvl3_5.html
- 2026-02-19T23:37:24.201Z
+ 2026-02-20T19:29:57.744Z
https://docs.axolotl.ai/docs/models/kimi-linear.html
- 2026-02-19T23:37:24.200Z
+ 2026-02-20T19:29:57.743Z
https://docs.axolotl.ai/docs/models/magistral/think.html
- 2026-02-19T23:37:24.206Z
+ 2026-02-20T19:29:57.747Z
https://docs.axolotl.ai/docs/models/index.html
- 2026-02-19T23:37:24.216Z
+ 2026-02-20T19:29:57.754Z
https://docs.axolotl.ai/docs/models/qwen3-next.html
- 2026-02-19T23:37:24.210Z
+ 2026-02-20T19:29:57.750Z
https://docs.axolotl.ai/docs/models/gemma3n.html
- 2026-02-19T23:37:24.211Z
+ 2026-02-20T19:29:57.751Z
https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html
- 2026-02-19T23:36:59.231Z
+ 2026-02-20T19:29:35.320Z
https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html
- 2026-02-19T23:37:00.167Z
+ 2026-02-20T19:29:36.269Z
https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html
- 2026-02-19T23:37:00.688Z
+ 2026-02-20T19:29:36.796Z
https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html
- 2026-02-19T23:37:00.679Z
+ 2026-02-20T19:29:36.786Z
https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html
- 2026-02-19T23:36:59.229Z
+ 2026-02-20T19:29:35.318Z
https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html
- 2026-02-19T23:37:00.817Z
+ 2026-02-20T19:29:36.926Z
https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html
- 2026-02-19T23:37:00.822Z
+ 2026-02-20T19:29:36.930Z
https://docs.axolotl.ai/docs/api/cli.preprocess.html
- 2026-02-19T23:36:59.426Z
+ 2026-02-20T19:29:35.518Z
https://docs.axolotl.ai/docs/api/cli.utils.load.html
- 2026-02-19T23:36:59.483Z
+ 2026-02-20T19:29:35.576Z
https://docs.axolotl.ai/docs/api/cli.inference.html
- 2026-02-19T23:36:59.392Z
+ 2026-02-20T19:29:35.484Z
https://docs.axolotl.ai/docs/api/cli.args.html
- 2026-02-19T23:36:59.335Z
+ 2026-02-20T19:29:35.425Z
https://docs.axolotl.ai/docs/api/prompt_tokenizers.html
- 2026-02-19T23:36:59.151Z
+ 2026-02-20T19:29:35.241Z
https://docs.axolotl.ai/docs/api/cli.vllm_serve.html
- 2026-02-19T23:36:59.441Z
+ 2026-02-20T19:29:35.532Z
https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html
- 2026-02-19T23:37:00.179Z
+ 2026-02-20T19:29:36.281Z
https://docs.axolotl.ai/docs/api/loaders.constants.html
- 2026-02-19T23:36:59.638Z
+ 2026-02-20T19:29:35.733Z
https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html
- 2026-02-19T23:36:59.808Z
+ 2026-02-20T19:29:35.903Z
https://docs.axolotl.ai/docs/api/core.trainers.trl.html
- 2026-02-19T23:36:59.541Z
+ 2026-02-20T19:29:35.634Z
https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html
- 2026-02-19T23:37:00.724Z
+ 2026-02-20T19:29:36.831Z
https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html
- 2026-02-19T23:37:00.154Z
+ 2026-02-20T19:29:36.256Z
https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html
- 2026-02-19T23:36:59.749Z
+ 2026-02-20T19:29:35.845Z
https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html
- 2026-02-19T23:36:59.822Z
+ 2026-02-20T19:29:35.917Z
https://docs.axolotl.ai/docs/api/utils.freeze.html
- 2026-02-19T23:37:00.256Z
+ 2026-02-20T19:29:36.359Z
https://docs.axolotl.ai/docs/api/logging_config.html
- 2026-02-19T23:36:59.163Z
+ 2026-02-20T19:29:35.253Z
https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html
- 2026-02-19T23:37:00.158Z
+ 2026-02-20T19:29:36.260Z
https://docs.axolotl.ai/docs/api/cli.art.html
- 2026-02-19T23:36:59.339Z
+ 2026-02-20T19:29:35.429Z
https://docs.axolotl.ai/docs/api/utils.collators.mamba.html
- 2026-02-19T23:37:00.753Z
+ 2026-02-20T19:29:36.862Z
https://docs.axolotl.ai/docs/api/cli.utils.train.html
- 2026-02-19T23:36:59.505Z
