tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Built site for gh-pages

Browse Source
This commit is contained in:
Quarto GHA Workflow Runner
2025-06-10 04:44:24 +00:00
parent 5c8a0d0f82
commit e8e07e15d8
6 changed files with 1069 additions and 891 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.nojekyll
View File

@@ -1 +1 @@
5efba35f
cb332e67

125
docs/api/prompt_strategies.chat_template.html
View File

@@ -525,28 +525,101 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a> message_field_training_detail<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a> field_messages<span class="op">=</span><span class="st">'messages'</span>,</span>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a> field_system<span class="op">=</span><span class="st">'system'</span>,</span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a> roles<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a> chat_template_kwargs<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a> drop_system_message<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a> field_tools<span class="op">=</span><span class="st">'tools'</span>,</span>
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a> roles<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a> chat_template_kwargs<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a> drop_system_message<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Prompter for HF chat templates</p>
<section id="methods" class="level4">
<h4 class="anchored" data-anchor-id="methods">Methods</h4>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td><a href="#axolotl.prompt_strategies.chat_template.ChatTemplatePrompter.build_prompt">build_prompt</a></td>
<td>Build a prompt from a conversation.</td>
</tr>
</tbody>
</table>
<section id="axolotl.prompt_strategies.chat_template.ChatTemplatePrompter.build_prompt" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.prompt_strategies.chat_template.ChatTemplatePrompter.build_prompt">build_prompt</h5>
<div class="sourceCode" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplatePrompter.build_prompt(</span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a> conversation,</span>
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a> add_generation_prompt<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a> images<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a> tools<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Build a prompt from a conversation.</p>
<section id="parameters" class="level6 doc-section doc-section-parameters">
<h6 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters">Parameters</h6>
<table class="caption-top table">
<colgroup>
<col style="width: 28%">
<col style="width: 10%">
<col style="width: 46%">
<col style="width: 15%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>conversation</td>
<td></td>
<td>A list of messages.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>add_generation_prompt</td>
<td></td>
<td>Whether to add a generation prompt.</td>
<td><code>False</code></td>
</tr>
<tr class="odd">
<td>images</td>
<td></td>
<td>A list of images. (optional)</td>
<td><code>None</code></td>
</tr>
<tr class="even">
<td>tools</td>
<td></td>
<td>A list of tools. (optional)</td>
<td><code>None</code></td>
</tr>
</tbody>
</table>
</section>
</section>
</section>
</section>
<section id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy">ChatTemplateStrategy</h3>
<div class="sourceCode" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy(</span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a> prompter,</span>
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a> tokenizer,</span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a> train_on_inputs,</span>
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a> sequence_len,</span>
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a> roles_to_train<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a> train_on_eos<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a> train_on_eot<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a> eot_tokens<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-10"><a href="#cb2-10" aria-hidden="true" tabindex="-1"></a> split_thinking<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-11"><a href="#cb2-11" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy(</span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a> prompter,</span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a> tokenizer,</span>
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a> train_on_inputs,</span>
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a> sequence_len,</span>
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a> roles_to_train<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a> train_on_eos<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a> train_on_eot<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a> eot_tokens<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-10"><a href="#cb3-10" aria-hidden="true" tabindex="-1"></a> split_thinking<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-11"><a href="#cb3-11" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Tokenizing strategy for instruction-based prompts.</p>
<section id="methods" class="level4">
<h4 class="anchored" data-anchor-id="methods">Methods</h4>
<section id="methods-1" class="level4">
<h4 class="anchored" data-anchor-id="methods-1">Methods</h4>
<table class="caption-top table">
<thead>
<tr class="header">
@@ -571,27 +644,31 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</table>
<section id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token">find_first_eot_token</h5>
<div class="sourceCode" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token(</span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a> input_ids,</span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a> start_idx,</span>
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy.find_first_eot_token(</span>
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a> input_ids,</span>
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a> start_idx,</span>
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Find the first EOT token in the input_ids starting from start_idx.</p>
</section>
<section id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy.find_turn" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy.find_turn">find_turn</h5>
<div class="sourceCode" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy.find_turn(turns, turn_idx)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy.find_turn(</span>
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a> turns,</span>
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> turn_idx,</span>
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> tools<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Locate the starting and ending indices of the specified turn in a conversation.</p>
</section>
<section id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.prompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt">tokenize_prompt</h5>
<div class="sourceCode" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt(prompt)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.ChatTemplateStrategy.tokenize_prompt(prompt)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Public method that can handle either a single prompt or a batch of prompts.</p>
</section>
</section>
</section>
<section id="axolotl.prompt_strategies.chat_template.StrategyLoader" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.prompt_strategies.chat_template.StrategyLoader">StrategyLoader</h3>
