From a93a5e6d303f0e9f9f6a5a30b4e8624e22270d48 Mon Sep 17 00:00:00 2001
From: Quarto GHA Workflow Runner <quarto-github-actions-publish@example.com>
Date: Sat, 12 Jul 2025 15:46:51 +0000
Subject: [PATCH] Built site for gh-pages

---
 .nojekyll        |   2 +-
 docs/docker.html |   2 +
 docs/rlhf.html   |  32 ++--
 search.json      |   6 +-
 sitemap.xml      | 378 +++++++++++++++++++++++------------------------
 5 files changed, 210 insertions(+), 210 deletions(-)

diff --git a/.nojekyll b/.nojekyll
index f2c30de18..15f25bd6f 100644
--- a/.nojekyll
+++ b/.nojekyll
@@ -1 +1 @@
-9001b065
\ No newline at end of file
+52e45560
\ No newline at end of file
diff --git a/docs/docker.html b/docs/docker.html
index 3b3b6e125..32a1f4e02 100644
--- a/docs/docker.html
+++ b/docs/docker.html
@@ -543,6 +543,7 @@ Important
 <ul>
 <li><code>main-base-py3.11-cu128-2.7.1</code></li>
 <li><code>main-base-py3.11-cu126-2.7.1</code></li>
+<li><code>main-base-py3.11-cu126-2.7.0</code></li>
 <li><code>main-base-py3.11-cu126-2.6.0</code></li>
 <li><code>main-base-py3.11-cu124-2.6.0</code></li>
 </ul>
@@ -586,6 +587,7 @@ Tip
 <ul>
 <li><code>main-py3.11-cu128-2.7.1</code></li>
 <li><code>main-py3.11-cu126-2.7.1</code></li>
+<li><code>main-py3.11-cu126-2.7.0</code></li>
 <li><code>main-py3.11-cu126-2.6.0</code></li>
 <li><code>main-py3.11-cu124-2.6.0</code></li>
 <li><code>main-latest</code></li>
diff --git a/docs/rlhf.html b/docs/rlhf.html
index ba678af7a..4b225aedb 100644
--- a/docs/rlhf.html
+++ b/docs/rlhf.html
@@ -792,15 +792,14 @@ Tip
 <span id="cb17-2"><a href="#cb17-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
 <span id="cb17-3"><a href="#cb17-3" aria-hidden="true" tabindex="-1"></a><span class="at">  </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> ...</span></span>
 <span id="cb17-4"><a href="#cb17-4" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
-<span id="cb17-5"><a href="#cb17-5" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">type</span><span class="kw">:</span><span class="at"> user_defined.default</span></span>
-<span id="cb17-6"><a href="#cb17-6" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb17-7"><a href="#cb17-7" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">"prompt"</span></span>
-<span id="cb17-8"><a href="#cb17-8" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_system</span><span class="kw">:</span><span class="at"> </span><span class="st">"system"</span></span>
-<span id="cb17-9"><a href="#cb17-9" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_chosen</span><span class="kw">:</span><span class="at"> </span><span class="st">"chosen"</span></span>
-<span id="cb17-10"><a href="#cb17-10" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_rejected</span><span class="kw">:</span><span class="at"> </span><span class="st">"rejected"</span></span>
-<span id="cb17-11"><a href="#cb17-11" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">prompt_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{prompt}"</span></span>
-<span id="cb17-12"><a href="#cb17-12" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">chosen_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{chosen}"</span></span>
-<span id="cb17-13"><a href="#cb17-13" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">rejected_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{rejected}"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb17-5"><a href="#cb17-5" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">type</span><span class="kw">:</span></span>
+<span id="cb17-6"><a href="#cb17-6" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">"prompt"</span></span>
+<span id="cb17-7"><a href="#cb17-7" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_system</span><span class="kw">:</span><span class="at"> </span><span class="st">"system"</span></span>
+<span id="cb17-8"><a href="#cb17-8" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_chosen</span><span class="kw">:</span><span class="at"> </span><span class="st">"chosen"</span></span>
+<span id="cb17-9"><a href="#cb17-9" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_rejected</span><span class="kw">:</span><span class="at"> </span><span class="st">"rejected"</span></span>
+<span id="cb17-10"><a href="#cb17-10" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">prompt_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{prompt}"</span></span>
+<span id="cb17-11"><a href="#cb17-11" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">chosen_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{chosen}"</span></span>
+<span id="cb17-12"><a href="#cb17-12" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">rejected_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{rejected}"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <p>The input format is a simple JSON input with customizable fields based on the above config.</p>
 <div class="sourceCode" id="cb18"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb18-1"><a href="#cb18-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
 <span id="cb18-2"><a href="#cb18-2" aria-hidden="true" tabindex="-1"></a>    <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span>  <span class="er">//</span> <span class="er">optional</span></span>
@@ -954,14 +953,13 @@ Tip
 <span id="cb33-2"><a href="#cb33-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
 <span id="cb33-3"><a href="#cb33-3" aria-hidden="true" tabindex="-1"></a><span class="at">  </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> ...</span></span>
 <span id="cb33-4"><a href="#cb33-4" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
-<span id="cb33-5"><a href="#cb33-5" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">type</span><span class="kw">:</span><span class="at"> user_defined.default</span></span>
-<span id="cb33-6"><a href="#cb33-6" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb33-7"><a href="#cb33-7" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">"prompt"</span></span>
-<span id="cb33-8"><a href="#cb33-8" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_system</span><span class="kw">:</span><span class="at"> </span><span class="st">"system"</span></span>
-<span id="cb33-9"><a href="#cb33-9" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_completion</span><span class="kw">:</span><span class="at"> </span><span class="st">"completion"</span></span>
-<span id="cb33-10"><a href="#cb33-10" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_label</span><span class="kw">:</span><span class="at"> </span><span class="st">"label"</span></span>
-<span id="cb33-11"><a href="#cb33-11" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">prompt_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{prompt}"</span></span>
-<span id="cb33-12"><a href="#cb33-12" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">completion_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{completion}"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb33-5"><a href="#cb33-5" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">type</span><span class="kw">:</span></span>
+<span id="cb33-6"><a href="#cb33-6" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">"prompt"</span></span>
+<span id="cb33-7"><a href="#cb33-7" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_system</span><span class="kw">:</span><span class="at"> </span><span class="st">"system"</span></span>
+<span id="cb33-8"><a href="#cb33-8" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_completion</span><span class="kw">:</span><span class="at"> </span><span class="st">"completion"</span></span>