+ 2026-02-20T19:29:35.598Z
https://docs.axolotl.ai/docs/api/integrations.base.html
- 2026-02-19T23:37:00.673Z
+ 2026-02-20T19:29:36.781Z
https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html
- 2026-02-19T23:36:59.556Z
+ 2026-02-20T19:29:35.652Z
https://docs.axolotl.ai/docs/api/cli.checks.html
- 2026-02-19T23:36:59.347Z
+ 2026-02-20T19:29:35.439Z
https://docs.axolotl.ai/docs/api/common.architectures.html
- 2026-02-19T23:37:00.702Z
+ 2026-02-20T19:29:36.810Z
https://docs.axolotl.ai/docs/api/utils.bench.html
- 2026-02-19T23:37:00.246Z
+ 2026-02-20T19:29:36.350Z
https://docs.axolotl.ai/docs/api/utils.data.streaming.html
- 2026-02-19T23:37:00.355Z
+ 2026-02-20T19:29:36.460Z
https://docs.axolotl.ai/docs/api/utils.chat_templates.html
- 2026-02-19T23:37:00.228Z
+ 2026-02-20T19:29:36.330Z
https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html
- 2026-02-19T23:36:59.765Z
+ 2026-02-20T19:29:35.861Z
https://docs.axolotl.ai/docs/api/core.trainers.utils.html
- 2026-02-19T23:36:59.586Z
+ 2026-02-20T19:29:35.681Z
https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html
- 2026-02-19T23:36:59.878Z
+ 2026-02-20T19:29:35.975Z
https://docs.axolotl.ai/docs/api/cli.evaluate.html
- 2026-02-19T23:36:59.310Z
+ 2026-02-20T19:29:35.401Z
https://docs.axolotl.ai/docs/api/monkeypatch.relora.html
- 2026-02-19T23:37:00.095Z
+ 2026-02-20T19:29:36.195Z
https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html
- 2026-02-19T23:36:59.876Z
+ 2026-02-20T19:29:35.973Z
https://docs.axolotl.ai/docs/api/cli.utils.fetch.html
- 2026-02-19T23:36:59.476Z
+ 2026-02-20T19:29:35.569Z
https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html
- 2026-02-19T23:37:00.443Z
+ 2026-02-20T19:29:36.550Z
https://docs.axolotl.ai/docs/api/common.datasets.html
- 2026-02-19T23:37:00.723Z
+ 2026-02-20T19:29:36.830Z
https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html
- 2026-02-19T23:37:00.828Z
+ 2026-02-20T19:29:36.939Z
https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html
- 2026-02-19T23:36:59.902Z
+ 2026-02-20T19:29:35.999Z
https://docs.axolotl.ai/docs/api/utils.schemas.model.html
- 2026-02-19T23:37:00.412Z
+ 2026-02-20T19:29:36.517Z
https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html
- 2026-02-19T23:37:00.087Z
+ 2026-02-20T19:29:36.187Z
https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html
- 2026-02-19T23:37:00.146Z
+ 2026-02-20T19:29:36.248Z
https://docs.axolotl.ai/docs/api/core.trainers.base.html
- 2026-02-19T23:36:59.522Z
+ 2026-02-20T19:29:35.615Z
https://docs.axolotl.ai/docs/api/cli.utils.args.html
- 2026-02-19T23:36:59.469Z
+ 2026-02-20T19:29:35.563Z
https://docs.axolotl.ai/docs/api/utils.schemas.trl.html
- 2026-02-19T23:37:00.459Z
+ 2026-02-20T19:29:36.566Z
https://docs.axolotl.ai/docs/api/core.builders.base.html
- 2026-02-19T23:36:59.171Z
+ 2026-02-20T19:29:35.261Z
https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html
- 2026-02-19T23:37:00.085Z
+ 2026-02-20T19:29:36.185Z
https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html
- 2026-02-19T23:36:59.453Z
+ 2026-02-20T19:29:35.547Z
https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html
- 2026-02-19T23:37:00.353Z
+ 2026-02-20T19:29:36.459Z
https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html
- 2026-02-19T23:37:00.701Z
+ 2026-02-20T19:29:36.808Z
https://docs.axolotl.ai/docs/api/cli.main.html
- 2026-02-19T23:36:59.290Z
+ 2026-02-20T19:29:35.380Z
https://docs.axolotl.ai/docs/api/kernels.lora.html
- 2026-02-19T23:37:00.041Z
+ 2026-02-20T19:29:36.142Z
https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html