<div class="sourceCode" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.StrategyLoader()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb7"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>prompt_strategies.chat_template.StrategyLoader()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Load chat template strategy based on configuration.</p>

1208
docs/config.html
View File

File diff suppressed because it is too large Load Diff

237
docs/dataset-formats/conversation.html
View File

@@ -549,9 +549,9 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="examples" class="level3">
<h3 class="anchored" data-anchor-id="examples">Examples</h3>
<ol type="1">
<li>(Legacy) Using the default chat template in the tokenizer_config.json on OpenAI messages format, training on only last message.</li>
</ol>
<section id="training-on-last-message" class="level4">
<h4 class="anchored" data-anchor-id="training-on-last-message">Training on last message</h4>
<p>(Legacy) Using the default chat template in the tokenizer_config.json on OpenAI messages format, training on only last message.</p>
<div class="sourceCode" id="cb3"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb3-2"><a href="#cb3-2" 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="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
@@ -570,24 +570,40 @@ Tip
<p>If you receive an error like “<code>chat_template</code> choice is <code>tokenizer_default</code> but tokenizer’s <code>chat_template</code> is null.”, it means the tokenizer does not have a default <code>chat_template</code>. Follow the examples below instead to set a custom <code>chat_template</code>.</p>
</div>
</div>
<ol start="2" type="1">
<li>Using the <code>gemma</code> chat template to override the tokenizer_config.json’s chat template on OpenAI messages format, training on all assistant messages.</li>
</ol>
</section>
<section id="overriding-default-chat-template" class="level4">
<h4 class="anchored" data-anchor-id="overriding-default-chat-template">Overriding default chat template</h4>
<p>Using the <code>gemma</code> chat template to override the tokenizer_config.json’s chat template on OpenAI messages format, training on all assistant messages.</p>
<div class="sourceCode" id="cb4"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> gemma</span><span class="co"> # this overwrites the tokenizer's chat_template</span></span>
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb4-3"><a href="#cb4-3" 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="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
<span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles_to_train</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"assistant"</span><span class="kw">]</span><span class="co"> # default value</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<ol start="3" type="1">
<li>Using the tokenizer_config.json’s chat template or <code>chatml</code> as fallback if the former’s chat template does not exist, on OpenAI messages format, training on all assistant messages.</li>
</ol>
<div class="callout callout-style-default callout-note callout-titled">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
<i class="callout-icon"></i>
</div>
<div class="callout-title-container flex-fill">
Note
</div>
</div>
<div class="callout-body-container callout-body">
<p>If you want to use built-in chat_template, use <code>chat_template: tokenizer_default</code> (this is set by default).</p>
</div>
</div>
</section>
<section id="using-default-chat-template-with-fallback" class="level4">
<h4 class="anchored" data-anchor-id="using-default-chat-template-with-fallback">Using default chat template with fallback</h4>
<p>Using the tokenizer_config.json’s chat template or <code>chatml</code> as fallback if the former’s chat template does not exist, on OpenAI messages format, training on all assistant messages.</p>
<div class="sourceCode" id="cb5"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> tokenizer_default_fallback_chatml</span><span class="co"> # this overwrites the tokenizer's chat_template</span></span>
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb5-3"><a href="#cb5-3" 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="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<ol start="4" type="1">
<li>Using a custom jinja template on OpenAI messages format, training on all assistant messages.</li>
</ol>
</section>
<section id="custom-jinja-template" class="level4">
<h4 class="anchored" data-anchor-id="custom-jinja-template">Custom Jinja template</h4>
<p>Using a custom jinja template on OpenAI messages format, training on all assistant messages.</p>
<div class="sourceCode" id="cb6"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="co"># chat_template: jinja # `jinja` will be implied if the `chat_template_jinja` is set and this field is empty</span></span>
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template_jinja</span><span class="kw">:</span><span class="at"> </span><span class="st">"{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'&lt;|system|&gt;' + '</span><span class="sc">\n</span><span class="st">' + message['content'] + '&lt;|end|&gt;' + '</span><span class="sc">\n</span><span class="st">'}}{% elif (message['role'] == 'user') %}{{'&lt;|user|&gt;' + '</span><span class="sc">\n</span><span class="st">' + message['content'] + '&lt;|end|&gt;' + '</span><span class="sc">\n</span><span class="st">' + '&lt;|assistant|&gt;' + '</span><span class="sc">\n</span><span class="st">'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '&lt;|end|&gt;' + '</span><span class="sc">\n</span><span class="st">'}}{% endif %}{% endfor %}"</span></span>
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a></span>
@@ -607,9 +623,12 @@ Important
<p>Please make sure that your <code>tokenizer.eos_token</code> is same as EOS (End-of-Sequence) token in template. Otherwise, set <code>eos_token</code> under <code>special_tokens:</code>.</p>
</div>
</div>
<ol start="5" type="1">
</section>
<section id="using-template-with-different-token-for-eot-and-eos" class="level4">
<h4 class="anchored" data-anchor-id="using-template-with-different-token-for-eot-and-eos">Using template with different token for EOT and EOS</h4>
<ul>
<li>If you are using a template that has a different EOT (End-of-Turn) token from EOS token or multiple EOT tokens (like Mistral V7 Tekken), set the <code>eot_tokens:</code> config. The handling of EOT tokens follows <code>train_on_eos:</code> which defaults to turn.</li>
</ol>
</ul>
<div class="sourceCode" id="cb7"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="fu">eot_tokens</span><span class="kw">:</span></span>
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="st">"[/INST]"</span></span>
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a><span class="co"> # - "[/SYSTEM_PROMPT]"</span></span>
@@ -647,9 +666,9 @@ Note
<p>You can add those tokens as new tokens under <code>tokens:</code> or (recommended) override unused added_tokens via <code>added_tokens_overrides:</code>. See <a href="../../docs/config.html">config</a> for more details.</p>
</div>
</div>
<ol start="6" type="1">
<ul>
<li>Continuing from the previous example, if you want to train on all EOT token trainable turns but only last EOS token, set <code>train_on_eos: last</code>.</li>
</ol>
</ul>
<div class="sourceCode" id="cb8"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="fu">eot_tokens</span><span class="kw">:</span></span>
<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="st">"[/INST]"</span></span>
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a><span class="co"> # ...</span></span>