+<span id="cb33-9"><a href="#cb33-9" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">field_label</span><span class="kw">:</span><span class="at"> </span><span class="st">"label"</span></span>
+<span id="cb33-10"><a href="#cb33-10" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">prompt_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{prompt}"</span></span>
+<span id="cb33-11"><a href="#cb33-11" aria-hidden="true" tabindex="-1"></a><span class="at">      </span><span class="fu">completion_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{completion}"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <p>The input format is a simple JSON input with customizable fields based on the above config.</p>
 <div class="sourceCode" id="cb34"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb34-1"><a href="#cb34-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
 <span id="cb34-2"><a href="#cb34-2" aria-hidden="true" tabindex="-1"></a>    <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span>  <span class="er">//</span> <span class="er">optional</span></span>
diff --git a/search.json b/search.json
index 57801035a..5ebd7077c 100644
--- a/search.json
+++ b/search.json
@@ -2193,7 +2193,7 @@
     "href": "docs/rlhf.html#rlhf-using-axolotl",
     "title": "RLHF (Beta)",
     "section": "RLHF using Axolotl",
-    "text": "RLHF using Axolotl\n\n\n\n\n\n\nImportant\n\n\n\nThis is a BETA feature and many features are not fully implemented. You are encouraged to open new PRs to improve the integration and functionality.\n\n\nWe rely on the TRL library for implementations of various RL training methods, which we wrap around to expose in axolotl. Each method has their own supported ways of loading datasets and prompt formats.\n\n\n\n\n\n\nTip\n\n\n\nYou can find what each method supports by going into src/axolotl/prompt_strategies/{method} where {method} is one of our supported methods. The type: can be retrieved from {method}.{function_name}.\n\n\n\nDPO\nExample config:\nrl: dpo\ndatasets:\n  - path: Intel/orca_dpo_pairs\n    split: train\n    type: chatml.intel\n  - path: argilla/ultrafeedback-binarized-preferences\n    split: train\n    type: chatml\nDPO supports the following types with the following dataset format:\n\nchatml.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"chosen_response\": \"...\",\n    \"rejected_response\": \"...\"\n}\n\n\nchatml.argilla_chat\n{\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nchatml.icr\n{\n    \"system\": \"...\", // optional\n    \"input\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nchatml.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nchatml.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nchatml.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nllama3.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"chosen_response\": \"...\",\n    \"rejected_response\": \"...\"\n}\n\n\nllama3.argilla_chat\n{\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nllama3.icr\n{\n    \"system\": \"...\", // optional\n    \"input\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nllama3.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nllama3.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nllama3.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nzephyr.nectar\n{\n    \"prompt\": \"...\",\n    \"answers\": [\n        {\n            \"answer\": \"...\",\n            \"rank\": 1\n        },\n        {\n            \"answer\": \"...\",\n            \"rank\": 2\n        }\n        // ... more answers with ranks\n    ]\n}\n\n\nchat_template.default\nrl: dpo\ndatasets:\n  - path: ...\n    split: train\n    type: chat_template.default\n    field_messages: \"messages\"\n    field_chosen: \"chosen\"\n    field_rejected: \"rejected\"\n    message_property_mappings:\n      role: role\n      content: content\n    roles:\n      user: [\"user\"]\n      assistant: [\"assistant\"]\n      system: [\"system\"]\nSample input format:\n{\n    \"messages\": [\n        {\n            \"role\": \"system\",\n            \"content\": \"...\"\n        },\n        {\n            \"role\": \"user\",\n            \"content\": \"...\"\n        },\n        // ... more messages\n    ],\n    \"chosen\": {\n        \"role\": \"assistant\",\n        \"content\": \"...\"\n    },\n    \"rejected\": {\n        \"role\": \"assistant\",\n        \"content\": \"...\"\n    }\n}\n\n\nuser_defined.default\nFor custom behaviors,\nrl: dpo\ndatasets:\n  - path: ...\n    split: train\n    type: user_defined.default\n\n    field_prompt: \"prompt\"\n    field_system: \"system\"\n    field_chosen: \"chosen\"\n    field_rejected: \"rejected\"\n    prompt_format: \"{prompt}\"\n    chosen_format: \"{chosen}\"\n    rejected_format: \"{rejected}\"\nThe input format is a simple JSON input with customizable fields based on the above config.\n{\n    \"system\": \"...\",  // optional\n    \"prompt\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\n\nIPO\nAs IPO is just DPO with a different loss function, all supported dataset formats for DPO are also supported for IPO.\nrl: ipo\n\n\nORPO\nPaper: https://arxiv.org/abs/2403.07691\nrl: orpo\norpo_alpha: 0.1\nremove_unused_columns: false\n\nchat_template: chatml\ndatasets:\n  - path: argilla/ultrafeedback-binarized-preferences-cleaned\n    type: chat_template.argilla\nORPO supports the following types with the following dataset format:\n\nchat_template.argilla\n{\n    \"system\": \"...\",  // optional\n    \"prompt\": \"...\",  // if available, will be taken as user message for single-turn instead of from list below\n\n    // chosen/rejected should be same till last content and only even-number of alternating user/assistant turns\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\n\nKTO\nrl: kto\nrl_beta: 0.1  # default\nkto_desirable_weight: 1.0  # default\nkto_undesirable_weight: 1.0  # default\n\nremove_unused_columns: false\n\ndatasets:\n  - path: argilla/ultrafeedback-binarized-preferences-cleaned-kto\n    type: llama3.ultra\n    split: train\n\ngradient_checkpointing: true\ngradient_checkpointing_kwargs:\n  use_reentrant: true\nKTO supports the following types with the following dataset format:\n\nchatml.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nchatml.argilla_chat\n{\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"}\n    ],\n    \"completion\": [\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nchatml.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nchatml.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nchatml.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.argilla_chat\n{\n    \"completion\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nllama3.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nuser_defined.default\nFor custom behaviors,\nrl: kto\ndatasets:\n  - path: ...\n    split: train\n    type: user_defined.default\n\n    field_prompt: \"prompt\"\n    field_system: \"system\"\n    field_completion: \"completion\"\n    field_label: \"label\"\n    prompt_format: \"{prompt}\"\n    completion_format: \"{completion}\"\nThe input format is a simple JSON input with customizable fields based on the above config.\n{\n    \"system\": \"...\",  // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\",\n    \"label\": \"...\"\n}\n\n\n\nGRPO\n\n\n\n\n\n\nTip\n\n\n\nCheck out our GRPO cookbook.