diff --git a/.nojekyll b/.nojekyll index 7dc9a4cc9..3366cdb39 100644 --- a/.nojekyll +++ b/.nojekyll @@ -1 +1 @@ -51905dfe \ No newline at end of file +e1e28bc6 \ No newline at end of file diff --git a/docs/multimodal.html b/docs/multimodal.html index eda17b8dd..67051594b 100644 --- a/docs/multimodal.html +++ b/docs/multimodal.html @@ -511,6 +511,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
  • Pixtral
  • Llava-1.5
  • Mistral-Small-3.1
    • +
  • Magistral-Small-2509
  • Voxtral
  • Gemma-3
  • Gemma-3n
    • @@ -560,6 +561,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
  • Pixtral
  • Llava-1.5
  • Mistral-Small-3.1
    • +
  • Magistral-Small-2509
  • Voxtral
  • Gemma-3
  • Gemma-3n
    • @@ -637,9 +639,37 @@ Warning

    Mistral-Small-3.1

    -
    base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
-
-chat_template: mistral_v7_tekken
    +
    +
    +
    + +
    +
    +Tip +
    +
    +
    +

    Please make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'

    +
    +
    +
    base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
    +
    +
    +

    Magistral-Small-2509

    +
    +
    +
    + +
    +
    +Tip +
    +
    +
    +

    Please make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'

    +
    +
    +
    base_model: mistralai/Magistral-Small-2509

    Voxtral

    @@ -656,7 +686,7 @@ Tip

    Please make sure to install audio lib via pip3 install librosa==0.11.0 'mistral_common[audio]==1.8.3'

    -
    base_model: mistralai/Voxtral-Mini-3B-2507
    +
    base_model: mistralai/Voxtral-Mini-3B-2507

    Gemma-3

    @@ -674,9 +704,9 @@ Tip

    For multi-modal 4B/12B/27B models, use the following config:

    -
    base_model: google/gemma-3-4b-it
-
-chat_template: gemma3
    +
    base_model: google/gemma-3-4b-it
+
+chat_template: gemma3

    Gemma-3n

    @@ -706,21 +736,21 @@ Tip

    Please make sure to install timm via pip3 install timm==1.0.17

    -
    base_model: google/gemma-3n-E2B-it
-
-chat_template: gemma3n
    +
    base_model: google/gemma-3n-E2B-it
+
+chat_template: gemma3n

    Qwen2-VL

    -
    base_model: Qwen/Qwen2-VL-7B-Instruct
-
-chat_template: qwen2_vl
    +
    base_model: Qwen/Qwen2-VL-7B-Instruct
+
+chat_template: qwen2_vl

    Qwen2.5-VL

    -
    base_model: Qwen/Qwen2.5-VL-7B-Instruct
-
-chat_template: qwen2_vl  # same as qwen2-vl
    +
    base_model: Qwen/Qwen2.5-VL-7B-Instruct
+
+chat_template: qwen2_vl  # same as qwen2-vl

    SmolVLM2

    @@ -737,7 +767,7 @@ Tip

    Please make sure to install num2words via pip3 install num2words==0.5.14

    -
    base_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct
    +
    base_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct

    LFM2-VL

    @@ -754,7 +784,7 @@ Warning

    Please uninstall causal-conv1d via pip3 uninstall -y causal-conv1d

    -
    base_model: LiquidAI/LFM2-VL-450M
    +
    base_model: LiquidAI/LFM2-VL-450M
    @@ -839,31 +869,31 @@ Warning

    Example

    Here is an example of a multi-modal dataset:

    -
    [
-  {
-    "messages": [
-        {
-            "role": "system",
-            "content": [
-              {"type": "text", "text": "You are a helpful assistant."}
-              ]
-        },
-        {
-            "role": "user",
-            "content": [
-                {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
-                {"type": "text", "text": "Describe this image in detail."}
-            ]
-        },
-        {
-            "role": "assistant",
-            "content": [
-              {"type": "text", "text": "The image is a bee."}
-            ]
-        }
-    ]
-  }
-]
    +
    [
+  {
+    "messages": [
+        {
+            "role": "system",
+            "content": [
+              {"type": "text", "text": "You are a helpful assistant."}
+              ]
+        },
+        {
+            "role": "user",
+            "content": [
+                {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+                {"type": "text", "text": "Describe this image in detail."}
+            ]
+        },
+        {
+            "role": "assistant",
+            "content": [
+              {"type": "text", "text": "The image is a bee."}
+            ]
+        }
+    ]
+  }
+]
    diff --git a/search.json b/search.json index 5e249f1a9..4f27916f5 100644 --- a/search.json +++ b/search.json @@ -472,7 +472,7 @@ "href": "docs/multimodal.html", "title": "MultiModal / Vision Language Models (BETA)", "section": "", - "text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL", + "text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL", "crumbs": [ "How To Guides", "MultiModal / Vision Language Models (BETA)" @@ -483,7 +483,7 @@ "href": "docs/multimodal.html#supported-models", "title": "MultiModal / Vision Language Models (BETA)", "section": "", - "text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL", + "text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL", "crumbs": [ "How To Guides", "MultiModal / Vision Language Models (BETA)" @@ -494,7 +494,7 @@ "href": "docs/multimodal.html#usage", "title": "MultiModal / Vision Language Models (BETA)", "section": "Usage", - "text": "Usage\nMultimodal support is limited and doesn’t have full feature parity.\nHere are the hyperparams you’ll need to use to finetune a multimodal model.\nprocessor_type: AutoProcessor\n\nskip_prepare_dataset: true\nremove_unused_columns: false # leave columns in place as they are needed to handle image embeddings during training\nsample_packing: false # not yet supported with multimodal\n\nchat_template: # see in next section if specified\n\n# example dataset\ndatasets:\n - path: HuggingFaceH4/llava-instruct-mix-vsft\n type: chat_template\n split: train[:1%]\n field_messages: messages\n\n# (optional) if doing lora, only finetune the Language model,\n# leave the vision model and vision tower frozen\n# load_in_8bit: true\nadapter: lora\nlora_target_modules: 'model.language_model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'\n\n# (optional) if you want to resize images to a set size\nimage_size: 512\nimage_resize_algorithm: bilinear\nPlease see examples folder for full configs.\n\n\n\n\n\n\nWarning\n\n\n\nSome of our chat_templates have been extended to support broader dataset types. This should not break any existing configs.\n\n\n\nMllama\nbase_model: meta-llama/Llama-3.2-11B-Vision-Instruct\n\nchat_template: llama3_2_vision\n\n\nLlama4\nbase_model: meta-llama/Llama-4-Scout-17B-16E-Instruct\n\nchat_template: llama4\n\n\nPixtral\nbase_model: mistralai/Pixtral-12B-2409\n\nchat_template: pixtral\n\n\nLlava-1.5\nbase_model: llava-hf/llava-1.5-7b-hf\n\nchat_template: llava\n\n\nMistral-Small-3.1\nbase_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503\n\nchat_template: mistral_v7_tekken\n\n\nVoxtral\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install audio lib via pip3 install librosa==0.11.0 'mistral_common[audio]==1.8.3'\n\n\nbase_model: mistralai/Voxtral-Mini-3B-2507\n\n\nGemma-3\n\n\n\n\n\n\nTip\n\n\n\nThe Gemma3-1B model is a text-only model, so please train as regular text model.