Built site for gh-pages

2025-03-23 15:11:04 +00:00
parent 8dc7909473
commit 0fbd202764
9 changed files with 2301 additions and 1122 deletions
--- a/.nojekyll
+++ b/.nojekyll
@@ -1 +1 @@
-60422756
+bef07254
--- a/docs/api/core.training_args.html
+++ b/docs/api/core.training_args.html
@@ -545,8 +545,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <span id="cb1-43"><a href="#cb1-43" aria-hidden="true" tabindex="-1"></a>    kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb1-44"><a href="#cb1-44" aria-hidden="true" tabindex="-1"></a>    kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb1-45"><a href="#cb1-45" aria-hidden="true" tabindex="-1"></a>    sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
-<span id="cb1-46"><a href="#cb1-46" aria-hidden="true" tabindex="-1"></a>    simpo_gamma<span class="op">=</span><span class="va">None</span>,</span>
-<span id="cb1-47"><a href="#cb1-47" 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="cb1-46"><a href="#cb1-46" aria-hidden="true" tabindex="-1"></a>    image_size<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb1-47"><a href="#cb1-47" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb1-48"><a href="#cb1-48" aria-hidden="true" tabindex="-1"></a>    simpo_gamma<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb1-49"><a href="#cb1-49" 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>CPO config for CPO training</p>
 </section>
 <section id="axolotl.core.training_args.AxolotlKTOConfig" class="level3">
@@ -596,7 +598,9 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <span id="cb2-43"><a href="#cb2-43" aria-hidden="true" tabindex="-1"></a>    kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb2-44"><a href="#cb2-44" aria-hidden="true" tabindex="-1"></a>    kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb2-45"><a href="#cb2-45" aria-hidden="true" tabindex="-1"></a>    sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
-<span id="cb2-46"><a href="#cb2-46" 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="cb2-46"><a href="#cb2-46" aria-hidden="true" tabindex="-1"></a>    image_size<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb2-47"><a href="#cb2-47" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb2-48"><a href="#cb2-48" 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>KTO config for KTO training</p>
 </section>
 <section id="axolotl.core.training_args.AxolotlORPOConfig" class="level3">
@@ -646,7 +650,9 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <span id="cb3-43"><a href="#cb3-43" aria-hidden="true" tabindex="-1"></a>    kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb3-44"><a href="#cb3-44" aria-hidden="true" tabindex="-1"></a>    kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb3-45"><a href="#cb3-45" aria-hidden="true" tabindex="-1"></a>    sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
-<span id="cb3-46"><a href="#cb3-46" 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="cb3-46"><a href="#cb3-46" aria-hidden="true" tabindex="-1"></a>    image_size<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb3-47"><a href="#cb3-47" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb3-48"><a href="#cb3-48" 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>ORPO config for ORPO training</p>
 </section>
 <section id="axolotl.core.training_args.AxolotlPRMConfig" class="level3">
@@ -696,7 +702,9 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <span id="cb4-43"><a href="#cb4-43" aria-hidden="true" tabindex="-1"></a>    kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb4-44"><a href="#cb4-44" aria-hidden="true" tabindex="-1"></a>    kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb4-45"><a href="#cb4-45" aria-hidden="true" tabindex="-1"></a>    sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
-<span id="cb4-46"><a href="#cb4-46" 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="cb4-46"><a href="#cb4-46" aria-hidden="true" tabindex="-1"></a>    image_size<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb4-47"><a href="#cb4-47" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb4-48"><a href="#cb4-48" 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>PRM config for PRM training</p>
 </section>
 <section id="axolotl.core.training_args.AxolotlRewardConfig" class="level3">
@@ -746,7 +754,9 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <span id="cb5-43"><a href="#cb5-43" aria-hidden="true" tabindex="-1"></a>    kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb5-44"><a href="#cb5-44" aria-hidden="true" tabindex="-1"></a>    kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb5-45"><a href="#cb5-45" aria-hidden="true" tabindex="-1"></a>    sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
-<span id="cb5-46"><a href="#cb5-46" 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="cb5-46"><a href="#cb5-46" aria-hidden="true" tabindex="-1"></a>    image_size<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb5-47"><a href="#cb5-47" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb5-48"><a href="#cb5-48" 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>Reward config for Reward training</p>
 </section>
 <section id="axolotl.core.training_args.AxolotlTrainingArguments" class="level3">
@@ -796,7 +806,9 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <span id="cb6-43"><a href="#cb6-43" aria-hidden="true" tabindex="-1"></a>    kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb6-44"><a href="#cb6-44" aria-hidden="true" tabindex="-1"></a>    kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb6-45"><a href="#cb6-45" aria-hidden="true" tabindex="-1"></a>    sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
-<span id="cb6-46"><a href="#cb6-46" 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="cb6-46"><a href="#cb6-46" aria-hidden="true" tabindex="-1"></a>    image_size<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb6-47"><a href="#cb6-47" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb6-48"><a href="#cb6-48" 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>Training arguments for Causal trainer</p>
 <p>This code is duplicated due to HF TrainingArguments not setting output_dir with a
 default value so it can’t be used as a mixin.</p>
@@ -848,7 +860,9 @@ default value so it can’t be used as a mixin.</p>
 <span id="cb7-43"><a href="#cb7-43" aria-hidden="true" tabindex="-1"></a>    kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb7-44"><a href="#cb7-44" aria-hidden="true" tabindex="-1"></a>    kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
 <span id="cb7-45"><a href="#cb7-45" aria-hidden="true" tabindex="-1"></a>    sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
-<span id="cb7-46"><a href="#cb7-46" 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="cb7-46"><a href="#cb7-46" aria-hidden="true" tabindex="-1"></a>    image_size<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb7-47"><a href="#cb7-47" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb7-48"><a href="#cb7-48" 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>Mixin class for the Axolotl training args.</p>


--- a/docs/api/index.html
+++ b/docs/api/index.html
@@ -891,14 +891,18 @@ ul.task-list li input[type="checkbox"] {
 <td>Pydantic models for TRL trainer configuration</td>
 </tr>
 <tr class="odd">
+<td><a href="../../docs/api/utils.schemas.multimodal.html#axolotl.utils.schemas.multimodal">utils.schemas.multimodal</a></td>
+<td>Pydantic models for multimodal-related configuration</td>
+</tr>
+<tr class="even">
 <td><a href="../../docs/api/utils.schemas.integrations.html#axolotl.utils.schemas.integrations">utils.schemas.integrations</a></td>
 <td>Pydantic models for Axolotl integrations</td>
 </tr>
-<tr class="even">
+<tr class="odd">
 <td><a href="../../docs/api/utils.schemas.enums.html#axolotl.utils.schemas.enums">utils.schemas.enums</a></td>
 <td>Enums for Axolotl input config</td>
 </tr>
-<tr class="odd">
+<tr class="even">
 <td><a href="../../docs/api/utils.schemas.utils.html#axolotl.utils.schemas.utils">utils.schemas.utils</a></td>
 <td>Utilities for Axolotl Pydantic models</td>
 </tr>
--- a/docs/api/utils.collators.mm_chat.html
+++ b/docs/api/utils.collators.mm_chat.html
@@ -473,14 +473,12 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <div class="sourceCode" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a>utils.collators.mm_chat.MultiModalChatDataCollator(</span>
 <span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a>    <span class="va">self</span>,</span>
 <span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a>    tokenizer,</span>
-<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a>    processor,</span>
-<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a>    return_tensors<span class="op">=</span><span class="st">'pt'</span>,</span>
-<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a>    chat_template<span class="op">=</span><span class="va">None</span>,</span>
-<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a>    packing<span class="op">=</span><span class="va">False</span>,</span>
-<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a>    max_images<span class="op">=-</span><span class="dv">1</span>,</span>
-<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a>    padding<span class="op">=</span><span class="va">True</span>,</span>
-<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a>    pad_to_multiple_of<span class="op">=</span><span class="va">None</span>,</span>
-<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a>    processing_strategy,</span>
+<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a>    packing<span class="op">=</span><span class="va">False</span>,</span>
+<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a>    return_tensors<span class="op">=</span><span class="st">'pt'</span>,</span>
+<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a>    padding<span class="op">=</span><span class="va">True</span>,</span>
+<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a>    pad_to_multiple_of<span class="op">=</span><span class="va">None</span>,</span>
+<span id="cb1-9"><a href="#cb1-9" 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>Collator for multi-modal chat messages</p>


--- a/docs/api/utils.schemas.multimodal.html
+++ b/docs/api/utils.schemas.multimodal.html
@@ -0,0 +1,928 @@
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
+
+<meta charset="utf-8">