@@ -673,51 +692,127 @@ Tip
<p>If EOS token only appears at the end of a prompt, <code>train_on_eos: last</code> is equivalent to <code>train_on_eos: turn</code>. Therefore, generally, you can leave them to their defaults and omit them.</p>
</div>
</div>
<ol start="7" type="1">
<li>(Advanced) Using fine-grained control over tokens and turns to train in a conversation</li>
</ol>
</section>
<section id="using-tool-use" class="level4">
<h4 class="anchored" data-anchor-id="using-tool-use">Using tool use</h4>
<p>Instead of passing <code>tools</code> via the system prompt, an alternative method would be to have the <code>tools</code> in a separate column and loaded via <code>chat_template</code> to let the template dynamically build it.</p>
<div class="sourceCode" id="cb9"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"tools"</span><span class="fu">:</span> <span class="ot">[</span></span>
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"type"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"function"</span><span class="fu">:</span> <span class="fu">{</span></span>
<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"name"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">"description"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">"parameters"</span><span class="fu">:</span> <span class="fu">{</span></span>
<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">"type"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a> <span class="dt">"properties"</span><span class="fu">:</span> <span class="fu">{</span></span>
<span id="cb9-11"><a href="#cb9-11" aria-hidden="true" tabindex="-1"></a> <span class="er">//</span> <span class="er">...</span></span>
<span id="cb9-12"><a href="#cb9-12" aria-hidden="true" tabindex="-1"></a> <span class="fu">},</span></span>
<span id="cb9-13"><a href="#cb9-13" aria-hidden="true" tabindex="-1"></a> <span class="dt">"required"</span><span class="fu">:</span> <span class="ot">[</span><span class="st">"..."</span><span class="ot">]</span><span class="fu">,</span></span>
<span id="cb9-14"><a href="#cb9-14" aria-hidden="true" tabindex="-1"></a> <span class="fu">},</span></span>
<span id="cb9-15"><a href="#cb9-15" aria-hidden="true" tabindex="-1"></a> <span class="fu">},</span></span>
<span id="cb9-16"><a href="#cb9-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-17"><a href="#cb9-17" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
<span id="cb9-18"><a href="#cb9-18" aria-hidden="true" tabindex="-1"></a> <span class="dt">"messages"</span><span class="fu">:</span> <span class="ot">[</span></span>
<span id="cb9-19"><a href="#cb9-19" aria-hidden="true" tabindex="-1"></a> <span class="er">//</span> <span class="er">...</span></span>
<span id="cb9-20"><a href="#cb9-20" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb9-21"><a href="#cb9-21" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="er">//</span> <span class="er">call</span> <span class="er">the</span> <span class="er">function</span> <span class="er">via</span> <span class="er">assistant</span></span>
<span id="cb9-22"><a href="#cb9-22" aria-hidden="true" tabindex="-1"></a> <span class="dt">"tool_calls"</span><span class="fu">:</span> <span class="ot">[</span></span>
<span id="cb9-23"><a href="#cb9-23" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb9-24"><a href="#cb9-24" aria-hidden="true" tabindex="-1"></a> <span class="dt">"type"</span><span class="fu">:</span> <span class="st">"function"</span><span class="fu">,</span></span>
<span id="cb9-25"><a href="#cb9-25" aria-hidden="true" tabindex="-1"></a> <span class="dt">"function"</span><span class="fu">:</span> <span class="fu">{</span></span>
<span id="cb9-26"><a href="#cb9-26" aria-hidden="true" tabindex="-1"></a> <span class="dt">"name"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
<span id="cb9-27"><a href="#cb9-27" aria-hidden="true" tabindex="-1"></a> <span class="dt">"arguments"</span><span class="fu">:</span> <span class="fu">{</span></span>
<span id="cb9-28"><a href="#cb9-28" aria-hidden="true" tabindex="-1"></a> <span class="dt">"..."</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
<span id="cb9-29"><a href="#cb9-29" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
<span id="cb9-30"><a href="#cb9-30" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
<span id="cb9-31"><a href="#cb9-31" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
<span id="cb9-32"><a href="#cb9-32" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
<span id="cb9-33"><a href="#cb9-33" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-34"><a href="#cb9-34" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb9-35"><a href="#cb9-35" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"tool"</span><span class="fu">,</span></span>
<span id="cb9-36"><a href="#cb9-36" aria-hidden="true" tabindex="-1"></a> <span class="dt">"name"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
<span id="cb9-37"><a href="#cb9-37" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span></span>
<span id="cb9-38"><a href="#cb9-38" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-39"><a href="#cb9-39" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
<span id="cb9-40"><a href="#cb9-40" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="callout callout-style-default callout-note callout-titled">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
<i class="callout-icon"></i>
</div>
<div class="callout-title-container flex-fill">
Note
</div>
</div>
<div class="callout-body-container callout-body">
<p>Tools need to follow <a href="https://json-schema.org/learn/getting-started-step-by-step">JSON schema</a>.</p>
</div>
</div>
<div class="sourceCode" id="cb10"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> llama4</span></span>
<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb10-3"><a href="#cb10-3" 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="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a><span class="co"> # field_tools: tools # default is `tools`</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="callout callout-style-default callout-tip callout-titled">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
<i class="callout-icon"></i>
</div>
<div class="callout-title-container flex-fill">
Tip
</div>
</div>
<div class="callout-body-container callout-body">
<p>Look into the <code>chat_template</code> you are using to see if it supports <code>tools</code> and what the expected role is for the tool answer. In the example above, the tool answer is expected to be in the <code>tool</code> or <code>ipython</code> role for <code>llama4</code> template.</p>
</div>
</div>
</section>
<section id="using-fine-grained-control-over-token-masking" class="level4">
<h4 class="anchored" data-anchor-id="using-fine-grained-control-over-token-masking">Using fine-grained control over token masking</h4>
<p>(Advanced) Using fine-grained control over tokens and turns to train in a conversation</p>
<p>For a data sample that looks like:</p>
<div class="code-with-filename">
<div class="code-with-filename-file">
<pre><strong>data.jsonl</strong></pre>
</div>
<div class="sourceCode" id="cb9" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span></span>
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"system"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"You are an AI assistant."</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"human"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"Hello"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"Hello"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"human"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"How are you?"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">"from"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span></span>