\n\n\nIn the latest GRPO implementation, vLLM is used to significantly speedup trajectory generation during training. In this example, we’re using 4 GPUs - 2 for training, and 2 for vLLM:\n\n\n\n\n\n\nImportant\n\n\n\nMake sure you’ve installed the correct version of vLLM by including it as an extra when installing axolotl, e.g. pip install axolotl[vllm].\n\n\nbase_model: Qwen/Qwen2.5-1.5B-Instruct\n\nvllm:\n    host: 0.0.0.0\n    port: 8000\n    tensor_parallel_size: 2\n    gpu_memory_utilization: 0.85\n    dtype: auto\n    # max_model_len: # you may find it useful to set the vLLM model context length if you know this beforehand\n\nrl: grpo\ntrl:\n    use_vllm: true\n    vllm_server_host: 0.0.0.0\n    vllm_server_port: 8000\n    vllm_server_timeout: 300\nCUDA_VISIBLE_DEVICES=2,3 axolotl vllm-serve grpo.yaml\nYour vLLM instance will now attempt to spin up, and it’s time to kick off training utilizing our remaining two GPUs. In another terminal, execute:\nCUDA_VISIBLE_DEVICES=0,1 axolotl train grpo.yaml --num-processes 2\n\n\n\n\n\n\nNote\n\n\n\nDue to TRL’s implementation with vLLM, the vLLM instance must use the last N GPUs instead of the first N GPUs. This is why in the example above, we use CUDA_VISIBLE_DEVICES=2,3 for the vLLM instance.\n\n\n\nReward functions\nGRPO uses custom reward functions and transformations. Please have them ready locally.\nFor example, to load OpenAI’s GSM8K and use a random reward for completions:\n# rewards.py\nimport random\n\ndef rand_reward_func(completions, **kwargs) -&gt; list[float]:\n    return [random.uniform(0, 1) for _ in completions]\n\ndef oai_gsm8k_transform(cfg, *args, **kwargs):\n    def transform_fn(example, tokenizer=None):\n        label = example[\"answer\"].split(\"####\")[-1].strip().replace(\",\", \"\")\n        return {\n            \"prompt\": [{\"role\": \"user\", \"content\": example[\"question\"]},],\n            \"answer\": label,\n        }\n    return transform_fn, {\"remove_columns\": [\"question\"]}\nrl: grpo\n\ntrl:\n    beta: 0.001\n    max_completion_length: 256\n    use_vllm: True\n    num_generations: 4\n    reward_funcs: [\"rewards.rand_reward_func\"]    # format: '{file_name}.{fn_name}'\n    reward_weights: [1.0]\ndatasets:\n  - path: openai/gsm8k\n    name: main\n    type: rewards.oai_gsm8k_transform  # format: '{file_name}.{fn_name}'\nTo see other examples of custom reward functions, please see TRL GRPO Docs.\nTo see all configs, please see TRLConfig.\n\n\nGRPO with DAPO/Dr. GRPO loss\nThe DAPO paper and subsequently Dr. GRPO paper proposed an alternative loss function for GRPO to remediate the penalty in longer responses.\ntrl:\n  loss_type: dr_grpo\n  # Normalizes loss based on max completion length (default: 256)\n  max_completion_length:\nFor more information, see GRPO docs.\n\n\n\nSimPO\nSimPO uses CPOTrainer but with alternative loss function.\nrl: simpo\nrl_beta: 0.1  # default in CPOTrainer\ncpo_alpha: 1.0  # default in CPOTrainer\nsimpo_gamma: 0.5  # default in CPOTrainer\nThis method uses the same dataset format as DPO.\n\n\nUsing local dataset files\ndatasets:\n  - ds_type: json\n    data_files:\n      - orca_rlhf.jsonl\n    split: train\n    type: chatml.intel\n\n\nTRL auto-unwrapping for PEFT\nTRL supports auto-unwrapping PEFT models for RL training paradigms which rely on a reference model. This significantly reduces memory pressure as an additional refreference model does not need to be loaded, and reference model log-probabilities can be obtained by disabling PEFT adapters. This is enabled by default. To turn it off, pass the following config:\n# load ref model when adapter training.\nrl_adapter_ref_model: true",
+    "text": "RLHF using Axolotl\n\n\n\n\n\n\nImportant\n\n\n\nThis is a BETA feature and many features are not fully implemented. You are encouraged to open new PRs to improve the integration and functionality.\n\n\nWe rely on the TRL library for implementations of various RL training methods, which we wrap around to expose in axolotl. Each method has their own supported ways of loading datasets and prompt formats.\n\n\n\n\n\n\nTip\n\n\n\nYou can find what each method supports by going into src/axolotl/prompt_strategies/{method} where {method} is one of our supported methods. The type: can be retrieved from {method}.{function_name}.\n\n\n\nDPO\nExample config:\nrl: dpo\ndatasets:\n  - path: Intel/orca_dpo_pairs\n    split: train\n    type: chatml.intel\n  - path: argilla/ultrafeedback-binarized-preferences\n    split: train\n    type: chatml\nDPO supports the following types with the following dataset format:\n\nchatml.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"chosen_response\": \"...\",\n    \"rejected_response\": \"...\"\n}\n\n\nchatml.argilla_chat\n{\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nchatml.icr\n{\n    \"system\": \"...\", // optional\n    \"input\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nchatml.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nchatml.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nchatml.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nllama3.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"chosen_response\": \"...\",\n    \"rejected_response\": \"...\"\n}\n\n\nllama3.argilla_chat\n{\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nllama3.icr\n{\n    \"system\": \"...\", // optional\n    \"input\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nllama3.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nllama3.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\nllama3.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nzephyr.nectar\n{\n    \"prompt\": \"...\",\n    \"answers\": [\n        {\n            \"answer\": \"...\",\n            \"rank\": 1\n        },\n        {\n            \"answer\": \"...\",\n            \"rank\": 2\n        }\n        // ... more answers with ranks\n    ]\n}\n\n\nchat_template.default\nrl: dpo\ndatasets:\n  - path: ...\n    split: train\n    type: chat_template.default\n    field_messages: \"messages\"\n    field_chosen: \"chosen\"\n    field_rejected: \"rejected\"\n    message_property_mappings:\n      role: role\n      content: content\n    roles:\n      user: [\"user\"]\n      assistant: [\"assistant\"]\n      system: [\"system\"]\nSample input format:\n{\n    \"messages\": [\n        {\n            \"role\": \"system\",\n            \"content\": \"...\"\n        },\n        {\n            \"role\": \"user\",\n            \"content\": \"...\"\n        },\n        // ... more messages\n    ],\n    \"chosen\": {\n        \"role\": \"assistant\",\n        \"content\": \"...\"\n    },\n    \"rejected\": {\n        \"role\": \"assistant\",\n        \"content\": \"...\"\n    }\n}\n\n\nuser_defined.default\nFor custom behaviors,\nrl: dpo\ndatasets:\n  - path: ...\n    split: train\n    type:\n      field_prompt: \"prompt\"\n      field_system: \"system\"\n      field_chosen: \"chosen\"\n      field_rejected: \"rejected\"\n      prompt_format: \"{prompt}\"\n      chosen_format: \"{chosen}\"\n      rejected_format: \"{rejected}\"\nThe input format is a simple JSON input with customizable fields based on the above config.\n{\n    \"system\": \"...\",  // optional\n    \"prompt\": \"...\",\n    \"chosen\": \"...\",\n    \"rejected\": \"...\"\n}\n\n\n\nIPO\nAs IPO is just DPO with a different loss function, all supported dataset formats for DPO are also supported for IPO.\nrl: ipo\n\n\nORPO\nPaper: https://arxiv.org/abs/2403.07691\nrl: orpo\norpo_alpha: 0.1\nremove_unused_columns: false\n\nchat_template: chatml\ndatasets:\n  - path: argilla/ultrafeedback-binarized-preferences-cleaned\n    type: chat_template.argilla\nORPO supports the following types with the following dataset format:\n\nchat_template.argilla\n{\n    \"system\": \"...