+<meta name="generator" content="quarto-1.6.42">
+
+<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
+
+
+<title>utils.schemas.multimodal – Axolotl</title>
+<style>
+code{white-space: pre-wrap;}
+span.smallcaps{font-variant: small-caps;}
+div.columns{display: flex; gap: min(4vw, 1.5em);}
+div.column{flex: auto; overflow-x: auto;}
+div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
+ul.task-list{list-style: none;}
+ul.task-list li input[type="checkbox"] {
+  width: 0.8em;
+  margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */ 
+  vertical-align: middle;
+}
+/* CSS for syntax highlighting */
+pre > code.sourceCode { white-space: pre; position: relative; }
+pre > code.sourceCode > span { line-height: 1.25; }
+pre > code.sourceCode > span:empty { height: 1.2em; }
+.sourceCode { overflow: visible; }
+code.sourceCode > span { color: inherit; text-decoration: inherit; }
+div.sourceCode { margin: 1em 0; }
+pre.sourceCode { margin: 0; }
+@media screen {
+div.sourceCode { overflow: auto; }
+}
+@media print {
+pre > code.sourceCode { white-space: pre-wrap; }
+pre > code.sourceCode > span { display: inline-block; text-indent: -5em; padding-left: 5em; }
+}
+pre.numberSource code
+  { counter-reset: source-line 0; }
+pre.numberSource code > span
+  { position: relative; left: -4em; counter-increment: source-line; }
+pre.numberSource code > span > a:first-child::before
+  { content: counter(source-line);
+    position: relative; left: -1em; text-align: right; vertical-align: baseline;
+    border: none; display: inline-block;
+    -webkit-touch-callout: none; -webkit-user-select: none;
+    -khtml-user-select: none; -moz-user-select: none;
+    -ms-user-select: none; user-select: none;
+    padding: 0 4px; width: 4em;
+  }
+pre.numberSource { margin-left: 3em;  padding-left: 4px; }
+div.sourceCode
+  {   }
+@media screen {
+pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
+}
+</style>
+
+
+<script src="../../site_libs/quarto-nav/quarto-nav.js"></script>
+<script src="../../site_libs/clipboard/clipboard.min.js"></script>
+<script src="../../site_libs/quarto-search/autocomplete.umd.js"></script>
+<script src="../../site_libs/quarto-search/fuse.min.js"></script>
+<script src="../../site_libs/quarto-search/quarto-search.js"></script>
+<meta name="quarto:offset" content="../../">
+<link href="../../favicon.jpg" rel="icon" type="image/jpeg">
+<script src="../../site_libs/quarto-html/quarto.js"></script>
+<script src="../../site_libs/quarto-html/popper.min.js"></script>
+<script src="../../site_libs/quarto-html/tippy.umd.min.js"></script>
+<script src="../../site_libs/quarto-html/anchor.min.js"></script>
+<link href="../../site_libs/quarto-html/tippy.css" rel="stylesheet">
+<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.css" rel="stylesheet" id="quarto-text-highlighting-styles">
+<script src="../../site_libs/bootstrap/bootstrap.min.js"></script>
+<link href="../../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
+<link href="../../site_libs/bootstrap/bootstrap-71f806479865a0e7fd52beea5cc266f1.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
+<script id="quarto-search-options" type="application/json">{
+  "location": "navbar",
+  "copy-button": false,
+  "collapse-after": 3,
+  "panel-placement": "end",
+  "type": "overlay",
+  "limit": 50,
+  "keyboard-shortcut": [
+    "f",
+    "/",
+    "s"
+  ],
+  "show-item-context": false,
+  "language": {
+    "search-no-results-text": "No results",
+    "search-matching-documents-text": "matching documents",
+    "search-copy-link-title": "Copy link to search",
+    "search-hide-matches-text": "Hide additional matches",
+    "search-more-match-text": "more match in this document",
+    "search-more-matches-text": "more matches in this document",
+    "search-clear-button-title": "Clear",
+    "search-text-placeholder": "",
+    "search-detached-cancel-button-title": "Cancel",
+    "search-submit-button-title": "Submit",
+    "search-label": "Search"
+  }
+}</script>
+
+
+<link rel="stylesheet" href="../../styles.css">
+</head>
+
+<body class="nav-sidebar docked nav-fixed">
+
+<div id="quarto-search-results"></div>
+  <header id="quarto-header" class="headroom fixed-top">
+    <nav class="navbar navbar-expand " data-bs-theme="dark">
+      <div class="navbar-container container-fluid">
+      <div class="navbar-brand-container mx-auto">
+    <a href="../../index.html" class="navbar-brand navbar-brand-logo">
+    <img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
+    </a>
+  </div>
+        <div class="quarto-navbar-tools tools-wide tools-end">
+    <a href="https://twitter.com/axolotl_ai" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-twitter"></i></a>
+    <a href="https://github.com/axolotl-ai-cloud/axolotl/" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-github"></i></a>
+    <a href="https://discord.gg/7m9sfhzaf3" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-discord"></i></a>
+</div>
+          <div id="quarto-search" class="" title="Search"></div>
+      </div> <!-- /container-fluid -->
+    </nav>
+  <nav class="quarto-secondary-nav">
+    <div class="container-fluid d-flex">
+      <button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
+        <i class="bi bi-layout-text-sidebar-reverse"></i>
+      </button>
+        <nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"></ol></nav>
+        <a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">      
+        </a>
+    </div>
+  </nav>
+</header>
+<!-- content -->
+<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article page-navbar">
+<!-- sidebar -->
+  <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto">
+    <div class="sidebar-menu-container"> 
+    <ul class="list-unstyled mt-1">
+        <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../index.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Home</span></a>
+  </div>
+</li>
+        <li class="sidebar-item sidebar-item-section">
+      <div class="sidebar-item-container"> 
+            <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true">
+ <span class="menu-text">Getting Started</span></a>
+          <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true" aria-label="Toggle section">
+            <i class="bi bi-chevron-right ms-2"></i>
+          </a> 
+      </div>
+      <ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show">  
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/getting-started.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Quickstart</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/installation.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Installation</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/inference.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Inference and Merging</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Command Line Interface (CLI)</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/config.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Config Reference</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/api" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">API Reference</span></a>
+  </div>
+</li>
+      </ul>
+  </li>
+        <li class="sidebar-item sidebar-item-section">
+      <div class="sidebar-item-container"> 
+            <a href="../../docs/dataset-formats/index.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Dataset Formats</span></a>
+          <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true" aria-label="Toggle section">
+            <i class="bi bi-chevron-right ms-2"></i>
+          </a> 
+      </div>
+      <ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth1 show">  
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/dataset-formats/pretraining.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Pre-training</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/dataset-formats/inst_tune.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Instruction Tuning</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/dataset-formats/conversation.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Conversation</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/dataset-formats/stepwise_supervised.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Stepwise Supervised Format</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/dataset-formats/template_free.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Template-Free</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/dataset-formats/tokenized.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Custom Pre-Tokenized Dataset</span></a>
+  </div>
+</li>
+      </ul>
+  </li>
+        <li class="sidebar-item sidebar-item-section">
+      <div class="sidebar-item-container"> 
+            <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true">
+ <span class="menu-text">Deployments</span></a>
+          <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
+            <i class="bi bi-chevron-right ms-2"></i>
+          </a> 
+      </div>
+      <ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">  
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/docker.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Docker</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/multi-gpu.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Multi-GPU</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/multi-node.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Multi Node</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/ray-integration.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Ray Train</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/amd_hpc.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">AMD GPUs on HPC Systems</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/mac.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Mac M-series</span></a>
+  </div>
+</li>
+      </ul>
+  </li>
+        <li class="sidebar-item sidebar-item-section">
+      <div class="sidebar-item-container"> 
+            <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true">
+ <span class="menu-text">How To Guides</span></a>
+          <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true" aria-label="Toggle section">
+            <i class="bi bi-chevron-right ms-2"></i>
+          </a> 
+      </div>
+      <ul id="quarto-sidebar-section-4" class="collapse list-unstyled sidebar-section depth1 show">  