<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"I'm doing very well, thank you!"</span><span class="fu">,</span></span>
<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a> <span class="dt">"train_detail"</span><span class="fu">:</span> <span class="ot">[</span></span>
<span id="cb9-11"><a href="#cb9-11" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"begin_offset"</span><span class="fu">:</span> <span class="dv">0</span><span class="fu">,</span> <span class="dt">"end_offset"</span><span class="fu">:</span> <span class="dv">8</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-12"><a href="#cb9-12" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"begin_offset"</span><span class="fu">:</span> <span class="dv">9</span><span class="fu">,</span> <span class="dt">"end_offset"</span><span class="fu">:</span> <span class="dv">18</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-13"><a href="#cb9-13" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"begin_offset"</span><span class="fu">:</span> <span class="dv">19</span><span class="fu">,</span> <span class="dt">"end_offset"</span><span class="fu">:</span> <span class="dv">30</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-14"><a href="#cb9-14" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
<span id="cb9-15"><a href="#cb9-15" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-16"><a href="#cb9-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb9-17"><a href="#cb9-17" aria-hidden="true" tabindex="-1"></a> <span class="dt">"from"</span><span class="fu">:</span> <span class="st">"human"</span><span class="fu">,</span></span>
<span id="cb9-18"><a href="#cb9-18" aria-hidden="true" tabindex="-1"></a> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"I'm doing very well, thank you!"</span><span class="fu">,</span></span>
<span id="cb9-19"><a href="#cb9-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">,</span></span>
<span id="cb9-20"><a href="#cb9-20" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
<span id="cb9-21"><a href="#cb9-21" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"Hi there!"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span></span>
<span id="cb9-22"><a href="#cb9-22" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
<span id="cb9-23"><a href="#cb9-23" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb11" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span></span>
<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"system"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"You are an AI assistant."</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"human"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"Hello"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"Hello"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-6"><a href="#cb11-6" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"human"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"How are you?"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-7"><a href="#cb11-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb11-8"><a href="#cb11-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">"from"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span></span>
<span id="cb11-9"><a href="#cb11-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"I'm doing very well, thank you!"</span><span class="fu">,</span></span>
<span id="cb11-10"><a href="#cb11-10" aria-hidden="true" tabindex="-1"></a> <span class="dt">"train_detail"</span><span class="fu">:</span> <span class="ot">[</span></span>
<span id="cb11-11"><a href="#cb11-11" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"begin_offset"</span><span class="fu">:</span> <span class="dv">0</span><span class="fu">,</span> <span class="dt">"end_offset"</span><span class="fu">:</span> <span class="dv">8</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-12"><a href="#cb11-12" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"begin_offset"</span><span class="fu">:</span> <span class="dv">9</span><span class="fu">,</span> <span class="dt">"end_offset"</span><span class="fu">:</span> <span class="dv">18</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-13"><a href="#cb11-13" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"begin_offset"</span><span class="fu">:</span> <span class="dv">19</span><span class="fu">,</span> <span class="dt">"end_offset"</span><span class="fu">:</span> <span class="dv">30</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">false</span><span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-14"><a href="#cb11-14" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
<span id="cb11-15"><a href="#cb11-15" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-16"><a href="#cb11-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
<span id="cb11-17"><a href="#cb11-17" aria-hidden="true" tabindex="-1"></a> <span class="dt">"from"</span><span class="fu">:</span> <span class="st">"human"</span><span class="fu">,</span></span>
<span id="cb11-18"><a href="#cb11-18" aria-hidden="true" tabindex="-1"></a> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"I'm doing very well, thank you!"</span><span class="fu">,</span></span>
<span id="cb11-19"><a href="#cb11-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">,</span></span>
<span id="cb11-20"><a href="#cb11-20" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
<span id="cb11-21"><a href="#cb11-21" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"Hi there!"</span><span class="fu">,</span> <span class="dt">"train"</span><span class="fu">:</span> <span class="kw">true</span><span class="fu">}</span></span>
<span id="cb11-22"><a href="#cb11-22" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
<span id="cb11-23"><a href="#cb11-23" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>The configuration would look like:</p>
<div class="sourceCode" id="cb10"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb10-2"><a href="#cb10-2" 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="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
<span id="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> tokenizer_default</span></span>
<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> conversations</span></span>
<span id="cb10-6"><a href="#cb10-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_property_mappings</span><span class="kw">:</span></span>
<span id="cb10-7"><a href="#cb10-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">role</span><span class="kw">:</span><span class="at"> from</span></span>
<span id="cb10-8"><a href="#cb10-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">content</span><span class="kw">:</span><span class="at"> value</span></span>
<span id="cb10-9"><a href="#cb10-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles_to_train</span><span class="kw">:</span><span class="at"> </span><span class="kw">[]</span></span>
<span id="cb10-10"><a href="#cb10-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">train_on_eos</span><span class="kw">:</span><span class="at"> turn</span></span>
<span id="cb10-11"><a href="#cb10-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_field_training</span><span class="kw">:</span><span class="at"> train</span></span>