- 2026-02-19T23:37:00.241Z
+ 2026-02-20T19:29:36.345Z
https://docs.axolotl.ai/docs/api/utils.distributed.html
- 2026-02-19T23:37:00.337Z
+ 2026-02-20T19:29:36.442Z
https://docs.axolotl.ai/docs/api/loaders.model.html
- 2026-02-19T23:36:59.598Z
+ 2026-02-20T19:29:35.693Z
https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html
- 2026-02-19T23:37:00.089Z
+ 2026-02-20T19:29:36.189Z
https://docs.axolotl.ai/docs/api/evaluate.html
- 2026-02-19T23:36:59.074Z
+ 2026-02-20T19:29:35.162Z
https://docs.axolotl.ai/docs/api/cli.delinearize_llama4.html
- 2026-02-19T23:36:59.374Z
+ 2026-02-20T19:29:35.467Z
https://docs.axolotl.ai/docs/api/utils.trainer.html
- 2026-02-19T23:37:00.277Z
+ 2026-02-20T19:29:36.381Z
https://docs.axolotl.ai/docs/api/cli.quantize.html
- 2026-02-19T23:36:59.432Z
+ 2026-02-20T19:29:35.524Z
https://docs.axolotl.ai/docs/api/common.const.html
- 2026-02-19T23:37:00.704Z
+ 2026-02-20T19:29:36.812Z
https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html
- 2026-02-19T23:36:59.793Z
+ 2026-02-20T19:29:35.888Z
https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html
- 2026-02-19T23:37:00.759Z
+ 2026-02-20T19:29:36.868Z
https://docs.axolotl.ai/docs/api/core.datasets.chat.html
- 2026-02-19T23:36:59.240Z
+ 2026-02-20T19:29:35.328Z
https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html
- 2026-02-19T23:36:59.935Z
+ 2026-02-20T19:29:36.032Z
https://docs.axolotl.ai/docs/api/core.trainers.mamba.html
- 2026-02-19T23:36:59.548Z
+ 2026-02-20T19:29:35.643Z
https://docs.axolotl.ai/docs/api/core.builders.causal.html
- 2026-02-19T23:36:59.177Z
+ 2026-02-20T19:29:35.266Z
https://docs.axolotl.ai/docs/api/kernels.geglu.html
- 2026-02-19T23:37:00.055Z
+ 2026-02-20T19:29:36.155Z
https://docs.axolotl.ai/docs/api/utils.schemas.utils.html
- 2026-02-19T23:37:00.503Z
+ 2026-02-20T19:29:36.610Z
https://docs.axolotl.ai/docs/custom_integrations.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/index.html
- 2026-02-19T23:33:26.131Z
+ 2026-02-20T19:25:56.549Z
https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html
- 2026-02-19T23:33:26.115Z
+ 2026-02-20T19:25:56.534Z
https://docs.axolotl.ai/FAQS.html
- 2026-02-19T23:33:26.103Z
+ 2026-02-20T19:25:56.523Z
https://docs.axolotl.ai/docs/inference.html
- 2026-02-19T23:33:26.108Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html
- 2026-02-19T23:36:59.249Z
+ 2026-02-20T19:29:35.340Z
https://docs.axolotl.ai/docs/api/train.html
- 2026-02-19T23:36:59.061Z
+ 2026-02-20T19:29:35.149Z
https://docs.axolotl.ai/docs/api/utils.schemas.training.html
- 2026-02-19T23:37:00.420Z
+ 2026-02-20T19:29:36.525Z
https://docs.axolotl.ai/docs/api/kernels.quantize.html
- 2026-02-19T23:37:00.076Z
+ 2026-02-20T19:29:36.176Z
https://docs.axolotl.ai/docs/api/utils.dict.html
- 2026-02-19T23:37:00.343Z
+ 2026-02-20T19:29:36.449Z
https://docs.axolotl.ai/docs/api/utils.quantization.html
- 2026-02-19T23:37:00.387Z
+ 2026-02-20T19:29:36.492Z
https://docs.axolotl.ai/docs/api/utils.collators.batching.html
- 2026-02-19T23:37:00.749Z
+ 2026-02-20T19:29:36.858Z
https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html
- 2026-02-19T23:37:00.090Z
+ 2026-02-20T19:29:36.190Z
https://docs.axolotl.ai/docs/api/cli.config.html
- 2026-02-19T23:36:59.368Z
+ 2026-02-20T19:29:35.461Z
https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html
- 2026-02-19T23:36:59.645Z
+ 2026-02-20T19:29:35.742Z
https://docs.axolotl.ai/docs/api/utils.lora.html
- 2026-02-19T23:37:00.234Z
+ 2026-02-20T19:29:36.338Z
https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html
- 2026-02-19T23:36:59.585Z
+ 2026-02-20T19:29:35.679Z