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/multimodal.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">MultiModal / Vision Language Models (BETA)</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/rlhf.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">RLHF (Beta)</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/reward_modelling.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Reward Modelling</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/lr_groups.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Learning Rate Groups</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/lora_optims.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">LoRA Optimizations</span></a>
+  </div>
+</li>
+      </ul>
+  </li>
+        <li class="sidebar-item sidebar-item-section">
+      <div class="sidebar-item-container"> 
+            <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-5" role="navigation" aria-expanded="true">
+ <span class="menu-text">Core Concepts</span></a>
+          <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-5" role="navigation" aria-expanded="true" aria-label="Toggle section">
+            <i class="bi bi-chevron-right ms-2"></i>
+          </a> 
+      </div>
+      <ul id="quarto-sidebar-section-5" class="collapse list-unstyled sidebar-section depth1 show">  
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/batch_vs_grad.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Batch size vs Gradient accumulation</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/dataset_preprocessing.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Dataset Preprocessing</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/multipack.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Multipack (Sample Packing)</span></a>
+  </div>
+</li>
+      </ul>
+  </li>
+        <li class="sidebar-item sidebar-item-section">
+      <div class="sidebar-item-container"> 
+            <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-6" role="navigation" aria-expanded="true">
+ <span class="menu-text">Advanced Features</span></a>
+          <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-6" role="navigation" aria-expanded="true" aria-label="Toggle section">
+            <i class="bi bi-chevron-right ms-2"></i>
+          </a> 
+      </div>
+      <ul id="quarto-sidebar-section-6" class="collapse list-unstyled sidebar-section depth1 show">  
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">FDSP + QLoRA</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/unsloth.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Unsloth</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/torchao.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">PyTorch ao</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/custom_integrations.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Custom Integrations</span></a>
+  </div>
+</li>
+      </ul>
+  </li>
+        <li class="sidebar-item sidebar-item-section">
+      <div class="sidebar-item-container"> 
+            <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-7" role="navigation" aria-expanded="true">
+ <span class="menu-text">Troubleshooting</span></a>
+          <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-7" role="navigation" aria-expanded="true" aria-label="Toggle section">
+            <i class="bi bi-chevron-right ms-2"></i>
+          </a> 
+      </div>
+      <ul id="quarto-sidebar-section-7" class="collapse list-unstyled sidebar-section depth1 show">  
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/faq.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">FAQ</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/debugging.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">Debugging</span></a>
+  </div>
+</li>
+          <li class="sidebar-item">
+  <div class="sidebar-item-container"> 
+  <a href="../../docs/nccl.html" class="sidebar-item-text sidebar-link">
+ <span class="menu-text">NCCL</span></a>
+  </div>
+</li>
+      </ul>
+  </li>
+    </ul>
+    </div>
+</nav>
+<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
+<!-- margin-sidebar -->
+    <div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
+        <nav id="TOC" role="doc-toc" class="toc-active">
+    <h2 id="toc-title">On this page</h2>
+   
+  <ul>
+  <li><a href="#axolotl.utils.schemas.multimodal" id="toc-axolotl.utils.schemas.multimodal" class="nav-link active" data-scroll-target="#axolotl.utils.schemas.multimodal">utils.schemas.multimodal</a>
+  <ul class="collapse">
+  <li><a href="#classes" id="toc-classes" class="nav-link" data-scroll-target="#classes">Classes</a>
+  <ul class="collapse">
+  <li><a href="#axolotl.utils.schemas.multimodal.MultiModalConfig" id="toc-axolotl.utils.schemas.multimodal.MultiModalConfig" class="nav-link" data-scroll-target="#axolotl.utils.schemas.multimodal.MultiModalConfig">MultiModalConfig</a></li>
+  </ul></li>
+  </ul></li>
+  </ul>
+</nav>
+    </div>
+<!-- main -->
+<main class="content" id="quarto-document-content"><header id="title-block-header" class="quarto-title-block"></header>
+
+
+
+
+<section id="axolotl.utils.schemas.multimodal" class="level1">
+<h1>utils.schemas.multimodal</h1>
+<p><code>utils.schemas.multimodal</code></p>
+<p>Pydantic models for multimodal-related configuration</p>
+<section id="classes" class="level2">
+<h2 class="anchored" data-anchor-id="classes">Classes</h2>
+<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.utils.schemas.multimodal.MultiModalConfig">MultiModalConfig</a></td>
+<td>Multi-modal configuration subset</td>
+</tr>
+</tbody>
+</table>
+<section id="axolotl.utils.schemas.multimodal.MultiModalConfig" class="level3">
+<h3 class="anchored" data-anchor-id="axolotl.utils.schemas.multimodal.MultiModalConfig">MultiModalConfig</h3>
+<div class="sourceCode" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a>utils.schemas.multimodal.MultiModalConfig()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<p>Multi-modal configuration subset</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.utils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm">convert_image_resize_algorithm</a></td>
+<td>Convert the image resize algorithm to a PIL.Image.Resampling enum.</td>
+</tr>
+</tbody>
+</table>
+<section id="axolotl.utils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm" class="level5">
+<h5 class="anchored" data-anchor-id="axolotl.utils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm">convert_image_resize_algorithm</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>utils.schemas.multimodal.MultiModalConfig.convert_image_resize_algorithm(</span>
+<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a>    image_resize_algorithm,</span>
+<span id="cb2-3"><a href="#cb2-3" 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>Convert the image resize algorithm to a PIL.Image.Resampling enum.</p>
+
+
+</section>
+</section>
+</section>
+</section>
+</section>
+
+</main> <!-- /main -->
+<script id="quarto-html-after-body" type="application/javascript">
+window.document.addEventListener("DOMContentLoaded", function (event) {
+  const toggleBodyColorMode = (bsSheetEl) => {
+    const mode = bsSheetEl.getAttribute("data-mode");
+    const bodyEl = window.document.querySelector("body");
+    if (mode === "dark") {
+      bodyEl.classList.add("quarto-dark");
+      bodyEl.classList.remove("quarto-light");
+    } else {
+      bodyEl.classList.add("quarto-light");
+      bodyEl.classList.remove("quarto-dark");
+    }
+  }
+  const toggleBodyColorPrimary = () => {
+    const bsSheetEl = window.document.querySelector("link#quarto-bootstrap");
+    if (bsSheetEl) {
+      toggleBodyColorMode(bsSheetEl);
+    }
+  }
+  toggleBodyColorPrimary();  
+  const icon = "";
+  const anchorJS = new window.AnchorJS();
+  anchorJS.options = {
+    placement: 'right',
+    icon: icon
+  };
+  anchorJS.add('.anchored');
+  const isCodeAnnotation = (el) => {
+    for (const clz of el.classList) {
+      if (clz.startsWith('code-annotation-')) {                     
+        return true;
+      }
+    }
+    return false;
+  }
+  const onCopySuccess = function(e) {
+    // button target
+    const button = e.trigger;
+    // don't keep focus
+    button.blur();
+    // flash "checked"
+    button.classList.add('code-copy-button-checked');
+    var currentTitle = button.getAttribute("title");
+    button.setAttribute("title", "Copied!");
+    let tooltip;
+    if (window.bootstrap) {
+      button.setAttribute("data-bs-toggle", "tooltip");
+      button.setAttribute("data-bs-placement", "left");
+      button.setAttribute("data-bs-title", "Copied!");
+      tooltip = new bootstrap.Tooltip(button, 
+        { trigger: "manual", 
+          customClass: "code-copy-button-tooltip",
+          offset: [0, -8]});
+      tooltip.show();    
+    }
+    setTimeout(function() {
+      if (tooltip) {
+        tooltip.hide();
+        button.removeAttribute("data-bs-title");
+        button.removeAttribute("data-bs-toggle");
+        button.removeAttribute("data-bs-placement");
+      }
+      button.setAttribute("title", currentTitle);
+      button.classList.remove('code-copy-button-checked');
+    }, 1000);
+    // clear code selection
+    e.clearSelection();
+  }
+  const getTextToCopy = function(trigger) {
+      const codeEl = trigger.previousElementSibling.cloneNode(true);
+      for (const childEl of codeEl.children) {
+        if (isCodeAnnotation(childEl)) {
+          childEl.remove();
+        }
+      }
+      return codeEl.innerText;
+  }
+  const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
+    text: getTextToCopy
+  });
+  clipboard.on('success', onCopySuccess);
+  if (window.document.getElementById('quarto-embedded-source-code-modal')) {
+    const clipboardModal = new window.ClipboardJS('.code-copy-button[data-in-quarto-modal]', {
+      text: getTextToCopy,
+      container: window.document.getElementById('quarto-embedded-source-code-modal')
+    });
+    clipboardModal.on('success', onCopySuccess);
+  }
+    var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
+    var mailtoRegex = new RegExp(/^mailto:/);
+      var filterRegex = new RegExp("https:\/\/axolotl-ai-cloud\.github\.io\/axolotl\/");
+    var isInternal = (href) => {
+        return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href);
+    }
+    // Inspect non-navigation links and adorn them if external