<span id="cb10-12"><a href="#cb10-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_field_training_detail</span><span class="kw">:</span><span class="at"> train_detail</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb12"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb12-2"><a href="#cb12-2" 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="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
<span id="cb12-4"><a href="#cb12-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> tokenizer_default</span></span>
<span id="cb12-5"><a href="#cb12-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> conversations</span></span>
<span id="cb12-6"><a href="#cb12-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_property_mappings</span><span class="kw">:</span></span>
<span id="cb12-7"><a href="#cb12-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">role</span><span class="kw">:</span><span class="at"> from</span></span>
<span id="cb12-8"><a href="#cb12-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">content</span><span class="kw">:</span><span class="at"> value</span></span>
<span id="cb12-9"><a href="#cb12-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles_to_train</span><span class="kw">:</span><span class="at"> </span><span class="kw">[]</span></span>
<span id="cb12-10"><a href="#cb12-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">train_on_eos</span><span class="kw">:</span><span class="at"> turn</span></span>
<span id="cb12-11"><a href="#cb12-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_field_training</span><span class="kw">:</span><span class="at"> train</span></span>
<span id="cb12-12"><a href="#cb12-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_field_training_detail</span><span class="kw">:</span><span class="at"> train_detail</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="callout callout-style-default callout-tip callout-titled">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
@@ -731,23 +826,25 @@ Tip
<p>It is not necessary to set both <code>message_field_training</code> and <code>message_field_training_detail</code> at once.</p>
</div>
</div>
<ol start="8" type="1">
<li>(For Qwen3 template only) Enable reasoning split, where the reasoning is split from the content and passed as a separate field into the template.</li>
</ol>
<div class="sourceCode" id="cb11"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb11-2"><a href="#cb11-2" 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="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> qwen3</span></span>
<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split_thinking</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</section>
<section id="reasoning-split" class="level4">
<h4 class="anchored" data-anchor-id="reasoning-split">Reasoning split</h4>
<p>(For Qwen3 template only) Enable reasoning split, where the reasoning is split from the content and passed as a separate field into the template.</p>
<div class="sourceCode" id="cb13"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb13-2"><a href="#cb13-2" 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="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
<span id="cb13-4"><a href="#cb13-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> qwen3</span></span>
<span id="cb13-5"><a href="#cb13-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split_thinking</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>For example, a content can look like:</p>
<div class="sourceCode" id="cb12"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"&lt;think&gt;Some thinking outputs&lt;/think&gt;Output after thinking."</span></span>
<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb14"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb14-2"><a href="#cb14-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"&lt;think&gt;Some thinking outputs&lt;/think&gt;Output after thinking."</span></span>
<span id="cb14-3"><a href="#cb14-3" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>After split, it will look like:</p>
<div class="sourceCode" id="cb13"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"reasoning_content"</span><span class="fu">:</span> <span class="st">"Some thinking outputs"</span><span class="fu">,</span></span>
<span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"Output after thinking..."</span></span>
<span id="cb13-4"><a href="#cb13-4" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb15"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb15-2"><a href="#cb15-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"reasoning_content"</span><span class="fu">:</span> <span class="st">"Some thinking outputs"</span><span class="fu">,</span></span>
<span id="cb15-3"><a href="#cb15-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"Output after thinking..."</span></span>
<span id="cb15-4"><a href="#cb15-4" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</section>
</section>
</section>
<section id="sharegpt" class="level2">
@@ -772,7 +869,7 @@ Important
<div class="code-with-filename-file">
<pre><strong>data.jsonl</strong></pre>
</div>
<div class="sourceCode" id="cb14" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb16" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>

10
search.json
View File

File diff suppressed because one or more lines are too long

378
sitemap.xml
View File

@@ -2,758 +2,758 @@
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url>
<loc>https://docs.axolotl.ai/FAQS.html</loc>
<lastmod>2025-06-09T06:14:21.507Z</lastmod>
<lastmod>2025-06-10T04:42:14.206Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
<lastmod>2025-06-09T06:14:21.533Z</lastmod>
<lastmod>2025-06-10T04:42:14.228Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html</loc>
<lastmod>2025-06-09T06:14:21.514Z</lastmod>
<lastmod>2025-06-10T04:42:14.212Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/lr_groups.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/lora_optims.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/rlhf.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/qat.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/fsdp_qlora.html</loc>
<lastmod>2025-06-09T06:14:21.510Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/custom_integrations.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.207Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset-formats/pretraining.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset-formats/template_free.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset-formats/conversation.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.207Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset-formats/tokenized.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/multipack.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/mac.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/input_output.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/quantize.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/cli.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.207Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/multi-node.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/nccl.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.data.sft.html</loc>
<lastmod>2025-06-09T06:14:49.831Z</lastmod>
<lastmod>2025-06-10T04:42:43.170Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html</loc>
<lastmod>2025-06-09T06:14:48.971Z</lastmod>
<lastmod>2025-06-10T04:42:42.299Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/evaluate.html</loc>
<lastmod>2025-06-09T06:14:48.755Z</lastmod>
<lastmod>2025-06-10T04:42:42.082Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html</loc>
<lastmod>2025-06-09T06:14:49.690Z</lastmod>