\",  // optional\n    \"prompt\": \"...\",  // if available, will be taken as user message for single-turn instead of from list below\n\n    // chosen/rejected should be same till last content and only even-number of alternating user/assistant turns\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ],\n    \"rejected\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\n\nKTO\nrl: kto\nrl_beta: 0.1  # default\nkto_desirable_weight: 1.0  # default\nkto_undesirable_weight: 1.0  # default\n\nremove_unused_columns: false\n\ndatasets:\n  - path: argilla/ultrafeedback-binarized-preferences-cleaned-kto\n    type: llama3.ultra\n    split: train\n\ngradient_checkpointing: true\ngradient_checkpointing_kwargs:\n  use_reentrant: true\nKTO supports the following types with the following dataset format:\n\nchatml.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nchatml.argilla_chat\n{\n    \"chosen\": [\n        {\"role\": \"user\", \"content\": \"...\"}\n    ],\n    \"completion\": [\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nchatml.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nchatml.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nchatml.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.argilla\n{\n    \"system\": \"...\", // optional\n    \"instruction\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.argilla_chat\n{\n    \"completion\": [\n        {\"role\": \"user\", \"content\": \"...\"},\n        {\"role\": \"assistant\", \"content\": \"...\"}\n    ]\n}\n\n\nllama3.intel\n{\n    \"system\": \"...\", // optional\n    \"question\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.prompt_pairs\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nllama3.ultra\n{\n    \"system\": \"...\", // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\"\n}\n\n\nuser_defined.default\nFor custom behaviors,\nrl: kto\ndatasets:\n  - path: ...\n    split: train\n    type:\n      field_prompt: \"prompt\"\n      field_system: \"system\"\n      field_completion: \"completion\"\n      field_label: \"label\"\n      prompt_format: \"{prompt}\"\n      completion_format: \"{completion}\"\nThe input format is a simple JSON input with customizable fields based on the above config.\n{\n    \"system\": \"...\",  // optional\n    \"prompt\": \"...\",\n    \"completion\": \"...\",\n    \"label\": \"...\"\n}\n\n\n\nGRPO\n\n\n\n\n\n\nTip\n\n\n\nCheck out our GRPO cookbook.\n\n\nIn the latest GRPO implementation, vLLM is used to significantly speedup trajectory generation during training. In this example, we’re using 4 GPUs - 2 for training, and 2 for vLLM:\n\n\n\n\n\n\nImportant\n\n\n\nMake sure you’ve installed the correct version of vLLM by including it as an extra when installing axolotl, e.g. pip install axolotl[vllm].\n\n\nbase_model: Qwen/Qwen2.5-1.5B-Instruct\n\nvllm:\n    host: 0.0.0.0\n    port: 8000\n    tensor_parallel_size: 2\n    gpu_memory_utilization: 0.85\n    dtype: auto\n    # max_model_len: # you may find it useful to set the vLLM model context length if you know this beforehand\n\nrl: grpo\ntrl:\n    use_vllm: true\n    vllm_server_host: 0.0.0.0\n    vllm_server_port: 8000\n    vllm_server_timeout: 300\nCUDA_VISIBLE_DEVICES=2,3 axolotl vllm-serve grpo.yaml\nYour vLLM instance will now attempt to spin up, and it’s time to kick off training utilizing our remaining two GPUs. In another terminal, execute:\nCUDA_VISIBLE_DEVICES=0,1 axolotl train grpo.yaml --num-processes 2\n\n\n\n\n\n\nNote\n\n\n\nDue to TRL’s implementation with vLLM, the vLLM instance must use the last N GPUs instead of the first N GPUs. This is why in the example above, we use CUDA_VISIBLE_DEVICES=2,3 for the vLLM instance.\n\n\n\nReward functions\nGRPO uses custom reward functions and transformations. Please have them ready locally.\nFor example, to load OpenAI’s GSM8K and use a random reward for completions:\n# rewards.py\nimport random\n\ndef rand_reward_func(completions, **kwargs) -&gt; list[float]:\n    return [random.uniform(0, 1) for _ in completions]\n\ndef oai_gsm8k_transform(cfg, *args, **kwargs):\n    def transform_fn(example, tokenizer=None):\n        label = example[\"answer\"].split(\"####\")[-1].strip().replace(\",\", \"\")\n        return {\n            \"prompt\": [{\"role\": \"user\", \"content\": example[\"question\"]},],\n            \"answer\": label,\n        }\n    return transform_fn, {\"remove_columns\": [\"question\"]}\nrl: grpo\n\ntrl:\n    beta: 0.001\n    max_completion_length: 256\n    use_vllm: True\n    num_generations: 4\n    reward_funcs: [\"rewards.rand_reward_func\"]    # format: '{file_name}.{fn_name}'\n    reward_weights: [1.0]\ndatasets:\n  - path: openai/gsm8k\n    name: main\n    type: rewards.oai_gsm8k_transform  # format: '{file_name}.{fn_name}'\nTo see other examples of custom reward functions, please see TRL GRPO Docs.\nTo see all configs, please see TRLConfig.\n\n\nGRPO with DAPO/Dr. GRPO loss\nThe DAPO paper and subsequently Dr. GRPO paper proposed an alternative loss function for GRPO to remediate the penalty in longer responses.\ntrl:\n  loss_type: dr_grpo\n  # Normalizes loss based on max completion length (default: 256)\n  max_completion_length:\nFor more information, see GRPO docs.\n\n\n\nSimPO\nSimPO uses CPOTrainer but with alternative loss function.\nrl: simpo\nrl_beta: 0.1  # default in CPOTrainer\ncpo_alpha: 1.0  # default in CPOTrainer\nsimpo_gamma: 0.5  # default in CPOTrainer\nThis method uses the same dataset format as DPO.\n\n\nUsing local dataset files\ndatasets:\n  - ds_type: json\n    data_files:\n      - orca_rlhf.jsonl\n    split: train\n    type: chatml.intel\n\n\nTRL auto-unwrapping for PEFT\nTRL supports auto-unwrapping PEFT models for RL training paradigms which rely on a reference model. This significantly reduces memory pressure as an additional refreference model does not need to be loaded, and reference model log-probabilities can be obtained by disabling PEFT adapters. This is enabled by default. To turn it off, pass the following config:\n# load ref model when adapter training.\nrl_adapter_ref_model: true",
     "crumbs": [
       "How To Guides",
       "RLHF (Beta)"
@@ -2523,7 +2523,7 @@
     "href": "docs/docker.html#base",
     "title": "Docker",
     "section": "Base",
-    "text": "Base\nThe base image is the most minimal image that can install Axolotl. It is based on the nvidia/cuda image. It includes python, torch, git, git-lfs, awscli, pydantic, and more.\n\nImage\naxolotlai/axolotl-base\nLink: Docker Hub\n\n\nTags format\nmain-base-py{python_version}-cu{cuda_version}-{pytorch_version}\nTags examples:\n\nmain-base-py3.11-cu128-2.7.1\nmain-base-py3.11-cu126-2.7.1\nmain-base-py3.11-cu126-2.6.0\nmain-base-py3.11-cu124-2.6.0",
+    "text": "Base\nThe base image is the most minimal image that can install Axolotl. It is based on the nvidia/cuda image. It includes python, torch, git, git-lfs, awscli, pydantic, and more.\n\nImage\naxolotlai/axolotl-base\nLink: Docker Hub\n\n\nTags format\nmain-base-py{python_version}-cu{cuda_version}-{pytorch_version}\nTags examples:\n\nmain-base-py3.11-cu128-2.7.1\nmain-base-py3.11-cu126-2.7.1\nmain-base-py3.11-cu126-2.7.0\nmain-base-py3.11-cu126-2.6.0\nmain-base-py3.11-cu124-2.6.0",
     "crumbs": [
       "Deployments",
       "Docker"
@@ -2534,7 +2534,7 @@
     "href": "docs/docker.html#main",
     "title": "Docker",
     "section": "Main",