+ 	var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool):not(.about-link)');
+    for (var i=0; i<links.length; i++) {
+      const link = links[i];
+      if (!isInternal(link.href)) {
+        // undo the damage that might have been done by quarto-nav.js in the case of
+        // links that we want to consider external
+        if (link.dataset.originalHref !== undefined) {
+          link.href = link.dataset.originalHref;
+        }
+      }
+    }
+  function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) {
+    const config = {
+      allowHTML: true,
+      maxWidth: 500,
+      delay: 100,
+      arrow: false,
+      appendTo: function(el) {
+          return el.parentElement;
+      },
+      interactive: true,
+      interactiveBorder: 10,
+      theme: 'quarto',
+      placement: 'bottom-start',
+    };
+    if (contentFn) {
+      config.content = contentFn;
+    }
+    if (onTriggerFn) {
+      config.onTrigger = onTriggerFn;
+    }
+    if (onUntriggerFn) {
+      config.onUntrigger = onUntriggerFn;
+    }
+    window.tippy(el, config); 
+  }
+  const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
+  for (var i=0; i<noterefs.length; i++) {
+    const ref = noterefs[i];
+    tippyHover(ref, function() {
+      // use id or data attribute instead here
+      let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
+      try { href = new URL(href).hash; } catch {}
+      const id = href.replace(/^#\/?/, "");
+      const note = window.document.getElementById(id);
+      if (note) {
+        return note.innerHTML;
+      } else {
+        return "";
+      }
+    });
+  }
+  const xrefs = window.document.querySelectorAll('a.quarto-xref');
+  const processXRef = (id, note) => {
+    // Strip column container classes
+    const stripColumnClz = (el) => {
+      el.classList.remove("page-full", "page-columns");
+      if (el.children) {
+        for (const child of el.children) {
+          stripColumnClz(child);
+        }
+      }
+    }
+    stripColumnClz(note)
+    if (id === null || id.startsWith('sec-')) {
+      // Special case sections, only their first couple elements
+      const container = document.createElement("div");
+      if (note.children && note.children.length > 2) {
+        container.appendChild(note.children[0].cloneNode(true));
+        for (let i = 1; i < note.children.length; i++) {
+          const child = note.children[i];
+          if (child.tagName === "P" && child.innerText === "") {
+            continue;
+          } else {
+            container.appendChild(child.cloneNode(true));
+            break;
+          }
+        }
+        if (window.Quarto?.typesetMath) {
+          window.Quarto.typesetMath(container);
+        }
+        return container.innerHTML
+      } else {
+        if (window.Quarto?.typesetMath) {
+          window.Quarto.typesetMath(note);
+        }
+        return note.innerHTML;
+      }
+    } else {
+      // Remove any anchor links if they are present
+      const anchorLink = note.querySelector('a.anchorjs-link');
+      if (anchorLink) {
+        anchorLink.remove();
+      }
+      if (window.Quarto?.typesetMath) {
+        window.Quarto.typesetMath(note);
+      }
+      if (note.classList.contains("callout")) {
+        return note.outerHTML;
+      } else {
+        return note.innerHTML;
+      }
+    }
+  }
+  for (var i=0; i<xrefs.length; i++) {
+    const xref = xrefs[i];
+    tippyHover(xref, undefined, function(instance) {
+      instance.disable();
+      let url = xref.getAttribute('href');
+      let hash = undefined; 
+      if (url.startsWith('#')) {
+        hash = url;
+      } else {
+        try { hash = new URL(url).hash; } catch {}
+      }
+      if (hash) {
+        const id = hash.replace(/^#\/?/, "");
+        const note = window.document.getElementById(id);
+        if (note !== null) {
+          try {
+            const html = processXRef(id, note.cloneNode(true));
+            instance.setContent(html);
+          } finally {
+            instance.enable();
+            instance.show();
+          }
+        } else {
+          // See if we can fetch this
+          fetch(url.split('#')[0])
+          .then(res => res.text())
+          .then(html => {
+            const parser = new DOMParser();
+            const htmlDoc = parser.parseFromString(html, "text/html");
+            const note = htmlDoc.getElementById(id);
+            if (note !== null) {
+              const html = processXRef(id, note);
+              instance.setContent(html);
+            } 
+          }).finally(() => {
+            instance.enable();
+            instance.show();
+          });
+        }
+      } else {
+        // See if we can fetch a full url (with no hash to target)
+        // This is a special case and we should probably do some content thinning / targeting
+        fetch(url)
+        .then(res => res.text())
+        .then(html => {
+          const parser = new DOMParser();
+          const htmlDoc = parser.parseFromString(html, "text/html");
+          const note = htmlDoc.querySelector('main.content');
+          if (note !== null) {
+            // This should only happen for chapter cross references
+            // (since there is no id in the URL)
+            // remove the first header
+            if (note.children.length > 0 && note.children[0].tagName === "HEADER") {
+              note.children[0].remove();
+            }
+            const html = processXRef(null, note);
+            instance.setContent(html);
+          } 
+        }).finally(() => {
+          instance.enable();
+          instance.show();
+        });
+      }
+    }, function(instance) {
+    });
+  }
+      let selectedAnnoteEl;
+      const selectorForAnnotation = ( cell, annotation) => {
+        let cellAttr = 'data-code-cell="' + cell + '"';
+        let lineAttr = 'data-code-annotation="' +  annotation + '"';
+        const selector = 'span[' + cellAttr + '][' + lineAttr + ']';
+        return selector;
+      }
+      const selectCodeLines = (annoteEl) => {
+        const doc = window.document;
+        const targetCell = annoteEl.getAttribute("data-target-cell");
+        const targetAnnotation = annoteEl.getAttribute("data-target-annotation");
+        const annoteSpan = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation));
+        const lines = annoteSpan.getAttribute("data-code-lines").split(",");
+        const lineIds = lines.map((line) => {
+          return targetCell + "-" + line;
+        })
+        let top = null;
+        let height = null;
+        let parent = null;
+        if (lineIds.length > 0) {
+            //compute the position of the single el (top and bottom and make a div)
+            const el = window.document.getElementById(lineIds[0]);
+            top = el.offsetTop;
+            height = el.offsetHeight;
+            parent = el.parentElement.parentElement;
+          if (lineIds.length > 1) {
+            const lastEl = window.document.getElementById(lineIds[lineIds.length - 1]);
+            const bottom = lastEl.offsetTop + lastEl.offsetHeight;
+            height = bottom - top;
+          }
+          if (top !== null && height !== null && parent !== null) {
+            // cook up a div (if necessary) and position it 
+            let div = window.document.getElementById("code-annotation-line-highlight");
+            if (div === null) {
+              div = window.document.createElement("div");
+              div.setAttribute("id", "code-annotation-line-highlight");
+              div.style.position = 'absolute';
+              parent.appendChild(div);
+            }
+            div.style.top = top - 2 + "px";
+            div.style.height = height + 4 + "px";
+            div.style.left = 0;
+            let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter");
+            if (gutterDiv === null) {
+              gutterDiv = window.document.createElement("div");
+              gutterDiv.setAttribute("id", "code-annotation-line-highlight-gutter");
+              gutterDiv.style.position = 'absolute';
+              const codeCell = window.document.getElementById(targetCell);
+              const gutter = codeCell.querySelector('.code-annotation-gutter');
+              gutter.appendChild(gutterDiv);
+            }
+            gutterDiv.style.top = top - 2 + "px";
+            gutterDiv.style.height = height + 4 + "px";
+          }
+          selectedAnnoteEl = annoteEl;
+        }
+      };
+      const unselectCodeLines = () => {
+        const elementsIds = ["code-annotation-line-highlight", "code-annotation-line-highlight-gutter"];
+        elementsIds.forEach((elId) => {
+          const div = window.document.getElementById(elId);
+          if (div) {
+            div.remove();
+          }
+        });
+        selectedAnnoteEl = undefined;
+      };
+        // Handle positioning of the toggle
+    window.addEventListener(
+      "resize",
+      throttle(() => {
+        elRect = undefined;
+        if (selectedAnnoteEl) {
+          selectCodeLines(selectedAnnoteEl);
+        }
+      }, 10)
+    );
+    function throttle(fn, ms) {
+    let throttle = false;
+    let timer;
+      return (...args) => {
+        if(!throttle) { // first call gets through
+            fn.apply(this, args);
+            throttle = true;
+        } else { // all the others get throttled
+            if(timer) clearTimeout(timer); // cancel #2
+            timer = setTimeout(() => {
+              fn.apply(this, args);
+              timer = throttle = false;
+            }, ms);
+        }
+      };
+    }
+      // Attach click handler to the DT
+      const annoteDls = window.document.querySelectorAll('dt[data-target-cell]');
+      for (const annoteDlNode of annoteDls) {
+        annoteDlNode.addEventListener('click', (event) => {
+          const clickedEl = event.target;
+          if (clickedEl !== selectedAnnoteEl) {
+            unselectCodeLines();
+            const activeEl = window.document.querySelector('dt[data-target-cell].code-annotation-active');
+            if (activeEl) {
+              activeEl.classList.remove('code-annotation-active');
+            }
+            selectCodeLines(clickedEl);
+            clickedEl.classList.add('code-annotation-active');
+          } else {
+            // Unselect the line
+            unselectCodeLines();
+            clickedEl.classList.remove('code-annotation-active');
+          }
+        });