https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html
- 2026-02-19T23:36:59.827Z
+ 2026-02-20T19:29:35.922Z
https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html
- 2026-02-19T23:37:00.181Z
+ 2026-02-20T19:29:36.283Z
https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html
- 2026-02-19T23:36:59.863Z
+ 2026-02-20T19:29:35.960Z
https://docs.axolotl.ai/docs/api/index.html
- 2026-02-19T23:36:58.985Z
+ 2026-02-20T19:29:35.071Z
https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html
- 2026-02-19T23:36:59.688Z
+ 2026-02-20T19:29:35.783Z
https://docs.axolotl.ai/docs/api/cli.utils.html
- 2026-02-19T23:36:59.455Z
+ 2026-02-20T19:29:35.549Z
https://docs.axolotl.ai/docs/api/cli.merge_lora.html
- 2026-02-19T23:36:59.402Z
+ 2026-02-20T19:29:35.494Z
https://docs.axolotl.ai/docs/api/kernels.utils.html
- 2026-02-19T23:37:00.078Z
+ 2026-02-20T19:29:36.178Z
https://docs.axolotl.ai/docs/api/prompt_strategies.base.html
- 2026-02-19T23:36:59.690Z
+ 2026-02-20T19:29:35.785Z
https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html
- 2026-02-19T23:37:00.833Z
+ 2026-02-20T19:29:36.944Z
https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html
- 2026-02-19T23:37:00.465Z
+ 2026-02-20T19:29:36.572Z
https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html
- 2026-02-19T23:36:59.731Z
+ 2026-02-20T19:29:35.826Z
https://docs.axolotl.ai/docs/api/utils.callbacks.qat.html
- 2026-02-19T23:37:00.841Z
+ 2026-02-20T19:29:36.952Z
https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html
- 2026-02-19T23:37:00.809Z
+ 2026-02-20T19:29:36.918Z
https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html
- 2026-02-19T23:36:59.931Z
+ 2026-02-20T19:29:36.027Z
https://docs.axolotl.ai/docs/api/core.chat.format.shared.html
- 2026-02-19T23:36:59.233Z
+ 2026-02-20T19:29:35.322Z
https://docs.axolotl.ai/docs/api/utils.collators.core.html
- 2026-02-19T23:37:00.726Z
+ 2026-02-20T19:29:36.833Z
https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html
- 2026-02-19T23:37:00.696Z
+ 2026-02-20T19:29:36.804Z
https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html
- 2026-02-19T23:36:59.570Z
+ 2026-02-20T19:29:35.665Z
https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html
- 2026-02-19T23:36:59.849Z
+ 2026-02-20T19:29:35.946Z
https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html
- 2026-02-19T23:37:00.144Z
+ 2026-02-20T19:29:36.246Z
https://docs.axolotl.ai/docs/api/utils.schemas.enums.html
- 2026-02-19T23:37:00.496Z
+ 2026-02-20T19:29:36.603Z
https://docs.axolotl.ai/docs/api/utils.schemas.config.html
- 2026-02-19T23:37:00.403Z
+ 2026-02-20T19:29:36.508Z
https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html
- 2026-02-19T23:36:59.882Z
+ 2026-02-20T19:29:35.978Z
https://docs.axolotl.ai/docs/api/convert.html
- 2026-02-19T23:36:59.098Z
+ 2026-02-20T19:29:35.186Z
https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html
- 2026-02-19T23:37:00.485Z
+ 2026-02-20T19:29:36.592Z
https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html
- 2026-02-19T23:36:59.892Z
+ 2026-02-20T19:29:35.989Z
https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html
- 2026-02-19T23:36:59.880Z
+ 2026-02-20T19:29:35.977Z
https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html
- 2026-02-19T23:36:59.659Z
+ 2026-02-20T19:29:35.754Z
https://docs.axolotl.ai/docs/api/core.chat.messages.html
- 2026-02-19T23:36:59.228Z
+ 2026-02-20T19:29:35.317Z
https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html
- 2026-02-19T23:36:59.777Z
+ 2026-02-20T19:29:35.872Z
https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html