-    "text": "Main\nThe main image is the image that is used to run Axolotl. It is based on the axolotlai/axolotl-base image and includes the Axolotl codebase, dependencies, and more.\n\nImage\naxolotlai/axolotl\nLink: Docker Hub\n\n\nTags format\n# on push to main\nmain-py{python_version}-cu{cuda_version}-{pytorch_version}\n\n# latest main (currently torch 2.6.0, python 3.11, cuda 12.4)\nmain-latest\n\n# nightly build\n{branch}-{date_in_YYYYMMDD}-py{python_version}-cu{cuda_version}-{pytorch_version}\n\n# tagged release\n{version}\n\n\n\n\n\n\nTip\n\n\n\nThere may be some extra tags appended to the image, like -vllm which installs those packages.\n\n\nTags examples:\n\nmain-py3.11-cu128-2.7.1\nmain-py3.11-cu126-2.7.1\nmain-py3.11-cu126-2.6.0\nmain-py3.11-cu124-2.6.0\nmain-latest\nmain-20250303-py3.11-cu124-2.6.0\nmain-20250303-py3.11-cu126-2.6.0\n0.10.1",
+    "text": "Main\nThe main image is the image that is used to run Axolotl. It is based on the axolotlai/axolotl-base image and includes the Axolotl codebase, dependencies, and more.\n\nImage\naxolotlai/axolotl\nLink: Docker Hub\n\n\nTags format\n# on push to main\nmain-py{python_version}-cu{cuda_version}-{pytorch_version}\n\n# latest main (currently torch 2.6.0, python 3.11, cuda 12.4)\nmain-latest\n\n# nightly build\n{branch}-{date_in_YYYYMMDD}-py{python_version}-cu{cuda_version}-{pytorch_version}\n\n# tagged release\n{version}\n\n\n\n\n\n\nTip\n\n\n\nThere may be some extra tags appended to the image, like -vllm which installs those packages.\n\n\nTags examples:\n\nmain-py3.11-cu128-2.7.1\nmain-py3.11-cu126-2.7.1\nmain-py3.11-cu126-2.7.0\nmain-py3.11-cu126-2.6.0\nmain-py3.11-cu124-2.6.0\nmain-latest\nmain-20250303-py3.11-cu124-2.6.0\nmain-20250303-py3.11-cu126-2.6.0\n0.10.1",
     "crumbs": [
       "Deployments",
       "Docker"
diff --git a/sitemap.xml b/sitemap.xml
index b08bfeb26..0350cdf6b 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -2,758 +2,758 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
     <loc>https://docs.axolotl.ai/TODO.html</loc>
-    <lastmod>2025-07-12T14:18:08.998Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.501Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/index.html</loc>
-    <lastmod>2025-07-12T14:18:09.018Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.521Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/debugging.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.503Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/amd_hpc.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html</loc>
-    <lastmod>2025-07-12T14:21:13.570Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.140Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html</loc>
-    <lastmod>2025-07-12T14:21:13.005Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.574Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/loaders.patch_manager.html</loc>
-    <lastmod>2025-07-12T14:21:12.616Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.183Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html</loc>
-    <lastmod>2025-07-12T14:21:12.312Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.879Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.train.html</loc>
-    <lastmod>2025-07-12T14:21:12.366Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.932Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html</loc>
-    <lastmod>2025-07-12T14:21:13.561Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.131Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.chat.messages.html</loc>
-    <lastmod>2025-07-12T14:21:12.310Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.876Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html</loc>
-    <lastmod>2025-07-12T14:21:13.566Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.136Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
-    <lastmod>2025-07-12T14:21:12.451Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.019Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.sweeps.html</loc>
-    <lastmod>2025-07-12T14:21:12.465Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.033Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.chat_templates.html</loc>
-    <lastmod>2025-07-12T14:21:13.103Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.672Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.chat.format.shared.html</loc>
-    <lastmod>2025-07-12T14:21:12.314Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.880Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html</loc>
-    <lastmod>2025-07-12T14:21:12.623Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.190Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.collators.mamba.html</loc>
-    <lastmod>2025-07-12T14:21:13.510Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.080Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/logging_config.html</loc>
-    <lastmod>2025-07-12T14:21:12.259Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.825Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html</loc>
-    <lastmod>2025-07-12T14:21:13.515Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.084Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html</loc>
-    <lastmod>2025-07-12T14:21:12.743Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.311Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/kernels.utils.html</loc>
-    <lastmod>2025-07-12T14:21:12.955Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.523Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html</loc>
-    <lastmod>2025-07-12T14:21:12.776Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.344Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/kernels.swiglu.html</loc>
-    <lastmod>2025-07-12T14:21:12.946Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.514Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/common.const.html</loc>
-    <lastmod>2025-07-12T14:21:13.470Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.040Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.cloud.base.html</loc>
-    <lastmod>2025-07-12T14:21:12.507Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.074Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html</loc>
-    <lastmod>2025-07-12T14:21:13.573Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.143Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html</loc>
-    <lastmod>2025-07-12T14:21:13.069Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.638Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/common.architectures.html</loc>
-    <lastmod>2025-07-12T14:21:13.469Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.038Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html</loc>
-    <lastmod>2025-07-12T14:21:12.770Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.338Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.peft.html</loc>
-    <lastmod>2025-07-12T14:21:13.276Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.845Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html</loc>
-    <lastmod>2025-07-12T14:21:12.800Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.367Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html</loc>
-    <lastmod>2025-07-12T14:21:13.267Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.836Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html</loc>
-    <lastmod>2025-07-12T14:21:12.717Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.284Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.base.html</loc>