\n\n\nFor multi-modal 4B/12B/27B models, use the following config:\nbase_model: google/gemma-3-4b-it\n\nchat_template: gemma3\n\n\nGemma-3n\n\n\n\n\n\n\nWarning\n\n\n\nThe model’s initial loss and grad norm will be very high. We suspect this to be due to the Conv in the vision layers.\n\n\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install timm via pip3 install timm==1.0.17\n\n\nbase_model: google/gemma-3n-E2B-it\n\nchat_template: gemma3n\n\n\nQwen2-VL\nbase_model: Qwen/Qwen2-VL-7B-Instruct\n\nchat_template: qwen2_vl\n\n\nQwen2.5-VL\nbase_model: Qwen/Qwen2.5-VL-7B-Instruct\n\nchat_template: qwen2_vl # same as qwen2-vl\n\n\nSmolVLM2\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install num2words via pip3 install num2words==0.5.14\n\n\nbase_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct\n\n\nLFM2-VL\n\n\n\n\n\n\nWarning\n\n\n\nPlease uninstall causal-conv1d via pip3 uninstall -y causal-conv1d\n\n\nbase_model: LiquidAI/LFM2-VL-450M", + "text": "Usage\nMultimodal support is limited and doesn’t have full feature parity.\nHere are the hyperparams you’ll need to use to finetune a multimodal model.\nprocessor_type: AutoProcessor\n\nskip_prepare_dataset: true\nremove_unused_columns: false # leave columns in place as they are needed to handle image embeddings during training\nsample_packing: false # not yet supported with multimodal\n\nchat_template: # see in next section if specified\n\n# example dataset\ndatasets:\n - path: HuggingFaceH4/llava-instruct-mix-vsft\n type: chat_template\n split: train[:1%]\n field_messages: messages\n\n# (optional) if doing lora, only finetune the Language model,\n# leave the vision model and vision tower frozen\n# load_in_8bit: true\nadapter: lora\nlora_target_modules: 'model.language_model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'\n\n# (optional) if you want to resize images to a set size\nimage_size: 512\nimage_resize_algorithm: bilinear\nPlease see examples folder for full configs.\n\n\n\n\n\n\nWarning\n\n\n\nSome of our chat_templates have been extended to support broader dataset types. This should not break any existing configs.\n\n\n\nMllama\nbase_model: meta-llama/Llama-3.2-11B-Vision-Instruct\n\nchat_template: llama3_2_vision\n\n\nLlama4\nbase_model: meta-llama/Llama-4-Scout-17B-16E-Instruct\n\nchat_template: llama4\n\n\nPixtral\nbase_model: mistralai/Pixtral-12B-2409\n\nchat_template: pixtral\n\n\nLlava-1.5\nbase_model: llava-hf/llava-1.5-7b-hf\n\nchat_template: llava\n\n\nMistral-Small-3.1\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'\n\n\nbase_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503\n\n\nMagistral-Small-2509\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'\n\n\nbase_model: mistralai/Magistral-Small-2509\n\n\nVoxtral\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install audio lib via pip3 install librosa==0.11.0 'mistral_common[audio]==1.8.3'\n\n\nbase_model: mistralai/Voxtral-Mini-3B-2507\n\n\nGemma-3\n\n\n\n\n\n\nTip\n\n\n\nThe Gemma3-1B model is a text-only model, so please train as regular text model.\n\n\nFor multi-modal 4B/12B/27B models, use the following config:\nbase_model: google/gemma-3-4b-it\n\nchat_template: gemma3\n\n\nGemma-3n\n\n\n\n\n\n\nWarning\n\n\n\nThe model’s initial loss and grad norm will be very high. We suspect this to be due to the Conv in the vision layers.\n\n\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install timm via pip3 install timm==1.0.17\n\n\nbase_model: google/gemma-3n-E2B-it\n\nchat_template: gemma3n\n\n\nQwen2-VL\nbase_model: Qwen/Qwen2-VL-7B-Instruct\n\nchat_template: qwen2_vl\n\n\nQwen2.5-VL\nbase_model: Qwen/Qwen2.5-VL-7B-Instruct\n\nchat_template: qwen2_vl # same as qwen2-vl\n\n\nSmolVLM2\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install num2words via pip3 install num2words==0.5.14\n\n\nbase_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct\n\n\nLFM2-VL\n\n\n\n\n\n\nWarning\n\n\n\nPlease uninstall causal-conv1d via pip3 uninstall -y causal-conv1d\n\n\nbase_model: LiquidAI/LFM2-VL-450M", "crumbs": [ "How To Guides", "MultiModal / Vision Language Models (BETA)" diff --git a/sitemap.xml b/sitemap.xml index 4d2e51f0b..042eca628 100644 --- a/sitemap.xml +++ b/sitemap.xml @@ -2,794 +2,794 @@ https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html - 2025-09-17T17:27:12.024Z + 2025-09-18T08:42:32.871Z https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html - 2025-09-17T17:27:12.040Z + 2025-09-18T08:42:32.888Z https://docs.axolotl.ai/FAQS.html - 2025-09-17T17:27:12.014Z + 2025-09-18T08:42:32.861Z https://docs.axolotl.ai/docs/unsloth.html - 2025-09-17T17:27:12.020Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/reward_modelling.