- 2026-02-19T23:36:59.841Z
+ 2026-02-20T19:29:35.938Z
https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html
- 2026-02-19T23:37:00.132Z
+ 2026-02-20T19:29:36.231Z
https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html
- 2026-02-19T23:36:59.814Z
+ 2026-02-20T19:29:35.909Z
https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html
- 2026-02-19T23:36:59.801Z
+ 2026-02-20T19:29:35.896Z
https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html
- 2026-02-19T23:36:59.650Z
+ 2026-02-20T19:29:35.746Z
https://docs.axolotl.ai/docs/api/cli.train.html
- 2026-02-19T23:36:59.300Z
+ 2026-02-20T19:29:35.390Z
https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html
- 2026-02-19T23:36:59.416Z
+ 2026-02-20T19:29:35.508Z
https://docs.axolotl.ai/docs/api/loaders.adapter.html
- 2026-02-19T23:36:59.617Z
+ 2026-02-20T19:29:35.712Z
https://docs.axolotl.ai/docs/api/core.training_args.html
- 2026-02-19T23:36:59.199Z
+ 2026-02-20T19:29:35.288Z
https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html
- 2026-02-19T23:37:00.824Z
+ 2026-02-20T19:29:36.932Z
https://docs.axolotl.ai/docs/api/loaders.processor.html
- 2026-02-19T23:36:59.610Z
+ 2026-02-20T19:29:35.705Z
https://docs.axolotl.ai/docs/api/core.builders.rl.html
- 2026-02-19T23:36:59.183Z
+ 2026-02-20T19:29:35.272Z
https://docs.axolotl.ai/docs/api/monkeypatch.utils.html
- 2026-02-19T23:37:00.142Z
+ 2026-02-20T19:29:36.244Z
https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html
- 2026-02-19T23:36:59.904Z
+ 2026-02-20T19:29:36.001Z
https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html
- 2026-02-19T23:37:00.677Z
+ 2026-02-20T19:29:36.785Z
https://docs.axolotl.ai/docs/api/kernels.swiglu.html
- 2026-02-19T23:37:00.067Z
+ 2026-02-20T19:29:36.167Z
https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html
- 2026-02-19T23:37:00.218Z
+ 2026-02-20T19:29:36.319Z
https://docs.axolotl.ai/docs/api/cli.cloud.base.html
- 2026-02-19T23:36:59.445Z
+ 2026-02-20T19:29:35.539Z
https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html
- 2026-02-19T23:36:59.750Z
+ 2026-02-20T19:29:35.847Z
https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html
- 2026-02-19T23:36:59.836Z
+ 2026-02-20T19:29:35.930Z
https://docs.axolotl.ai/docs/api/utils.schemas.peft.html
- 2026-02-19T23:37:00.454Z
+ 2026-02-20T19:29:36.561Z
https://docs.axolotl.ai/docs/api/integrations.liger.args.html
- 2026-02-19T23:37:00.692Z
+ 2026-02-20T19:29:36.800Z
https://docs.axolotl.ai/docs/api/loaders.patch_manager.html
- 2026-02-19T23:36:59.637Z
+ 2026-02-20T19:29:35.731Z
https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html
- 2026-02-19T23:37:00.165Z
+ 2026-02-20T19:29:36.267Z
https://docs.axolotl.ai/docs/api/utils.data.sft.html
- 2026-02-19T23:37:00.363Z
+ 2026-02-20T19:29:36.468Z
https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html
- 2026-02-19T23:37:00.185Z
+ 2026-02-20T19:29:36.287Z
https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html
- 2026-02-19T23:37:00.097Z
+ 2026-02-20T19:29:36.197Z
https://docs.axolotl.ai/docs/api/loaders.tokenizer.html
- 2026-02-19T23:36:59.608Z
+ 2026-02-20T19:29:35.703Z
https://docs.axolotl.ai/docs/api/utils.tokenization.html
- 2026-02-19T23:37:00.226Z
+ 2026-02-20T19:29:36.328Z
https://docs.axolotl.ai/docs/api/datasets.html
- 2026-02-19T23:36:59.081Z
+ 2026-02-20T19:29:35.170Z
https://docs.axolotl.ai/docs/api/cli.utils.sweeps.html
- 2026-02-19T23:36:59.490Z
+ 2026-02-20T19:29:35.583Z
https://docs.axolotl.ai/docs/api/utils.schedulers.html
- 2026-02-19T23:37:00.311Z
+ 2026-02-20T19:29:36.414Z
https://docs.axolotl.ai/docs/models/mimo.html