-    <lastmod>2025-07-12T14:21:12.658Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.225Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.lora.html</loc>
-    <lastmod>2025-07-12T14:21:13.108Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.677Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html</loc>
-    <lastmod>2025-07-12T14:21:12.749Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.317Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.trl.html</loc>
-    <lastmod>2025-07-12T14:21:13.279Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.848Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html</loc>
-    <lastmod>2025-07-12T14:21:12.798Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.366Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html</loc>
-    <lastmod>2025-07-12T14:21:13.457Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.027Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html</loc>
-    <lastmod>2025-07-12T14:21:13.095Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.664Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html</loc>
-    <lastmod>2025-07-12T14:21:13.196Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.765Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html</loc>
-    <lastmod>2025-07-12T14:21:13.063Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.631Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html</loc>
-    <lastmod>2025-07-12T14:21:12.513Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.081Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html</loc>
-    <lastmod>2025-07-12T14:21:12.703Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.271Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.freeze.html</loc>
-    <lastmod>2025-07-12T14:21:13.125Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.693Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
-    <lastmod>2025-07-12T14:21:12.843Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.410Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/integrations.base.html</loc>
-    <lastmod>2025-07-12T14:21:13.445Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.015Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html</loc>
-    <lastmod>2025-07-12T14:21:13.061Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.630Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html</loc>
-    <lastmod>2025-07-12T14:21:12.817Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.385Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.main.html</loc>
-    <lastmod>2025-07-12T14:21:12.358Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.924Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/common.datasets.html</loc>
-    <lastmod>2025-07-12T14:21:13.485Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.055Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/train.html</loc>
-    <lastmod>2025-07-12T14:21:12.173Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.739Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.base.html</loc>
-    <lastmod>2025-07-12T14:21:12.528Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.096Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html</loc>
-    <lastmod>2025-07-12T14:21:12.633Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.200Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html</loc>
-    <lastmod>2025-07-12T14:21:12.656Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.224Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.config.html</loc>
-    <lastmod>2025-07-12T14:21:13.238Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.807Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/loaders.tokenizer.html</loc>
-    <lastmod>2025-07-12T14:21:12.601Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.168Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/integrations.liger.args.html</loc>
-    <lastmod>2025-07-12T14:21:13.460Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.030Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.config.html</loc>
-    <lastmod>2025-07-12T14:21:12.417Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.984Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/loaders.processor.html</loc>
-    <lastmod>2025-07-12T14:21:12.602Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.170Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.utils.html</loc>
-    <lastmod>2025-07-12T14:21:13.041Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.610Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html</loc>
-    <lastmod>2025-07-12T14:21:13.449Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.019Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html</loc>
-    <lastmod>2025-07-12T14:21:12.559Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.126Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/loaders.adapter.html</loc>
-    <lastmod>2025-07-12T14:21:12.608Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.175Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html</loc>
-    <lastmod>2025-07-12T14:21:12.786Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.354Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html</loc>
-    <lastmod>2025-07-12T14:21:12.327Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.893Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html</loc>
-    <lastmod>2025-07-12T14:21:13.060Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.628Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/datasets.html</loc>
-    <lastmod>2025-07-12T14:21:12.195Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.760Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
-    <lastmod>2025-07-12T14:21:13.043Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.611Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.inference.html</loc>
-    <lastmod>2025-07-12T14:21:12.431Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.998Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.utils.html</loc>
-    <lastmod>2025-07-12T14:21:12.497Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.064Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.preprocess.html</loc>
-    <lastmod>2025-07-12T14:21:12.459Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.027Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/loaders.model.html</loc>
-    <lastmod>2025-07-12T14:21:12.592Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.160Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html</loc>
-    <lastmod>2025-07-12T14:21:12.581Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.149Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html</loc>
-    <lastmod>2025-07-12T14:21:12.569Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.137Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/batch_vs_grad.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/custom_integrations.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/quantize.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/unsloth.html</loc>