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/docker.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/batch_vs_grad.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.862Z https://docs.axolotl.ai/docs/streaming.html - 2025-09-17T17:27:12.020Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/nccl.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/quantize.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/nd_parallelism.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/custom_integrations.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.862Z https://docs.axolotl.ai/docs/debugging.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/gradient_checkpointing.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/multimodal.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/dataset_loading.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html - 2025-09-17T17:30:32.480Z + 2025-09-18T08:45:47.321Z https://docs.axolotl.ai/docs/api/loaders.adapter.html - 2025-09-17T17:30:31.622Z + 2025-09-18T08:45:46.479Z https://docs.axolotl.ai/docs/api/core.builders.base.html - 2025-09-17T17:30:31.256Z + 2025-09-18T08:45:46.122Z https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html - 2025-09-17T17:30:31.459Z + 2025-09-18T08:45:46.318Z https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html - 2025-09-17T17:30:31.489Z + 2025-09-18T08:45:46.347Z https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html - 2025-09-17T17:30:32.042Z + 2025-09-18T08:45:46.892Z https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html - 2025-09-17T17:30:32.470Z + 2025-09-18T08:45:47.311Z https://docs.axolotl.ai/docs/api/cli.delinearize_llama4.html - 2025-09-17T17:30:31.423Z + 2025-09-18T08:45:46.285Z https://docs.axolotl.ai/docs/api/cli.evaluate.html - 2025-09-17T17:30:31.371Z + 2025-09-18T08:45:46.233Z https://docs.axolotl.ai/docs/api/utils.schemas.model.html - 2025-09-17T17:30:32.251Z + 2025-09-18T08:45:47.096Z https://docs.axolotl.ai/docs/api/cli.art.html - 2025-09-17T17:30:31.394Z + 2025-09-18T08:45:46.256Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html - 2025-09-17T17:30:31.805Z + 2025-09-18T08:45:46.660Z https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html - 2025-09-17T17:30:31.304Z + 2025-09-18T08:45:46.169Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html - 2025-09-17T17:30:31.836Z + 2025-09-18T08:45:46.690Z https://docs.axolotl.ai/docs/api/cli.args.html - 2025-09-17T17:30:31.391Z + 2025-09-18T08:45:46.252Z https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html - 2025-09-17T17:30:32.067Z + 2025-09-18T08:45:46.917Z https://docs.axolotl.ai/docs/api/evaluate.html - 2025-09-17T17:30:31.179Z + 2025-09-18T08:45:46.046Z https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html - 2025-09-17T17:30:31.767Z + 2025-09-18T08:45:46.622Z https://docs.axolotl.ai/docs/api/cli.vllm_serve.html - 2025-09-17T17:30:31.479Z + 2025-09-18T08:45:46.338Z https://docs.axolotl.ai/docs/api/cli.quantize.html - 2025-09-17T17:30:31.472Z + 2025-09-18T08:45:46.331Z https://docs.axolotl.ai/docs/api/cli.utils.sweeps.html - 2025-09-17T17:30:31.518Z + 2025-09-18T08:45:46.377Z https://docs.axolotl.ai/docs/api/core.builders.rl.html - 2025-09-17T17:30:31.266Z + 2025-09-18T08:45:46.131Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html - 2025-09-17T17:30:31.815Z + 2025-09-18T08:45:46.670Z https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html - 2025-09-17T17:30:31.779Z + 2025-09-18T08:45:46.634Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html - 2025-09-17T17:30:31.820Z + 2025-09-18T08:45:46.674Z https://docs.axolotl.ai/docs/api/core.datasets.chat.html - 2025-09-17T17:30:31.311Z + 2025-09-18T08:45:46.176Z https://docs.axolotl.ai/docs/api/utils.distributed.html - 2025-09-17T17:30:32.189Z + 2025-09-18T08:45:47.035Z https://docs.axolotl.ai/docs/api/integrations.base.html - 2025-09-17T17:30:32.458Z + 2025-09-18T08:45:47.299Z https://docs.axolotl.ai/docs/api/index.html - 2025-09-17T17:30:31.110Z + 2025-09-18T08:45:45.978Z https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html - 2025-09-17T17:30:32.093Z + 2025-09-18T08:45:46.942Z https://docs.axolotl.ai/docs/api/utils.quantization.html - 2025-09-17T17:30:32.230Z + 2025-09-18T08:45:47.075Z https://docs.axolotl.ai/docs/api/utils.dict.html - 2025-09-17T17:30:32.195Z + 2025-09-18T08:45:47.041Z https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html - 2025-09-17T17:30:31.572Z + 2025-09-18T08:45:46.430Z https://docs.axolotl.ai/docs/api/utils.schemas.config.html - 2025-09-17T17:30:32.244Z + 2025-09-18T08:45:47.089Z https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html - 2025-09-17T17:30:31.782Z + 2025-09-18T08:45:46.637Z https://docs.axolotl.ai/docs/api/utils.collators.mamba.html - 2025-09-17T17:30:32.523Z + 2025-09-18T08:45:47.363Z https://docs.axolotl.ai/docs/api/datasets.html - 2025-09-17T17:30:31.185Z + 2025-09-18T08:45:46.052Z https://docs.axolotl.ai/docs/api/convert.html - 2025-09-17T17:30:31.199Z + 2025-09-18T08:45:46.065Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html - 2025-09-17T17:30:31.828Z + 2025-09-18T08:45:46.682Z https://docs.axolotl.ai/docs/api/utils.tokenization.html - 2025-09-17T17:30:32.100Z + 2025-09-18T08:45:46.949Z https://docs.axolotl.ai/docs/api/core.trainers.base.html - 2025-09-17T17:30:31.545Z + 2025-09-18T08:45:46.403Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html - 2025-09-17T17:30:31.996Z + 2025-09-18T08:45:46.847Z https://docs.axolotl.ai/docs/api/loaders.model.html - 2025-09-17T17:30:31.607Z + 2025-09-18T08:45:46.464Z https://docs.axolotl.ai/docs/api/logging_config.html - 2025-09-17T17:30:31.250Z + 2025-09-18T08:45:46.116Z https://docs.axolotl.ai/docs/api/core.chat.format.shared.html - 2025-09-17T17:30:31.306Z + 2025-09-18T08:45:46.171Z https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html - 2025-09-17T17:30:32.499Z + 2025-09-18T08:45:47.340Z https://docs.axolotl.ai/docs/api/utils.schemas.enums.html - 2025-09-17T17:30:32.315Z + 2025-09-18T08:45:47.158Z https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html - 2025-09-17T17:30:32.579Z + 2025-09-18T08:45:47.419Z https://docs.axolotl.ai/docs/api/utils.bench.html - 2025-09-17T17:30:32.116Z + 2025-09-18T08:45:46.964Z https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html - 2025-09-17T17:30:32.569Z + 2025-09-18T08:45:47.409Z https://docs.axolotl.ai/docs/api/core.trainers.mamba.html - 2025-09-17T17:30:31.565Z + 2025-09-18T08:45:46.423Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html - 2025-09-17T17:30:31.722Z + 2025-09-18T08:45:46.577Z https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html - 2025-09-17T17:30:32.034Z + 2025-09-18T08:45:46.885Z https://docs.axolotl.ai/docs/api/core.chat.messages.html - 2025-09-17T17:30:31.301Z + 2025-09-18T08:45:46.166Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html - 2025-09-17T17:30:32.036Z + 2025-09-18T08:45:46.886Z https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html - 2025-09-17T17:30:32.064Z + 2025-09-18T08:45:46.914Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html - 2025-09-17T17:30:31.649Z + 2025-09-18T08:45:46.505Z https://docs.axolotl.ai/docs/api/loaders.patch_manager.html - 2025-09-17T17:30:31.632Z + 2025-09-18T08:45:46.489Z https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html - 2025-09-17T17:30:32.202Z + 2025-09-18T08:45:47.048Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html - 2025-09-17T17:30:31.988Z + 2025-09-18T08:45:46.840Z https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html - 2025-09-17T17:30:32.575Z + 2025-09-18T08:45:47.415Z https://docs.axolotl.ai/docs/api/loaders.tokenizer.html - 2025-09-17T17:30:31.615Z + 2025-09-18T08:45:46.472Z https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html - 2025-09-17T17:30:31.789Z + 2025-09-18T08:45:46.644Z https://docs.axolotl.ai/docs/api/utils.lora.html - 2025-09-17T17:30:32.107Z + 2025-09-18T08:45:46.955Z https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html - 2025-09-17T17:30:31.743Z + 2025-09-18T08:45:46.598Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html - 2025-09-17T17:30:31.642Z + 2025-09-18T08:45:46.499Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html - 2025-09-17T17:30:31.818Z + 2025-09-18T08:45:46.673Z https://docs.axolotl.ai/docs/api/kernels.swiglu.html - 2025-09-17T17:30:31.972Z + 2025-09-18T08:45:46.824Z https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html - 2025-09-17T17:30:32.294Z + 2025-09-18T08:45:47.138Z https://docs.axolotl.ai/docs/api/cli.main.html - 2025-09-17T17:30:31.353Z + 2025-09-18T08:45:46.217Z https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html - 2025-09-17T17:30:31.673Z + 2025-09-18T08:45:46.529Z https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html - 2025-09-17T17:30:31.991Z + 2025-09-18T08:45:46.843Z https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html - 2025-09-17T17:30:31.303Z + 2025-09-18T08:45:46.168Z https://docs.axolotl.ai/docs/api/cli.cloud.base.html - 2025-09-17T17:30:31.482Z + 2025-09-18T08:45:46.341Z https://docs.axolotl.ai/docs/api/core.trainers.trl.html - 2025-09-17T17:30:31.560Z + 2025-09-18T08:45:46.418Z https://docs.axolotl.ai/docs/mixed_precision.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/installation.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/mac.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/sequence_parallelism.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/faq.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/dataset-formats/tokenized.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/dataset-formats/pretraining.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/dataset-formats/template_free.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/dataset-formats/index.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/dataset-formats/conversation.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/lr_groups.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/inference.html - 2025-09-17T17:27:12.018Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/lora_optims.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/multipack.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/amd_hpc.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.862Z https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html - 2025-09-17T17:30:32.045Z + 2025-09-18T08:45:46.895Z https://docs.axolotl.ai/docs/api/cli.inference.html - 2025-09-17T17:30:31.437Z + 2025-09-18T08:45:46.298Z https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html - 2025-09-17T17:30:32.528Z + 2025-09-18T08:45:47.368Z https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html - 2025-09-17T17:30:32.112Z + 2025-09-18T08:45:46.961Z https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html - 2025-09-17T17:30:31.986Z + 2025-09-18T08:45:46.838Z https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html - 2025-09-17T17:30:32.462Z + 2025-09-18T08:45:47.303Z https://docs.axolotl.ai/docs/api/utils.schemas.training.html - 2025-09-17T17:30:32.258Z + 2025-09-18T08:45:47.103Z https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html - 2025-09-17T17:30:32.306Z + 2025-09-18T08:45:47.150Z https://docs.axolotl.ai/docs/api/utils.schemas.utils.html - 2025-09-17T17:30:32.321Z + 2025-09-18T08:45:47.164Z https://docs.axolotl.ai/docs/api/cli.checks.html - 2025-09-17T17:30:31.400Z + 2025-09-18T08:45:46.262Z https://docs.axolotl.ai/docs/api/utils.callbacks.qat.html - 2025-09-17T17:30:32.594Z + 2025-09-18T08:45:47.434Z https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html - 2025-09-17T17:30:31.989Z + 2025-09-18T08:45:46.841Z https://docs.axolotl.ai/docs/api/utils.data.sft.html - 2025-09-17T17:30:32.210Z + 2025-09-18T08:45:47.056Z