+      }
+  const findCites = (el) => {
+    const parentEl = el.parentElement;
+    if (parentEl) {
+      const cites = parentEl.dataset.cites;
+      if (cites) {
+        return {
+          el,
+          cites: cites.split(' ')
+        };
+      } else {
+        return findCites(el.parentElement)
+      }
+    } else {
+      return undefined;
+    }
+  };
+  var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
+  for (var i=0; i<bibliorefs.length; i++) {
+    const ref = bibliorefs[i];
+    const citeInfo = findCites(ref);
+    if (citeInfo) {
+      tippyHover(citeInfo.el, function() {
+        var popup = window.document.createElement('div');
+        citeInfo.cites.forEach(function(cite) {
+          var citeDiv = window.document.createElement('div');
+          citeDiv.classList.add('hanging-indent');
+          citeDiv.classList.add('csl-entry');
+          var biblioDiv = window.document.getElementById('ref-' + cite);
+          if (biblioDiv) {
+            citeDiv.innerHTML = biblioDiv.innerHTML;
+          }
+          popup.appendChild(citeDiv);
+        });
+        return popup.innerHTML;
+      });
+    }
+  }
+});
+</script>
+</div> <!-- /content -->
+
+
+
+
+</body></html>
--- a/docs/config.html
+++ b/docs/config.html
@@ -1040,61 +1040,69 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
 <span id="cb1-580"><a href="#cb1-580" aria-hidden="true" tabindex="-1"></a><span class="co"># Be careful with this being turned on between different models.</span></span>
 <span id="cb1-581"><a href="#cb1-581" aria-hidden="true" tabindex="-1"></a><span class="fu">auto_resume_from_checkpoints</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
 <span id="cb1-582"><a href="#cb1-582" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-583"><a href="#cb1-583" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't mess with this, it's here for accelerate and torchrun</span></span>
-<span id="cb1-584"><a href="#cb1-584" aria-hidden="true" tabindex="-1"></a><span class="fu">local_rank</span><span class="kw">:</span></span>
-<span id="cb1-585"><a href="#cb1-585" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-586"><a href="#cb1-586" aria-hidden="true" tabindex="-1"></a><span class="co"># Add or change special tokens.</span></span>
-<span id="cb1-587"><a href="#cb1-587" aria-hidden="true" tabindex="-1"></a><span class="co"># If you add tokens here, you don't need to add them to the `tokens` list.</span></span>
-<span id="cb1-588"><a href="#cb1-588" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
-<span id="cb1-589"><a href="#cb1-589" aria-hidden="true" tabindex="-1"></a><span class="co">  # bos_token: "&lt;s&gt;"</span></span>
-<span id="cb1-590"><a href="#cb1-590" aria-hidden="true" tabindex="-1"></a><span class="co">  # eos_token: "&lt;/s&gt;"</span></span>
-<span id="cb1-591"><a href="#cb1-591" aria-hidden="true" tabindex="-1"></a><span class="co">  # unk_token: "&lt;unk&gt;"</span></span>
-<span id="cb1-592"><a href="#cb1-592" aria-hidden="true" tabindex="-1"></a><span class="co">  # pad_token: "[PAD]"</span></span>
+<span id="cb1-583"><a href="#cb1-583" aria-hidden="true" tabindex="-1"></a><span class="co">## Multimodal section</span></span>
+<span id="cb1-584"><a href="#cb1-584" aria-hidden="true" tabindex="-1"></a><span class="co"># int | tuple[int, int] | None . Size to resize images to, width x height.</span></span>
+<span id="cb1-585"><a href="#cb1-585" aria-hidden="true" tabindex="-1"></a><span class="co"># Will read from model/processor config if not set.</span></span>
+<span id="cb1-586"><a href="#cb1-586" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span></span>
+<span id="cb1-587"><a href="#cb1-587" aria-hidden="true" tabindex="-1"></a><span class="co"># str. Algorithm to use for image resizing. "bilinear", "bicubic", "lanczos". Default is "bilinear".</span></span>
+<span id="cb1-588"><a href="#cb1-588" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> </span><span class="st">'bilinear'</span></span>
+<span id="cb1-589"><a href="#cb1-589" aria-hidden="true" tabindex="-1"></a><span class="co">## End of multimodal section</span></span>
+<span id="cb1-590"><a href="#cb1-590" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-591"><a href="#cb1-591" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't mess with this, it's here for accelerate and torchrun</span></span>
+<span id="cb1-592"><a href="#cb1-592" aria-hidden="true" tabindex="-1"></a><span class="fu">local_rank</span><span class="kw">:</span></span>
 <span id="cb1-593"><a href="#cb1-593" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-594"><a href="#cb1-594" aria-hidden="true" tabindex="-1"></a><span class="co"># Add extra tokens.</span></span>
-<span id="cb1-595"><a href="#cb1-595" aria-hidden="true" tabindex="-1"></a><span class="fu">tokens</span><span class="kw">:</span></span>
-<span id="cb1-596"><a href="#cb1-596" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-597"><a href="#cb1-597" aria-hidden="true" tabindex="-1"></a><span class="co"># Mapping token_id to new_token_string to override reserved added_tokens in the tokenizer.</span></span>
-<span id="cb1-598"><a href="#cb1-598" aria-hidden="true" tabindex="-1"></a><span class="co"># Only works for tokens that are not part of the base vocab (aka are added_tokens).</span></span>
-<span id="cb1-599"><a href="#cb1-599" aria-hidden="true" tabindex="-1"></a><span class="co"># Can be checked if they exist in tokenizer.json added_tokens.</span></span>
-<span id="cb1-600"><a href="#cb1-600" aria-hidden="true" tabindex="-1"></a><span class="fu">added_tokens_overrides</span><span class="kw">:</span><span class="co">  # Dict[int, str]</span></span>
-<span id="cb1-601"><a href="#cb1-601" aria-hidden="true" tabindex="-1"></a><span class="co">#  128041: "&lt;|im_start|&gt;"</span></span>
-<span id="cb1-602"><a href="#cb1-602" aria-hidden="true" tabindex="-1"></a><span class="co">#  128042: "&lt;|im_end|&gt;"</span></span>
-<span id="cb1-603"><a href="#cb1-603" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-604"><a href="#cb1-604" aria-hidden="true" tabindex="-1"></a><span class="co"># FSDP</span></span>
-<span id="cb1-605"><a href="#cb1-605" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
-<span id="cb1-606"><a href="#cb1-606" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
-<span id="cb1-607"><a href="#cb1-607" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-608"><a href="#cb1-608" aria-hidden="true" tabindex="-1"></a><span class="co"># Deepspeed config path. e.g., deepspeed_configs/zero3.json</span></span>
-<span id="cb1-609"><a href="#cb1-609" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span></span>
-<span id="cb1-610"><a href="#cb1-610" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-611"><a href="#cb1-611" aria-hidden="true" tabindex="-1"></a><span class="co"># Advanced DDP Arguments</span></span>
-<span id="cb1-612"><a href="#cb1-612" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_timeout</span><span class="kw">:</span></span>
-<span id="cb1-613"><a href="#cb1-613" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_bucket_cap_mb</span><span class="kw">:</span></span>
-<span id="cb1-614"><a href="#cb1-614" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_broadcast_buffers</span><span class="kw">:</span></span>
+<span id="cb1-594"><a href="#cb1-594" aria-hidden="true" tabindex="-1"></a><span class="co"># Add or change special tokens.</span></span>
+<span id="cb1-595"><a href="#cb1-595" aria-hidden="true" tabindex="-1"></a><span class="co"># If you add tokens here, you don't need to add them to the `tokens` list.</span></span>
+<span id="cb1-596"><a href="#cb1-596" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
+<span id="cb1-597"><a href="#cb1-597" aria-hidden="true" tabindex="-1"></a><span class="co">  # bos_token: "&lt;s&gt;"</span></span>
+<span id="cb1-598"><a href="#cb1-598" aria-hidden="true" tabindex="-1"></a><span class="co">  # eos_token: "&lt;/s&gt;"</span></span>
+<span id="cb1-599"><a href="#cb1-599" aria-hidden="true" tabindex="-1"></a><span class="co">  # unk_token: "&lt;unk&gt;"</span></span>
+<span id="cb1-600"><a href="#cb1-600" aria-hidden="true" tabindex="-1"></a><span class="co">  # pad_token: "[PAD]"</span></span>
+<span id="cb1-601"><a href="#cb1-601" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-602"><a href="#cb1-602" aria-hidden="true" tabindex="-1"></a><span class="co"># Add extra tokens.</span></span>
+<span id="cb1-603"><a href="#cb1-603" aria-hidden="true" tabindex="-1"></a><span class="fu">tokens</span><span class="kw">:</span></span>
+<span id="cb1-604"><a href="#cb1-604" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-605"><a href="#cb1-605" aria-hidden="true" tabindex="-1"></a><span class="co"># Mapping token_id to new_token_string to override reserved added_tokens in the tokenizer.</span></span>
+<span id="cb1-606"><a href="#cb1-606" aria-hidden="true" tabindex="-1"></a><span class="co"># Only works for tokens that are not part of the base vocab (aka are added_tokens).</span></span>
+<span id="cb1-607"><a href="#cb1-607" aria-hidden="true" tabindex="-1"></a><span class="co"># Can be checked if they exist in tokenizer.json added_tokens.</span></span>
+<span id="cb1-608"><a href="#cb1-608" aria-hidden="true" tabindex="-1"></a><span class="fu">added_tokens_overrides</span><span class="kw">:</span><span class="co">  # Dict[int, str]</span></span>
+<span id="cb1-609"><a href="#cb1-609" aria-hidden="true" tabindex="-1"></a><span class="co">#  128041: "&lt;|im_start|&gt;"</span></span>
+<span id="cb1-610"><a href="#cb1-610" aria-hidden="true" tabindex="-1"></a><span class="co">#  128042: "&lt;|im_end|&gt;"</span></span>
+<span id="cb1-611"><a href="#cb1-611" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-612"><a href="#cb1-612" aria-hidden="true" tabindex="-1"></a><span class="co"># FSDP</span></span>
+<span id="cb1-613"><a href="#cb1-613" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
+<span id="cb1-614"><a href="#cb1-614" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
 <span id="cb1-615"><a href="#cb1-615" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-616"><a href="#cb1-616" aria-hidden="true" tabindex="-1"></a><span class="co"># Sequence parallelism</span></span>
-<span id="cb1-617"><a href="#cb1-617" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to a divisor of the number of GPUs available to split sequences into chunks of equal size.</span></span>