-    <lastmod>2025-07-12T14:18:09.004Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/ray-integration.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset-formats/template_free.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset-formats/index.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset-formats/pretraining.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/multi-gpu.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/torchao.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/cli.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/nccl.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset_preprocessing.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/faq.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.503Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/qat.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/lr_groups.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.505Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/mac.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
-    <lastmod>2025-07-12T14:18:09.022Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.525Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html</loc>
-    <lastmod>2025-07-12T14:18:09.022Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.525Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/input_output.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.505Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset_loading.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/getting-started.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.503Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/lora_optims.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.505Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/multi-node.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/fsdp_qlora.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.503Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/inference.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.505Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/sequence_parallelism.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/rlhf.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset-formats/tokenized.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset-formats/conversation.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html</loc>
-    <lastmod>2025-07-12T14:18:08.999Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.502Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/reward_modelling.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/docker.html</loc>
-    <lastmod>2025-07-12T14:18:09.000Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.503Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/installation.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.505Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/multimodal.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/config-reference.html</loc>
-    <lastmod>2025-07-12T14:21:26.033Z</lastmod>
+    <lastmod>2025-07-12T15:45:05.743Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_tokenizers.html</loc>
-    <lastmod>2025-07-12T14:21:12.249Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.816Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schedulers.html</loc>
-    <lastmod>2025-07-12T14:21:13.165Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.734Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html</loc>
-    <lastmod>2025-07-12T14:21:13.555Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.125Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html</loc>
-    <lastmod>2025-07-12T14:21:12.764Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.332Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.trl.html</loc>
-    <lastmod>2025-07-12T14:21:12.542Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.110Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html</loc>
-    <lastmod>2025-07-12T14:21:12.760Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.328Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html</loc>
-    <lastmod>2025-07-12T14:21:13.565Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.135Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.enums.html</loc>
-    <lastmod>2025-07-12T14:21:13.306Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.876Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.mamba.html</loc>
-    <lastmod>2025-07-12T14:21:12.548Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.115Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html</loc>
-    <lastmod>2025-07-12T14:21:12.980Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.548Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.relora.html</loc>
-    <lastmod>2025-07-12T14:21:13.004Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.572Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
-    <lastmod>2025-07-12T14:21:13.050Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.619Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/loaders.constants.html</loc>
-    <lastmod>2025-07-12T14:21:12.617Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.185Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.callbacks.qat.html</loc>
-    <lastmod>2025-07-12T14:21:13.580Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.150Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.model.html</loc>
-    <lastmod>2025-07-12T14:21:13.244Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.814Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html</loc>
-    <lastmod>2025-07-12T14:21:12.753Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.321Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html</loc>
-    <lastmod>2025-07-12T14:21:13.450Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.020Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/convert.html</loc>
-    <lastmod>2025-07-12T14:21:12.208Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.774Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/kernels.quantize.html</loc>
-    <lastmod>2025-07-12T14:21:12.953Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.521Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.training_args.html</loc>
-    <lastmod>2025-07-12T14:21:12.287Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.853Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html</loc>
-    <lastmod>2025-07-12T14:21:12.690Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.257Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/index.html</loc>
-    <lastmod>2025-07-12T14:21:12.112Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.677Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html</loc>
-    <lastmod>2025-07-12T14:21:12.737Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.305Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.trainer.html</loc>
-    <lastmod>2025-07-12T14:21:13.141Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.710Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html</loc>
-    <lastmod>2025-07-12T14:21:12.775Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.342Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html</loc>
-    <lastmod>2025-07-12T14:21:13.033Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.602Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/kernels.lora.html</loc>
-    <lastmod>2025-07-12T14:21:12.925Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.493Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.vllm_serve.html</loc>
-    <lastmod>2025-07-12T14:21:12.504Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.071Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html</loc>
-    <lastmod>2025-07-12T14:21:13.284Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.853Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.utils.html</loc>
-    <lastmod>2025-07-12T14:21:13.312Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.882Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html</loc>