https://docs.axolotl.ai/docs/api/utils.chat_templates.html - 2025-09-17T17:30:32.102Z + 2025-09-18T08:45:46.950Z https://docs.axolotl.ai/docs/api/monkeypatch.utils.html - 2025-09-17T17:30:32.033Z + 2025-09-18T08:45:46.883Z https://docs.axolotl.ai/docs/api/cli.utils.fetch.html - 2025-09-17T17:30:31.507Z + 2025-09-18T08:45:46.365Z https://docs.axolotl.ai/docs/api/core.builders.causal.html - 2025-09-17T17:30:31.261Z + 2025-09-18T08:45:46.127Z https://docs.axolotl.ai/docs/api/utils.schemas.trl.html - 2025-09-17T17:30:32.289Z + 2025-09-18T08:45:47.132Z https://docs.axolotl.ai/docs/api/utils.data.streaming.html - 2025-09-17T17:30:32.204Z + 2025-09-18T08:45:47.050Z https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html - 2025-09-17T17:30:32.053Z + 2025-09-18T08:45:46.903Z https://docs.axolotl.ai/docs/api/prompt_strategies.base.html - 2025-09-17T17:30:31.674Z + 2025-09-18T08:45:46.530Z https://docs.axolotl.ai/docs/api/cli.merge_lora.html - 2025-09-17T17:30:31.446Z + 2025-09-18T08:45:46.307Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html - 2025-09-17T17:30:31.723Z + 2025-09-18T08:45:46.578Z https://docs.axolotl.ai/docs/api/loaders.constants.html - 2025-09-17T17:30:31.633Z + 2025-09-18T08:45:46.490Z https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html - 2025-09-17T17:30:32.052Z + 2025-09-18T08:45:46.902Z https://docs.axolotl.ai/docs/api/monkeypatch.relora.html - 2025-09-17T17:30:31.994Z + 2025-09-18T08:45:46.846Z https://docs.axolotl.ai/docs/api/utils.schedulers.html - 2025-09-17T17:30:32.169Z + 2025-09-18T08:45:47.016Z https://docs.axolotl.ai/docs/api/kernels.lora.html - 2025-09-17T17:30:31.950Z + 2025-09-18T08:45:46.803Z https://docs.axolotl.ai/docs/api/utils.collators.batching.html - 2025-09-17T17:30:32.520Z + 2025-09-18T08:45:47.360Z https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html - 2025-09-17T17:30:31.761Z + 2025-09-18T08:45:46.617Z https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html - 2025-09-17T17:30:31.583Z + 2025-09-18T08:45:46.440Z https://docs.axolotl.ai/docs/api/common.architectures.html - 2025-09-17T17:30:32.481Z + 2025-09-18T08:45:47.322Z https://docs.axolotl.ai/docs/api/cli.utils.html - 2025-09-17T17:30:31.490Z + 2025-09-18T08:45:46.349Z https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html - 2025-09-17T17:30:31.858Z + 2025-09-18T08:45:46.712Z https://docs.axolotl.ai/docs/api/core.training_args.html - 2025-09-17T17:30:31.278Z + 2025-09-18T08:45:46.144Z https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html - 2025-09-17T17:30:32.277Z + 2025-09-18T08:45:47.121Z https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html - 2025-09-17T17:30:31.708Z + 2025-09-18T08:45:46.563Z https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html - 2025-09-17T17:30:31.735Z + 2025-09-18T08:45:46.590Z https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html - 2025-09-17T17:30:32.461Z + 2025-09-18T08:45:47.302Z https://docs.axolotl.ai/docs/api/common.const.html - 2025-09-17T17:30:32.483Z + 2025-09-18T08:45:47.324Z https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html - 2025-09-17T17:30:32.025Z + 2025-09-18T08:45:46.876Z https://docs.axolotl.ai/docs/api/kernels.quantize.html - 2025-09-17T17:30:31.979Z + 2025-09-18T08:45:46.831Z https://docs.axolotl.ai/docs/api/cli.config.html - 2025-09-17T17:30:31.418Z + 2025-09-18T08:45:46.280Z https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html - 2025-09-17T17:30:31.755Z + 2025-09-18T08:45:46.611Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html - 2025-09-17T17:30:31.817Z + 2025-09-18T08:45:46.671Z https://docs.axolotl.ai/docs/api/kernels.geglu.html - 2025-09-17T17:30:31.961Z + 2025-09-18T08:45:46.814Z https://docs.axolotl.ai/docs/api/utils.freeze.html - 2025-09-17T17:30:32.123Z + 2025-09-18T08:45:46.972Z https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html - 2025-09-17T17:30:32.584Z + 2025-09-18T08:45:47.424Z https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html - 2025-09-17T17:30:31.595Z + 2025-09-18T08:45:46.452Z https://docs.axolotl.ai/docs/api/cli.utils.train.html - 2025-09-17T17:30:31.530Z + 