<lastmod>2025-06-10T04:42:43.027Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html</loc>
<lastmod>2025-06-09T06:14:49.347Z</lastmod>
<lastmod>2025-06-10T04:42:42.681Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html</loc>
<lastmod>2025-06-09T06:14:50.080Z</lastmod>
<lastmod>2025-06-10T04:42:43.419Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.builders.rl.html</loc>
<lastmod>2025-06-09T06:14:48.844Z</lastmod>
<lastmod>2025-06-10T04:42:42.171Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/common.const.html</loc>
<lastmod>2025-06-09T06:14:50.083Z</lastmod>
<lastmod>2025-06-10T04:42:43.422Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/kernels.geglu.html</loc>
<lastmod>2025-06-09T06:14:49.565Z</lastmod>
<lastmod>2025-06-10T04:42:42.900Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/index.html</loc>
<lastmod>2025-06-09T06:14:48.684Z</lastmod>
<lastmod>2025-06-10T04:42:42.011Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html</loc>
<lastmod>2025-06-09T06:14:50.061Z</lastmod>
<lastmod>2025-06-10T04:42:43.400Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html</loc>
<lastmod>2025-06-09T06:14:49.355Z</lastmod>
<lastmod>2025-06-10T04:42:42.689Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html</loc>
<lastmod>2025-06-09T06:14:49.278Z</lastmod>
<lastmod>2025-06-10T04:42:42.607Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.datasets.chat.html</loc>
<lastmod>2025-06-09T06:14:48.963Z</lastmod>
<lastmod>2025-06-10T04:42:42.291Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/train.html</loc>
<lastmod>2025-06-09T06:14:48.745Z</lastmod>
<lastmod>2025-06-10T04:42:42.071Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.preprocess.html</loc>
<lastmod>2025-06-09T06:14:49.104Z</lastmod>
<lastmod>2025-06-10T04:42:42.432Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html</loc>
<lastmod>2025-06-09T06:14:49.429Z</lastmod>
<lastmod>2025-06-10T04:42:42.763Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.training_args.html</loc>
<lastmod>2025-06-09T06:14:48.931Z</lastmod>
<lastmod>2025-06-10T04:42:42.259Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/datasets.html</loc>
<lastmod>2025-06-09T06:14:48.762Z</lastmod>
<lastmod>2025-06-10T04:42:42.089Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html</loc>
<lastmod>2025-06-09T06:14:50.101Z</lastmod>
<lastmod>2025-06-10T04:42:43.440Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/kernels.utils.html</loc>
<lastmod>2025-06-09T06:14:49.584Z</lastmod>
<lastmod>2025-06-10T04:42:42.919Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/loaders.adapter.html</loc>
<lastmod>2025-06-09T06:14:49.253Z</lastmod>
<lastmod>2025-06-10T04:42:42.582Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html</loc>
<lastmod>2025-06-09T06:14:48.955Z</lastmod>
<lastmod>2025-06-10T04:42:42.283Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html</loc>
<lastmod>2025-06-09T06:14:49.205Z</lastmod>
<lastmod>2025-06-10T04:42:42.534Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html</loc>
<lastmod>2025-06-09T06:14:49.158Z</lastmod>
<lastmod>2025-06-10T04:42:42.486Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html</loc>
<lastmod>2025-06-09T06:14:49.384Z</lastmod>
<lastmod>2025-06-10T04:42:42.718Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html</loc>
<lastmod>2025-06-09T06:14:49.432Z</lastmod>
<lastmod>2025-06-10T04:42:42.766Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.relora.html</loc>
<lastmod>2025-06-09T06:14:49.633Z</lastmod>
<lastmod>2025-06-10T04:42:42.969Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/kernels.swiglu.html</loc>
<lastmod>2025-06-09T06:14:49.575Z</lastmod>
<lastmod>2025-06-10T04:42:42.911Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.cloud.base.html</loc>
<lastmod>2025-06-09T06:14:49.152Z</lastmod>
<lastmod>2025-06-10T04:42:42.480Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/common.datasets.html</loc>
<lastmod>2025-06-09T06:14:50.100Z</lastmod>
<lastmod>2025-06-10T04:42:43.438Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html</loc>
<lastmod>2025-06-09T06:14:49.227Z</lastmod>
<lastmod>2025-06-10T04:42:42.556Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.merge_lora.html</loc>
<lastmod>2025-06-09T06:14:49.084Z</lastmod>
<lastmod>2025-06-10T04:42:42.412Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html</loc>
<lastmod>2025-06-09T06:14:49.746Z</lastmod>
<lastmod>2025-06-10T04:42:43.084Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html</loc>
<lastmod>2025-06-09T06:14:49.417Z</lastmod>
<lastmod>2025-06-10T04:42:42.751Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/integrations.liger.args.html</loc>
<lastmod>2025-06-09T06:14:50.074Z</lastmod>
<lastmod>2025-06-10T04:42:43.412Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html</loc>
<lastmod>2025-06-09T06:14:50.186Z</lastmod>
<lastmod>2025-06-10T04:42:43.518Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.chat_templates.html</loc>
<lastmod>2025-06-09T06:14:49.736Z</lastmod>
<lastmod>2025-06-10T04:42:43.073Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.builders.base.html</loc>
<lastmod>2025-06-09T06:14:48.832Z</lastmod>
<lastmod>2025-06-10T04:42:42.159Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mamba.html</loc>
<lastmod>2025-06-09T06:14:49.194Z</lastmod>
<lastmod>2025-06-10T04:42:42.523Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html</loc>
<lastmod>2025-06-09T06:14:49.469Z</lastmod>
<lastmod>2025-06-10T04:42:42.804Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.data.pretraining.html</loc>
<lastmod>2025-06-09T06:14:49.830Z</lastmod>
<lastmod>2025-06-10T04:42:43.168Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.peft.html</loc>
<lastmod>2025-06-09T06:14:49.903Z</lastmod>
<lastmod>2025-06-10T04:42:43.240Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html</loc>
<lastmod>2025-06-09T06:14:49.679Z</lastmod>
<lastmod>2025-06-10T04:42:43.016Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html</loc>
<lastmod>2025-06-09T06:14:49.320Z</lastmod>
<lastmod>2025-06-10T04:42:42.655Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html</loc>
<lastmod>2025-06-09T06:14:49.448Z</lastmod>
<lastmod>2025-06-10T04:42:42.782Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
<lastmod>2025-06-09T06:14:49.669Z</lastmod>
<lastmod>2025-06-10T04:42:43.006Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.shared.html</loc>
<lastmod>2025-06-09T06:14:48.958Z</lastmod>
<lastmod>2025-06-10T04:42:42.286Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/logging_config.html</loc>
<lastmod>2025-06-09T06:14:48.826Z</lastmod>
<lastmod>2025-06-10T04:42:42.153Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.sweeps.html</loc>
<lastmod>2025-06-09T06:14:49.110Z</lastmod>
<lastmod>2025-06-10T04:42:42.438Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html</loc>
<lastmod>2025-06-09T06:14:49.407Z</lastmod>
<lastmod>2025-06-10T04:42:42.741Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_tokenizers.html</loc>
<lastmod>2025-06-09T06:14:48.816Z</lastmod>
<lastmod>2025-06-10T04:42:42.143Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/kernels.quantize.html</loc>
<lastmod>2025-06-09T06:14:49.583Z</lastmod>
<lastmod>2025-06-10T04:42:42.918Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html</loc>
<lastmod>2025-06-09T06:14:50.192Z</lastmod>
<lastmod>2025-06-10T04:42:43.523Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.trl.html</loc>
<lastmod>2025-06-09T06:14:49.906Z</lastmod>
<lastmod>2025-06-10T04:42:43.244Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.config.html</loc>
<lastmod>2025-06-09T06:14:49.864Z</lastmod>