-<span id="cb1-618"><a href="#cb1-618" aria-hidden="true" tabindex="-1"></a><span class="co"># Use in long context training to prevent OOM when sequences cannot fit into a single GPU's VRAM.</span></span>
-<span id="cb1-619"><a href="#cb1-619" aria-hidden="true" tabindex="-1"></a><span class="co"># E.g., if 4 GPUs are available, set this value to 2 to split each sequence into two equal-sized</span></span>
-<span id="cb1-620"><a href="#cb1-620" aria-hidden="true" tabindex="-1"></a><span class="co"># subsequences, or set to 4 to split into four equal-sized subsequences.</span></span>
-<span id="cb1-621"><a href="#cb1-621" aria-hidden="true" tabindex="-1"></a><span class="co"># See https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html for more details.</span></span>
-<span id="cb1-622"><a href="#cb1-622" aria-hidden="true" tabindex="-1"></a><span class="fu">sequence_parallel_degree</span><span class="kw">:</span></span>
+<span id="cb1-616"><a href="#cb1-616" aria-hidden="true" tabindex="-1"></a><span class="co"># Deepspeed config path. e.g., deepspeed_configs/zero3.json</span></span>
+<span id="cb1-617"><a href="#cb1-617" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span></span>
+<span id="cb1-618"><a href="#cb1-618" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-619"><a href="#cb1-619" aria-hidden="true" tabindex="-1"></a><span class="co"># Advanced DDP Arguments</span></span>
+<span id="cb1-620"><a href="#cb1-620" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_timeout</span><span class="kw">:</span></span>
+<span id="cb1-621"><a href="#cb1-621" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_bucket_cap_mb</span><span class="kw">:</span></span>
+<span id="cb1-622"><a href="#cb1-622" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_broadcast_buffers</span><span class="kw">:</span></span>
 <span id="cb1-623"><a href="#cb1-623" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-624"><a href="#cb1-624" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
-<span id="cb1-625"><a href="#cb1-625" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span></span>
-<span id="cb1-626"><a href="#cb1-626" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-627"><a href="#cb1-627" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize</span></span>
-<span id="cb1-628"><a href="#cb1-628" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
-<span id="cb1-629"><a href="#cb1-629" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-630"><a href="#cb1-630" aria-hidden="true" tabindex="-1"></a><span class="co"># Debug mode</span></span>
-<span id="cb1-631"><a href="#cb1-631" aria-hidden="true" tabindex="-1"></a><span class="fu">debug</span><span class="kw">:</span></span>
-<span id="cb1-632"><a href="#cb1-632" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-633"><a href="#cb1-633" aria-hidden="true" tabindex="-1"></a><span class="co"># Seed</span></span>
-<span id="cb1-634"><a href="#cb1-634" aria-hidden="true" tabindex="-1"></a><span class="fu">seed</span><span class="kw">:</span></span>
-<span id="cb1-635"><a href="#cb1-635" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-636"><a href="#cb1-636" aria-hidden="true" tabindex="-1"></a><span class="co"># Allow overwrite yml config using from cli</span></span>
-<span id="cb1-637"><a href="#cb1-637" aria-hidden="true" tabindex="-1"></a><span class="fu">strict</span><span class="kw">:</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb1-624"><a href="#cb1-624" aria-hidden="true" tabindex="-1"></a><span class="co"># Sequence parallelism</span></span>
+<span id="cb1-625"><a href="#cb1-625" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to a divisor of the number of GPUs available to split sequences into chunks of equal size.</span></span>
+<span id="cb1-626"><a href="#cb1-626" aria-hidden="true" tabindex="-1"></a><span class="co"># Use in long context training to prevent OOM when sequences cannot fit into a single GPU's VRAM.</span></span>
+<span id="cb1-627"><a href="#cb1-627" aria-hidden="true" tabindex="-1"></a><span class="co"># E.g., if 4 GPUs are available, set this value to 2 to split each sequence into two equal-sized</span></span>
+<span id="cb1-628"><a href="#cb1-628" aria-hidden="true" tabindex="-1"></a><span class="co"># subsequences, or set to 4 to split into four equal-sized subsequences.</span></span>
+<span id="cb1-629"><a href="#cb1-629" aria-hidden="true" tabindex="-1"></a><span class="co"># See https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html for more details.</span></span>
+<span id="cb1-630"><a href="#cb1-630" aria-hidden="true" tabindex="-1"></a><span class="fu">sequence_parallel_degree</span><span class="kw">:</span></span>
+<span id="cb1-631"><a href="#cb1-631" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-632"><a href="#cb1-632" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
+<span id="cb1-633"><a href="#cb1-633" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span></span>
+<span id="cb1-634"><a href="#cb1-634" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-635"><a href="#cb1-635" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize</span></span>
+<span id="cb1-636"><a href="#cb1-636" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
+<span id="cb1-637"><a href="#cb1-637" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-638"><a href="#cb1-638" aria-hidden="true" tabindex="-1"></a><span class="co"># Debug mode</span></span>
+<span id="cb1-639"><a href="#cb1-639" aria-hidden="true" tabindex="-1"></a><span class="fu">debug</span><span class="kw">:</span></span>
+<span id="cb1-640"><a href="#cb1-640" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-641"><a href="#cb1-641" aria-hidden="true" tabindex="-1"></a><span class="co"># Seed</span></span>
+<span id="cb1-642"><a href="#cb1-642" aria-hidden="true" tabindex="-1"></a><span class="fu">seed</span><span class="kw">:</span></span>
+<span id="cb1-643"><a href="#cb1-643" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-644"><a href="#cb1-644" aria-hidden="true" tabindex="-1"></a><span class="co"># Allow overwrite yml config using from cli</span></span>
+<span id="cb1-645"><a href="#cb1-645" aria-hidden="true" tabindex="-1"></a><span class="fu">strict</span><span class="kw">:</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>



--- a/docs/multimodal.html
+++ b/docs/multimodal.html
@@ -7,7 +7,7 @@
 <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">


-<title>multimodal – Axolotl</title>
+<title>MultiModal / Vision Language Models (BETA) – Axolotl</title>
 <style>
 code{white-space: pre-wrap;}
 span.smallcaps{font-variant: small-caps;}
@@ -432,50 +432,226 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
    <h2 id="toc-title">On this page</h2>
   
  <ul>
-  <li><a href="#multimodal-vision-language-models-beta" id="toc-multimodal-vision-language-models-beta" class="nav-link active" data-scroll-target="#multimodal-vision-language-models-beta">MultiModal / Vision Language Models (BETA)</a>
+  <li><a href="#supported-models" id="toc-supported-models" class="nav-link active" data-scroll-target="#supported-models">Supported Models</a></li>
+  <li><a href="#usage" id="toc-usage" class="nav-link" data-scroll-target="#usage">Usage</a>
  <ul class="collapse">
-  <li><a href="#supported-models" id="toc-supported-models" class="nav-link" data-scroll-target="#supported-models">Supported Models</a></li>
-  <li><a href="#usage" id="toc-usage" class="nav-link" data-scroll-target="#usage">Usage</a></li>
+  <li><a href="#sec-mllama" id="toc-sec-mllama" class="nav-link" data-scroll-target="#sec-mllama">Mllama</a></li>
+  <li><a href="#sec-pixtral" id="toc-sec-pixtral" class="nav-link" data-scroll-target="#sec-pixtral">Pixtral</a></li>
+  <li><a href="#sec-llava-15" id="toc-sec-llava-15" class="nav-link" data-scroll-target="#sec-llava-15">Llava-1.5</a></li>
+  <li><a href="#sec-mistral-small-31" id="toc-sec-mistral-small-31" class="nav-link" data-scroll-target="#sec-mistral-small-31">Mistral-Small-3.1</a></li>
+  <li><a href="#sec-gemma-3" id="toc-sec-gemma-3" class="nav-link" data-scroll-target="#sec-gemma-3">Gemma-3</a></li>
+  <li><a href="#sec-qwen2-vl" id="toc-sec-qwen2-vl" class="nav-link" data-scroll-target="#sec-qwen2-vl">Qwen2-VL</a></li>
+  <li><a href="#sec-qwen25-vl" id="toc-sec-qwen25-vl" class="nav-link" data-scroll-target="#sec-qwen25-vl">Qwen2.5-VL</a></li>
  </ul></li>
+  <li><a href="#dataset-format" id="toc-dataset-format" class="nav-link" data-scroll-target="#dataset-format">Dataset Format</a></li>
  </ul>
 </nav>
    </div>
 <!-- main -->
-<main class="content" id="quarto-document-content"><header id="title-block-header" class="quarto-title-block"><nav class="quarto-page-breadcrumbs quarto-title-breadcrumbs d-none d-lg-block" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../docs/multimodal.html">How To Guides</a></li><li class="breadcrumb-item"><a href="../docs/multimodal.html">MultiModal / Vision Language Models (BETA)</a></li></ol></nav></header>
+<main class="content" id="quarto-document-content">
+
+<header id="title-block-header" class="quarto-title-block default"><nav class="quarto-page-breadcrumbs quarto-title-breadcrumbs d-none d-lg-block" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../docs/multimodal.html">How To Guides</a></li><li class="breadcrumb-item"><a href="../docs/multimodal.html">MultiModal / Vision Language Models (BETA)</a></li></ol></nav>
+<div class="quarto-title">
+<h1 class="title">MultiModal / Vision Language Models (BETA)</h1>
+</div>



+<div class="quarto-title-meta">

-<section id="multimodal-vision-language-models-beta" class="level1">
-<h1>MultiModal / Vision Language Models (BETA)</h1>
-<section id="supported-models" class="level3">
-<h3 class="anchored" data-anchor-id="supported-models">Supported Models</h3>
+    
+  
+    
+  </div>
+  
+
+
+</header>
+
+
+<section id="supported-models" class="level2">
+<h2 class="anchored" data-anchor-id="supported-models">Supported Models</h2>
 <ul>
-<li>Mllama, i.e.&nbsp;llama with vision models</li>
+<li><a href="#sec-mllama">Mllama</a></li>
+<li><a href="#sec-pixtral">Pixtral</a></li>
+<li><a href="#sec-llava-15">Llava-1.5</a></li>
+<li><a href="#sec-mistral-small-31">Mistral-Small-3.1</a></li>
+<li><a href="#sec-gemma-3">Gemma-3</a></li>
+<li><a href="#sec-qwen2-vl">Qwen2-VL</a></li>
+<li><a href="#sec-qwen25-vl">Qwen2.5-VL</a></li>
 </ul>