2025-09-18T08:45:46.388Z https://docs.axolotl.ai/docs/api/cli.utils.load.html - 2025-09-17T17:30:31.513Z + 2025-09-18T08:45:46.371Z https://docs.axolotl.ai/docs/api/utils.collators.core.html - 2025-09-17T17:30:32.500Z + 2025-09-18T08:45:47.341Z https://docs.axolotl.ai/docs/api/integrations.liger.args.html - 2025-09-17T17:30:32.473Z + 2025-09-18T08:45:47.314Z https://docs.axolotl.ai/docs/api/cli.preprocess.html - 2025-09-17T17:30:31.467Z + 2025-09-18T08:45:46.326Z https://docs.axolotl.ai/docs/api/kernels.utils.html - 2025-09-17T17:30:31.981Z + 2025-09-18T08:45:46.833Z https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html - 2025-09-17T17:30:32.580Z + 2025-09-18T08:45:47.420Z https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html - 2025-09-17T17:30:32.062Z + 2025-09-18T08:45:46.912Z https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html - 2025-09-17T17:30:31.639Z + 2025-09-18T08:45:46.496Z https://docs.axolotl.ai/docs/api/loaders.processor.html - 2025-09-17T17:30:31.616Z + 2025-09-18T08:45:46.473Z https://docs.axolotl.ai/docs/api/core.trainers.utils.html - 2025-09-17T17:30:31.597Z + 2025-09-18T08:45:46.454Z https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html - 2025-09-17T17:30:31.795Z + 2025-09-18T08:45:46.649Z https://docs.axolotl.ai/docs/api/prompt_tokenizers.html - 2025-09-17T17:30:31.240Z + 2025-09-18T08:45:46.107Z https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html - 2025-09-17T17:30:32.587Z + 2025-09-18T08:45:47.427Z https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html - 2025-09-17T17:30:31.319Z + 2025-09-18T08:45:46.184Z https://docs.axolotl.ai/docs/api/utils.trainer.html - 2025-09-17T17:30:32.141Z + 2025-09-18T08:45:46.989Z https://docs.axolotl.ai/docs/api/cli.train.html - 2025-09-17T17:30:31.362Z + 2025-09-18T08:45:46.225Z https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html - 2025-09-17T17:30:32.477Z + 2025-09-18T08:45:47.318Z https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html - 2025-09-17T17:30:31.793Z + 2025-09-18T08:45:46.648Z https://docs.axolotl.ai/docs/api/utils.schemas.peft.html - 2025-09-17T17:30:32.285Z + 2025-09-18T08:45:47.129Z https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html - 2025-09-17T17:30:31.862Z + 2025-09-18T08:45:46.716Z https://docs.axolotl.ai/docs/api/cli.utils.args.html - 2025-09-17T17:30:31.502Z + 2025-09-18T08:45:46.360Z https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html - 2025-09-17T17:30:31.772Z + 2025-09-18T08:45:46.627Z https://docs.axolotl.ai/docs/api/common.datasets.html - 2025-09-17T17:30:32.498Z + 2025-09-18T08:45:47.338Z https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html - 2025-09-17T17:30:31.837Z + 2025-09-18T08:45:46.692Z https://docs.axolotl.ai/docs/api/train.html - 2025-09-17T17:30:31.168Z + 2025-09-18T08:45:46.036Z https://docs.axolotl.ai/docs/multi-node.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/input_output.html - 2025-09-17T17:27:12.018Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/ray-integration.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/getting-started.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/optimizers.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/multi-gpu.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/docs/dataset_preprocessing.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/torchao.html - 2025-09-17T17:27:12.020Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/config-reference.html - 2025-09-17T17:30:47.286Z + 2025-09-18T08:46:03.094Z https://docs.axolotl.ai/docs/rlhf.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.867Z https://docs.axolotl.ai/docs/cli.html - 2025-09-17T17:27:12.015Z + 2025-09-18T08:42:32.862Z https://docs.axolotl.ai/docs/fsdp_qlora.html - 2025-09-17T17:27:12.016Z + 2025-09-18T08:42:32.863Z https://docs.axolotl.ai/docs/qat.html - 2025-09-17T17:27:12.019Z + 2025-09-18T08:42:32.866Z https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html - 2025-09-17T17:27:12.040Z + 2025-09-18T08:42:32.888Z https://docs.axolotl.ai/index.html - 2025-09-17T17:27:12.036Z + 2025-09-18T08:42:32.883Z