-    <lastmod>2025-07-12T14:21:12.981Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.550Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html</loc>
-    <lastmod>2025-07-12T14:21:13.464Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.033Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html</loc>
-    <lastmod>2025-07-12T14:21:12.996Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.564Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.collators.core.html</loc>
-    <lastmod>2025-07-12T14:21:13.488Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.057Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html</loc>
-    <lastmod>2025-07-12T14:21:12.311Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.877Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html</loc>
-    <lastmod>2025-07-12T14:21:12.801Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.369Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.datasets.chat.html</loc>
-    <lastmod>2025-07-12T14:21:12.319Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.885Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.bench.html</loc>
-    <lastmod>2025-07-12T14:21:13.117Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.686Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.training.html</loc>
-    <lastmod>2025-07-12T14:21:13.249Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.819Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.collators.batching.html</loc>
-    <lastmod>2025-07-12T14:21:13.507Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.076Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html</loc>
-    <lastmod>2025-07-12T14:21:13.044Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.613Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html</loc>
-    <lastmod>2025-07-12T14:21:12.997Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.565Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.builders.causal.html</loc>
-    <lastmod>2025-07-12T14:21:12.269Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.836Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.evaluate.html</loc>
-    <lastmod>2025-07-12T14:21:12.374Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.940Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html</loc>
-    <lastmod>2025-07-12T14:21:13.053Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.622Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.utils.html</loc>
-    <lastmod>2025-07-12T14:21:12.583Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.150Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html</loc>
-    <lastmod>2025-07-12T14:21:13.296Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.866Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.dict.html</loc>
-    <lastmod>2025-07-12T14:21:13.188Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.757Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.builders.rl.html</loc>
-    <lastmod>2025-07-12T14:21:12.274Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.841Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html</loc>
-    <lastmod>2025-07-12T14:21:12.839Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.407Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.relora.html</loc>
-    <lastmod>2025-07-12T14:21:12.552Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.120Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html</loc>
-    <lastmod>2025-07-12T14:21:13.467Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.037Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.quantize.html</loc>
-    <lastmod>2025-07-12T14:21:12.518Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.085Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.checks.html</loc>
-    <lastmod>2025-07-12T14:21:12.400Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.966Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html</loc>
-    <lastmod>2025-07-12T14:21:12.809Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.377Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html</loc>
-    <lastmod>2025-07-12T14:21:13.113Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.682Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.quantization.html</loc>
-    <lastmod>2025-07-12T14:21:13.225Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.794Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html</loc>
-    <lastmod>2025-07-12T14:21:12.626Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.194Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/kernels.geglu.html</loc>
-    <lastmod>2025-07-12T14:21:12.936Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.504Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.data.pretraining.html</loc>
-    <lastmod>2025-07-12T14:21:13.197Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.767Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html</loc>
-    <lastmod>2025-07-12T14:21:12.819Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.386Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/core.builders.base.html</loc>
-    <lastmod>2025-07-12T14:21:12.265Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.831Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.merge_lora.html</loc>
-    <lastmod>2025-07-12T14:21:12.440Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.007Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html</loc>
-    <lastmod>2025-07-12T14:21:13.064Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.633Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.data.sft.html</loc>
-    <lastmod>2025-07-12T14:21:13.204Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.773Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html</loc>
-    <lastmod>2025-07-12T14:21:12.725Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.292Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.tokenization.html</loc>
-    <lastmod>2025-07-12T14:21:13.102Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.670Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html</loc>
-    <lastmod>2025-07-12T14:21:12.797Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.364Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html</loc>
-    <lastmod>2025-07-12T14:21:13.487Z</lastmod>
+    <lastmod>2025-07-12T15:44:53.056Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/cli.args.html</loc>
-    <lastmod>2025-07-12T14:21:12.393Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.960Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/evaluate.html</loc>
-    <lastmod>2025-07-12T14:21:12.184Z</lastmod>
+    <lastmod>2025-07-12T15:44:51.749Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html</loc>
-    <lastmod>2025-07-12T14:21:12.705Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.272Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/api/utils.distributed.html</loc>
-    <lastmod>2025-07-12T14:21:13.185Z</lastmod>
+    <lastmod>2025-07-12T15:44:52.754Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/docs/multipack.html</loc>
-    <lastmod>2025-07-12T14:18:09.003Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.506Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html</loc>
-    <lastmod>2025-07-12T14:18:09.005Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.510Z</lastmod>
   </url>
   <url>
     <loc>https://docs.axolotl.ai/FAQS.html</loc>
-    <lastmod>2025-07-12T14:18:08.998Z</lastmod>
+    <lastmod>2025-07-12T15:41:44.500Z</lastmod>
   </url>
 </urlset>