<lastmod>2025-06-10T04:42:43.202Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html</loc>
<lastmod>2025-06-09T06:14:49.687Z</lastmod>
<lastmod>2025-06-10T04:42:43.024Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.checks.html</loc>
<lastmod>2025-06-09T06:14:49.044Z</lastmod>
<lastmod>2025-06-10T04:42:42.372Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.chat.messages.html</loc>
<lastmod>2025-06-09T06:14:48.953Z</lastmod>
<lastmod>2025-06-10T04:42:42.282Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/loaders.patch_manager.html</loc>
<lastmod>2025-06-09T06:14:49.262Z</lastmod>
<lastmod>2025-06-10T04:42:42.590Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html</loc>
<lastmod>2025-06-09T06:14:49.634Z</lastmod>
<lastmod>2025-06-10T04:42:42.970Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.utils.html</loc>
<lastmod>2025-06-09T06:14:49.939Z</lastmod>
<lastmod>2025-06-10T04:42:43.277Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/integrations.base.html</loc>
<lastmod>2025-06-09T06:14:50.058Z</lastmod>
<lastmod>2025-06-10T04:42:43.397Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html</loc>
<lastmod>2025-06-09T06:14:50.173Z</lastmod>
<lastmod>2025-06-10T04:42:43.508Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html</loc>
<lastmod>2025-06-09T06:14:49.374Z</lastmod>
<lastmod>2025-06-10T04:42:42.708Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.collators.mamba.html</loc>
<lastmod>2025-06-09T06:14:50.125Z</lastmod>
<lastmod>2025-06-10T04:42:43.463Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.model.html</loc>
<lastmod>2025-06-09T06:14:49.871Z</lastmod>
<lastmod>2025-06-10T04:42:43.209Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.training.html</loc>
<lastmod>2025-06-09T06:14:49.876Z</lastmod>
<lastmod>2025-06-10T04:42:43.214Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html</loc>
<lastmod>2025-06-09T06:14:49.440Z</lastmod>
<lastmod>2025-06-10T04:42:42.774Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.utils.html</loc>
<lastmod>2025-06-09T06:14:49.229Z</lastmod>
<lastmod>2025-06-10T04:42:42.558Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html</loc>
<lastmod>2025-06-09T06:14:49.269Z</lastmod>
<lastmod>2025-06-10T04:42:42.597Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
<lastmod>2025-06-09T06:14:49.096Z</lastmod>
<lastmod>2025-06-10T04:42:42.424Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset_loading.html</loc>
<lastmod>2025-06-09T06:14:21.510Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/amd_hpc.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.207Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/TODO.html</loc>
<lastmod>2025-06-09T06:14:21.508Z</lastmod>
<lastmod>2025-06-10T04:42:14.206Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/debugging.html</loc>
<lastmod>2025-06-09T06:14:21.510Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/multi-gpu.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.utils.html</loc>
<lastmod>2025-06-09T06:14:49.142Z</lastmod>
<lastmod>2025-06-10T04:42:42.470Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.freeze.html</loc>
<lastmod>2025-06-09T06:14:49.757Z</lastmod>
<lastmod>2025-06-10T04:42:43.095Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/common.architectures.html</loc>
<lastmod>2025-06-09T06:14:50.082Z</lastmod>
<lastmod>2025-06-10T04:42:43.420Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schedulers.html</loc>
<lastmod>2025-06-09T06:14:49.798Z</lastmod>
<lastmod>2025-06-10T04:42:43.137Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.collators.core.html</loc>
<lastmod>2025-06-09T06:14:50.103Z</lastmod>
<lastmod>2025-06-10T04:42:43.441Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html</loc>
<lastmod>2025-06-09T06:14:49.911Z</lastmod>
<lastmod>2025-06-10T04:42:43.249Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.distributed.html</loc>
<lastmod>2025-06-09T06:14:49.818Z</lastmod>
<lastmod>2025-06-10T04:42:43.156Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html</loc>
<lastmod>2025-06-09T06:14:49.894Z</lastmod>
<lastmod>2025-06-10T04:42:43.232Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html</loc>
<lastmod>2025-06-09T06:14:49.449Z</lastmod>
<lastmod>2025-06-10T04:42:42.784Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.utils.html</loc>
<lastmod>2025-06-09T06:14:49.667Z</lastmod>
<lastmod>2025-06-10T04:42:43.004Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html</loc>
<lastmod>2025-06-09T06:14:49.923Z</lastmod>
<lastmod>2025-06-10T04:42:43.261Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html</loc>
<lastmod>2025-06-09T06:14:49.272Z</lastmod>
<lastmod>2025-06-10T04:42:42.601Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html</loc>
<lastmod>2025-06-09T06:14:50.077Z</lastmod>
<lastmod>2025-06-10T04:42:43.416Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/loaders.processor.html</loc>
<lastmod>2025-06-09T06:14:49.248Z</lastmod>
<lastmod>2025-06-10T04:42:42.577Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.trl.html</loc>
<lastmod>2025-06-09T06:14:49.189Z</lastmod>
<lastmod>2025-06-10T04:42:42.518Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/loaders.constants.html</loc>
<lastmod>2025-06-09T06:14:49.263Z</lastmod>
<lastmod>2025-06-10T04:42:42.592Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html</loc>
<lastmod>2025-06-09T06:14:49.609Z</lastmod>
<lastmod>2025-06-10T04:42:42.945Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.args.html</loc>
<lastmod>2025-06-09T06:14:49.037Z</lastmod>
<lastmod>2025-06-10T04:42:42.366Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.builders.causal.html</loc>
<lastmod>2025-06-09T06:14:48.836Z</lastmod>
<lastmod>2025-06-10T04:42:42.163Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html</loc>
<lastmod>2025-06-09T06:14:49.380Z</lastmod>
<lastmod>2025-06-10T04:42:42.714Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html</loc>
<lastmod>2025-06-09T06:14:48.956Z</lastmod>
<lastmod>2025-06-10T04:42:42.285Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.train.html</loc>
<lastmod>2025-06-09T06:14:49.010Z</lastmod>
<lastmod>2025-06-10T04:42:42.338Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/convert.html</loc>
<lastmod>2025-06-09T06:14:48.775Z</lastmod>
<lastmod>2025-06-10T04:42:42.102Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html</loc>
<lastmod>2025-06-09T06:14:49.829Z</lastmod>
<lastmod>2025-06-10T04:42:43.167Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html</loc>
<lastmod>2025-06-09T06:14:49.401Z</lastmod>
<lastmod>2025-06-10T04:42:42.735Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html</loc>
<lastmod>2025-06-09T06:14:50.070Z</lastmod>
<lastmod>2025-06-10T04:42:43.409Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.qat.html</loc>
<lastmod>2025-06-09T06:14:50.206Z</lastmod>
<lastmod>2025-06-10T04:42:43.533Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html</loc>
<lastmod>2025-06-09T06:14:50.188Z</lastmod>
<lastmod>2025-06-10T04:42:43.520Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/loaders.tokenizer.html</loc>
<lastmod>2025-06-09T06:14:49.246Z</lastmod>
<lastmod>2025-06-10T04:42:42.575Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.main.html</loc>
<lastmod>2025-06-09T06:14:49.002Z</lastmod>
<lastmod>2025-06-10T04:42:42.330Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html</loc>
<lastmod>2025-06-09T06:14:49.689Z</lastmod>
<lastmod>2025-06-10T04:42:43.026Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.evaluate.html</loc>
<lastmod>2025-06-09T06:14:49.018Z</lastmod>
<lastmod>2025-06-10T04:42:42.347Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.bench.html</loc>