 </section>
-<section id="usage" class="level3">
-<h3 class="anchored" data-anchor-id="usage">Usage</h3>
-<p>Currently multimodal support is limited and doesn’t have full feature parity. To finetune a multimodal Llama w/ LoRA,
-you’ll need to use the following in YAML in combination with the rest of the required hyperparams.</p>
-<div class="sourceCode" id="cb1"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> alpindale/Llama-3.2-11B-Vision-Instruct</span></span>
-<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">processor_type</span><span class="kw">:</span><span class="at"> AutoProcessor</span></span>
+<section id="usage" class="level2">
+<h2 class="anchored" data-anchor-id="usage">Usage</h2>
+<p>Multimodal support is limited and doesn’t have full feature parity.</p>
+<p>Here are the hyperparams you’ll need to use to finetune a multimodal model.</p>
+<div class="sourceCode" id="cb1"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">processor_type</span><span class="kw">:</span><span class="at"> AutoProcessor</span></span>
+<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a></span>
 <span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="fu">skip_prepare_dataset</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
-<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> llama3_2_vision</span></span>
-<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
-<span id="cb1-7"><a href="#cb1-7" 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"> HuggingFaceH4/llava-instruct-mix-vsft</span></span>
-<span id="cb1-8"><a href="#cb1-8" 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="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train[:1%]</span></span>
-<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> messages</span></span>
-<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a><span class="fu">remove_unused_columns</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
-<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
-<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a><span class="co"># only finetune the Language model, leave the vision model and vision tower frozen</span></span>
-<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_modules</span><span class="kw">:</span><span class="at"> </span><span class="st">'language_model.model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
-
-
+<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="fu">remove_unused_columns</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span><span class="co">  # leave columns in place as they are needed to handle image embeddings during training</span></span>
+<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span><span class="co">  # not yet supported with multimodal</span></span>
+<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="co">  # see in next section</span></span>
+<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a><span class="co"># example dataset</span></span>
+<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
+<span id="cb1-11"><a href="#cb1-11" 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"> HuggingFaceH4/llava-instruct-mix-vsft</span></span>
+<span id="cb1-12"><a href="#cb1-12" 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="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train[:1%]</span></span>
+<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a><span class="at">    </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> messages</span></span>
+<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-16"><a href="#cb1-16" aria-hidden="true" tabindex="-1"></a><span class="co"># (optional) if doing lora, only finetune the Language model,</span></span>
+<span id="cb1-17"><a href="#cb1-17" aria-hidden="true" tabindex="-1"></a><span class="co"># leave the vision model and vision tower frozen</span></span>
+<span id="cb1-18"><a href="#cb1-18" aria-hidden="true" tabindex="-1"></a><span class="co"># load_in_8bit: true</span></span>
+<span id="cb1-19"><a href="#cb1-19" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> lora</span></span>
+<span id="cb1-20"><a href="#cb1-20" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_modules</span><span class="kw">:</span><span class="at"> </span><span class="st">'language_model.model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'</span></span>
+<span id="cb1-21"><a href="#cb1-21" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb1-22"><a href="#cb1-22" aria-hidden="true" tabindex="-1"></a><span class="co"># (optional) if you want to resize images to a set size</span></span>
+<span id="cb1-23"><a href="#cb1-23" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">512</span></span>
+<span id="cb1-24"><a href="#cb1-24" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> bilinear</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<p>Please see <a href="https://github.com/axolotl-ai/axolotl/tree/main/examples">examples</a> folder for full configs.</p>
+<div class="callout callout-style-default callout-warning 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">
+Warning
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>Some of our chat_templates have been extended to support broader dataset types. This should not break any existing configs.</p>
+</div>
+</div>
+<section id="sec-mllama" class="level3">
+<h3 class="anchored" data-anchor-id="sec-mllama">Mllama</h3>
+<div class="sourceCode" id="cb2"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> meta-llama/Llama-3.2-11B-Vision-Instruct</span></span>
+<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> llama3_2_vision</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 </section>
+<section id="sec-pixtral" class="level3">
+<h3 class="anchored" data-anchor-id="sec-pixtral">Pixtral</h3>
+<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">base_model</span><span class="kw">:</span><span class="at"> mistralai/Pixtral-12B-2409</span></span>
+<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> pixtral</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+</section>
+<section id="sec-llava-15" class="level3">
+<h3 class="anchored" data-anchor-id="sec-llava-15">Llava-1.5</h3>
+<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">base_model</span><span class="kw">:</span><span class="at"> llava-hf/llava-1.5-7b-hf</span></span>
+<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> llava</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+</section>
+<section id="sec-mistral-small-31" class="level3">
+<h3 class="anchored" data-anchor-id="sec-mistral-small-31">Mistral-Small-3.1</h3>
+<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">base_model</span><span class="kw">:</span><span class="at"> mistralai/Mistral-Small-3.1-24B-Instruct-2503</span></span>
+<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> mistral_v7_tekken</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+</section>
+<section id="sec-gemma-3" class="level3">
+<h3 class="anchored" data-anchor-id="sec-gemma-3">Gemma-3</h3>
+<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>The Gemma3-1B model is a text-only model, so please train as regular text model.</p>
+</div>
+</div>
+<p>For multi-modal 4B/12B/27B models, use the following config:</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="fu">base_model</span><span class="kw">:</span><span class="at"> google/gemma-3-4b-it</span></span>
+<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> gemma3</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+</section>
+<section id="sec-qwen2-vl" class="level3">
+<h3 class="anchored" data-anchor-id="sec-qwen2-vl">Qwen2-VL</h3>
+<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">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen2-VL-7B-Instruct</span></span>
+<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> qwen2_vl</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+</section>
+<section id="sec-qwen25-vl" class="level3">
+<h3 class="anchored" data-anchor-id="sec-qwen25-vl">Qwen2.5-VL</h3>
+<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">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen2.5-VL-7B-Instruct</span></span>
+<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> qwen2_vl</span><span class="co">  # same as qwen2-vl</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+</section>
+</section>
+<section id="dataset-format" class="level2">
+<h2 class="anchored" data-anchor-id="dataset-format">Dataset Format</h2>
+<p>For multi-modal datasets, we adopt an extended <code>chat_template</code> format similar to OpenAI’s Message format.</p>
+<ul>
+<li>A message is a list of <code>role</code> and <code>content</code>.</li>
+<li><code>role</code> can be <code>system</code>, <code>user</code>, <code>assistant</code>, etc.</li>
+<li><code>content</code> is a list of <code>type</code> and (<code>text</code> or <code>image</code> or <code>path</code> or <code>url</code> or <code>base64</code>).</li>
+</ul>
+<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>For backwards compatibility:</p>
+<ul>
+<li>If the dataset has a <code>images</code> or <code>image</code> column of <code>list[Image]</code>, it will be appended to the first <code>content</code> list as <code>{"type": "image", "image": ...}</code>. However, if the content already has a <code>{"type": "image"}</code> but no <code>image</code> key, it will be set the <code>image</code> key.</li>
+<li>If <code>content</code> is a string, it will be converted to a list with <code>type</code> as <code>text</code>.</li>
+</ul>
+</div>
+</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>For image loading, you can use the following keys within <code>content</code> alongside <code>"type": "image"</code>:</p>
+<ul>
+<li><code>"path": "/path/to/image.jpg"</code></li>
+<li><code>"url": "https://example.com/image.jpg"</code></li>
+<li><code>"base64": "..."</code></li>
+<li><code>"image": PIL.Image</code></li>
+</ul>
+</div>
+</div>
+<p>Here is an example of a multi-modal dataset:</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="ot">[</span></span>
+<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a>  <span class="fu">{</span></span>
+<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a>    <span class="dt">"messages"</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>
+<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a>            <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"system"</span><span class="fu">,</span></span>