- 2026-02-19T23:37:24.201Z
+ 2026-02-20T19:29:57.743Z
https://docs.axolotl.ai/docs/models/jamba.html
- 2026-02-19T23:37:24.215Z
+ 2026-02-20T19:29:57.754Z
https://docs.axolotl.ai/docs/models/magistral/vision.html
- 2026-02-19T23:37:24.207Z
+ 2026-02-20T19:29:57.747Z
https://docs.axolotl.ai/docs/models/llama-2.html
- 2026-02-19T23:37:24.210Z
+ 2026-02-20T19:29:57.750Z
https://docs.axolotl.ai/docs/models/smolvlm2.html
- 2026-02-19T23:37:24.213Z
+ 2026-02-20T19:29:57.752Z
https://docs.axolotl.ai/docs/models/mistral-small.html
- 2026-02-19T23:37:24.208Z
+ 2026-02-20T19:29:57.748Z
https://docs.axolotl.ai/docs/models/mistral.html
- 2026-02-19T23:37:24.209Z
+ 2026-02-20T19:29:57.749Z
https://docs.axolotl.ai/docs/models/hunyuan.html
- 2026-02-19T23:37:24.215Z
+ 2026-02-20T19:29:57.753Z
https://docs.axolotl.ai/docs/models/orpheus.html
- 2026-02-19T23:37:24.215Z
+ 2026-02-20T19:29:57.754Z
https://docs.axolotl.ai/docs/models/qwen3.html
- 2026-02-19T23:37:24.211Z
+ 2026-02-20T19:29:57.750Z
https://docs.axolotl.ai/docs/models/seed-oss.html
- 2026-02-19T23:37:24.213Z
+ 2026-02-20T19:29:57.752Z
https://docs.axolotl.ai/docs/models/granite4.html
- 2026-02-19T23:37:24.214Z
+ 2026-02-20T19:29:57.753Z
https://docs.axolotl.ai/docs/models/olmo3.html
- 2026-02-19T23:37:24.202Z
+ 2026-02-20T19:29:57.744Z
https://docs.axolotl.ai/docs/models/phi.html
- 2026-02-19T23:37:24.213Z
+ 2026-02-20T19:29:57.752Z
https://docs.axolotl.ai/docs/models/gpt-oss.html
- 2026-02-19T23:37:24.212Z
+ 2026-02-20T19:29:57.751Z
https://docs.axolotl.ai/docs/models/ministral3/think.html
- 2026-02-19T23:37:24.205Z
+ 2026-02-20T19:29:57.746Z
https://docs.axolotl.ai/docs/models/apertus.html
- 2026-02-19T23:37:24.212Z
+ 2026-02-20T19:29:57.751Z
https://docs.axolotl.ai/docs/optimizers.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/torchao.html
- 2026-02-19T23:33:26.110Z
+ 2026-02-20T19:25:56.530Z
https://docs.axolotl.ai/docs/attention.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.524Z
https://docs.axolotl.ai/docs/nd_parallelism.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/batch_vs_grad.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.524Z
https://docs.axolotl.ai/docs/multi-node.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/rlhf.html
- 2026-02-19T23:33:26.110Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/dataset-formats/pretraining.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/dataset-formats/tokenized.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/dataset-formats/template_free.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/multi-gpu.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/input_output.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/docker.html
- 2026-02-19T23:33:26.106Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/checkpoint_saving.html
- 2026-02-19T23:33:26.105Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/multipack.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/qat.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/lr_groups.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.528Z
https://docs.axolotl.ai/docs/getting-started.html
- 2026-02-19T23:33:26.106Z
+ 2026-02-20T19:25:56.525Z
https://docs.axolotl.ai/docs/nccl.html
- 2026-02-19T23:33:26.109Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/telemetry.html
- 2026-02-19T23:33:26.110Z
+ 2026-02-20T19:25:56.529Z
https://docs.axolotl.ai/docs/unsloth.html
- 2026-02-19T23:33:26.110Z
+ 2026-02-20T19:25:56.530Z
https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html
- 2026-02-19T23:33:26.136Z
+ 2026-02-20T19:25:56.553Z