<lastmod>2025-06-09T06:14:49.750Z</lastmod>
<lastmod>2025-06-10T04:42:43.088Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html</loc>
<lastmod>2025-06-09T06:14:49.686Z</lastmod>
<lastmod>2025-06-10T04:42:43.023Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html</loc>
<lastmod>2025-06-09T06:14:49.670Z</lastmod>
<lastmod>2025-06-10T04:42:43.007Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html</loc>
<lastmod>2025-06-09T06:14:49.625Z</lastmod>
<lastmod>2025-06-10T04:42:42.961Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html</loc>
<lastmod>2025-06-09T06:14:49.301Z</lastmod>
<lastmod>2025-06-10T04:42:42.630Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html</loc>
<lastmod>2025-06-09T06:14:50.063Z</lastmod>
<lastmod>2025-06-10T04:42:43.401Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html</loc>
<lastmod>2025-06-09T06:14:50.197Z</lastmod>
<lastmod>2025-06-10T04:42:43.527Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html</loc>
<lastmod>2025-06-09T06:14:49.626Z</lastmod>
<lastmod>2025-06-10T04:42:42.962Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html</loc>
<lastmod>2025-06-09T06:14:50.129Z</lastmod>
<lastmod>2025-06-10T04:42:43.468Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.tokenization.html</loc>
<lastmod>2025-06-09T06:14:49.726Z</lastmod>
<lastmod>2025-06-10T04:42:43.063Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html</loc>
<lastmod>2025-06-09T06:14:49.391Z</lastmod>
<lastmod>2025-06-10T04:42:42.725Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.collators.batching.html</loc>
<lastmod>2025-06-09T06:14:50.121Z</lastmod>
<lastmod>2025-06-10T04:42:43.460Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.base.html</loc>
<lastmod>2025-06-09T06:14:49.173Z</lastmod>
<lastmod>2025-06-10T04:42:42.501Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html</loc>
<lastmod>2025-06-09T06:14:49.215Z</lastmod>
<lastmod>2025-06-10T04:42:42.544Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html</loc>
<lastmod>2025-06-09T06:14:49.427Z</lastmod>
<lastmod>2025-06-10T04:42:42.762Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.quantization.html</loc>
<lastmod>2025-06-09T06:14:49.852Z</lastmod>
<lastmod>2025-06-10T04:42:43.191Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html</loc>
<lastmod>2025-06-09T06:14:49.368Z</lastmod>
<lastmod>2025-06-10T04:42:42.702Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.quantize.html</loc>
<lastmod>2025-06-09T06:14:49.163Z</lastmod>
<lastmod>2025-06-10T04:42:42.491Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html</loc>
<lastmod>2025-06-09T06:14:49.336Z</lastmod>
<lastmod>2025-06-10T04:42:42.669Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.vllm_serve.html</loc>
<lastmod>2025-06-09T06:14:49.148Z</lastmod>
<lastmod>2025-06-10T04:42:42.477Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html</loc>
<lastmod>2025-06-09T06:14:49.334Z</lastmod>
<lastmod>2025-06-10T04:42:42.668Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
<lastmod>2025-06-09T06:14:49.473Z</lastmod>
<lastmod>2025-06-10T04:42:42.808Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.dict.html</loc>
<lastmod>2025-06-09T06:14:49.821Z</lastmod>
<lastmod>2025-06-10T04:42:43.159Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html</loc>
<lastmod>2025-06-09T06:14:49.430Z</lastmod>
<lastmod>2025-06-10T04:42:42.764Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html</loc>
<lastmod>2025-06-09T06:14:49.611Z</lastmod>
<lastmod>2025-06-10T04:42:42.946Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.lora.html</loc>
<lastmod>2025-06-09T06:14:49.741Z</lastmod>
<lastmod>2025-06-10T04:42:43.078Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html</loc>
<lastmod>2025-06-09T06:14:49.693Z</lastmod>
<lastmod>2025-06-10T04:42:43.031Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.trainer.html</loc>
<lastmod>2025-06-09T06:14:49.774Z</lastmod>
<lastmod>2025-06-10T04:42:43.112Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html</loc>
<lastmod>2025-06-09T06:14:49.394Z</lastmod>
<lastmod>2025-06-10T04:42:42.729Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html</loc>
<lastmod>2025-06-09T06:14:49.405Z</lastmod>
<lastmod>2025-06-10T04:42:42.740Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html</loc>
<lastmod>2025-06-09T06:14:49.659Z</lastmod>
<lastmod>2025-06-10T04:42:42.996Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.enums.html</loc>
<lastmod>2025-06-09T06:14:49.934Z</lastmod>
<lastmod>2025-06-10T04:42:43.272Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.config.html</loc>
<lastmod>2025-06-09T06:14:49.061Z</lastmod>
<lastmod>2025-06-10T04:42:42.390Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html</loc>
<lastmod>2025-06-09T06:14:49.719Z</lastmod>
<lastmod>2025-06-10T04:42:43.056Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
<lastmod>2025-06-09T06:14:49.676Z</lastmod>
<lastmod>2025-06-10T04:42:43.013Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/kernels.lora.html</loc>
<lastmod>2025-06-09T06:14:49.555Z</lastmod>
<lastmod>2025-06-10T04:42:42.890Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.base.html</loc>
<lastmod>2025-06-09T06:14:49.303Z</lastmod>
<lastmod>2025-06-10T04:42:42.632Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/core.trainers.relora.html</loc>
<lastmod>2025-06-09T06:14:49.198Z</lastmod>
<lastmod>2025-06-10T04:42:42.527Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/loaders.model.html</loc>
<lastmod>2025-06-09T06:14:49.238Z</lastmod>
<lastmod>2025-06-10T04:42:42.567Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html</loc>
<lastmod>2025-06-09T06:14:50.181Z</lastmod>
<lastmod>2025-06-10T04:42:43.515Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/api/cli.inference.html</loc>
<lastmod>2025-06-09T06:14:49.075Z</lastmod>
<lastmod>2025-06-10T04:42:42.404Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/batch_vs_grad.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.207Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/sequence_parallelism.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/getting-started.html</loc>
<lastmod>2025-06-09T06:14:21.510Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/torchao.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset_preprocessing.html</loc>
<lastmod>2025-06-09T06:14:21.510Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/docker.html</loc>
<lastmod>2025-06-09T06:14:21.510Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/ray-integration.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/dataset-formats/index.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.207Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/multimodal.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/reward_modelling.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/faq.html</loc>
<lastmod>2025-06-09T06:14:21.510Z</lastmod>
<lastmod>2025-06-10T04:42:14.208Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/installation.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/unsloth.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/config.html</loc>
<lastmod>2025-06-09T06:14:21.509Z</lastmod>
<lastmod>2025-06-10T04:42:14.207Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/docs/inference.html</loc>
<lastmod>2025-06-09T06:14:21.513Z</lastmod>
<lastmod>2025-06-10T04:42:14.211Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html</loc>
<lastmod>2025-06-09T06:14:21.533Z</lastmod>
<lastmod>2025-06-10T04:42:14.228Z</lastmod>
</url>
<url>
<loc>https://docs.axolotl.ai/index.html</loc>
<lastmod>2025-06-09T06:14:21.528Z</lastmod>
<lastmod>2025-06-10T04:42:14.224Z</lastmod>
</url>
</urlset>