+<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a>            <span class="dt">"content"</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 class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"You are a helpful assistant."</span><span class="fu">}</span></span>
+<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a>              <span class="ot">]</span></span>
+<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a>        <span class="fu">}</span><span class="ot">,</span></span>
+<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a>        <span class="fu">{</span></span>
+<span id="cb9-11"><a href="#cb9-11" aria-hidden="true" tabindex="-1"></a>            <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span></span>
+<span id="cb9-12"><a href="#cb9-12" aria-hidden="true" tabindex="-1"></a>            <span class="dt">"content"</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">"type"</span><span class="fu">:</span> <span class="st">"image"</span><span class="fu">,</span> <span class="dt">"image"</span><span class="fu">:</span> <span class="st">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"</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="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"Describe this image in detail."</span><span class="fu">}</span></span>
+<span id="cb9-15"><a href="#cb9-15" aria-hidden="true" tabindex="-1"></a>            <span class="ot">]</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="fu">{</span></span>
+<span id="cb9-18"><a href="#cb9-18" 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>
+<span id="cb9-19"><a href="#cb9-19" aria-hidden="true" tabindex="-1"></a>            <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
+<span id="cb9-20"><a href="#cb9-20" aria-hidden="true" tabindex="-1"></a>              <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"The image is a bee."</span><span class="fu">}</span></span>
+<span id="cb9-21"><a href="#cb9-21" aria-hidden="true" tabindex="-1"></a>            <span class="ot">]</span></span>
+<span id="cb9-22"><a href="#cb9-22" aria-hidden="true" tabindex="-1"></a>        <span class="fu">}</span></span>
+<span id="cb9-23"><a href="#cb9-23" aria-hidden="true" tabindex="-1"></a>    <span class="ot">]</span></span>
+<span id="cb9-24"><a href="#cb9-24" aria-hidden="true" tabindex="-1"></a>  <span class="fu">}</span></span>
+<span id="cb9-25"><a href="#cb9-25" aria-hidden="true" tabindex="-1"></a><span class="ot">]</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+
+
 </section>

 </main> <!-- /main -->
--- a/search.json
+++ b/search.json
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -2,670 +2,674 @@
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/examples/colab-notebooks/colab-axolotl-example.html</loc>
-    <lastmod>2025-03-23T00:33:31.707Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.819Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/stepwise_supervised.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/template_free.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/tokenized.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/nccl.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/amd_hpc.html</loc>
-    <lastmod>2025-03-23T00:33:31.701Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.812Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/config.html</loc>
-    <lastmod>2025-03-23T00:33:31.701Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.812Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-gpu.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/installation.html</loc>
-    <lastmod>2025-03-23T00:33:31.705Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/torchao.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/reward_modelling.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/input_output.html</loc>
-    <lastmod>2025-03-23T00:33:31.705Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multimodal.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.mlflow_.html</loc>
-    <lastmod>2025-03-23T00:34:00.504Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.246Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.trainer_fsdp_optim.html</loc>
-    <lastmod>2025-03-23T00:34:00.110Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.841Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.data.batch_dataset_fetcher.html</loc>
-    <lastmod>2025-03-23T00:34:00.125Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.857Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.stepwise_supervised.html</loc>
-    <lastmod>2025-03-23T00:33:59.819Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.545Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.mistral_attn_hijack_flash.html</loc>
-    <lastmod>2025-03-23T00:34:00.058Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.789Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.user_defined.html</loc>
-    <lastmod>2025-03-23T00:33:59.865Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.592Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.liger.args.html</loc>
-    <lastmod>2025-03-23T00:34:00.422Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.162Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.training.html</loc>
-    <lastmod>2025-03-23T00:34:00.292Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.025Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/datasets.html</loc>
-    <lastmod>2025-03-23T00:33:59.332Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.053Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.geglu.html</loc>
-    <lastmod>2025-03-23T00:33:59.999Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.728Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_attn_hijack_flash.html</loc>
-    <lastmod>2025-03-23T00:34:00.043Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.774Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.sweeps.html</loc>
-    <lastmod>2025-03-23T00:33:59.658Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.384Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.freeze.html</loc>
-    <lastmod>2025-03-23T00:34:00.196Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.928Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.multipack.html</loc>
-    <lastmod>2025-03-23T00:34:00.060Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.791Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.main.html</loc>
-    <lastmod>2025-03-23T00:33:59.557Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.283Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.trl.html</loc>
-    <lastmod>2025-03-23T00:33:59.727Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.454Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.passthrough.html</loc>
-    <lastmod>2025-03-23T00:33:59.867Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.594Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.format.llama3x.html</loc>
-    <lastmod>2025-03-23T00:33:59.512Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.239Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.datasets.transforms.chat_builder.html</loc>
-    <lastmod>2025-03-23T00:33:59.526Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.253Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.kto.user_defined.html</loc>
-    <lastmod>2025-03-23T00:33:59.884Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.611Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.mamba.html</loc>
-    <lastmod>2025-03-23T00:34:00.479Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.220Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.base.html</loc>
-    <lastmod>2025-03-23T00:34:00.407Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.147Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.bench.html</loc>
-    <lastmod>2025-03-23T00:34:00.188Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.920Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.swiglu.html</loc>
-    <lastmod>2025-03-23T00:34:00.009Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.738Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.format.shared.html</loc>
-    <lastmod>2025-03-23T00:33:59.514Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.240Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.cut_cross_entropy.args.html</loc>
-    <lastmod>2025-03-23T00:34:00.410Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.150Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.datasets.chat.html</loc>
-    <lastmod>2025-03-23T00:33:59.519Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.245Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.lisa.html</loc>
-    <lastmod>2025-03-23T00:34:00.500Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.242Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.grokfast.optimizer.html</loc>
-    <lastmod>2025-03-23T00:34:00.411Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.151Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.alpaca_chat.html</loc>
-    <lastmod>2025-03-23T00:33:59.767Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.495Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.alpaca_instruct.html</loc>
-    <lastmod>2025-03-23T00:33:59.769Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.496Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.kto.chatml.html</loc>
-    <lastmod>2025-03-23T00:33:59.883Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.610Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.integrations.html</loc>
-    <lastmod>2025-03-23T00:34:00.332Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.071Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.trl.html</loc>
-    <lastmod>2025-03-23T00:34:00.320Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.054Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_tokenizers.html</loc>
-    <lastmod>2025-03-23T00:33:59.387Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.109Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.data.sft.html</loc>
-    <lastmod>2025-03-23T00:34:00.269Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.002Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schedulers.html</loc>
-    <lastmod>2025-03-23T00:34:00.237Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.969Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.chat_templates.html</loc>
-    <lastmod>2025-03-23T00:34:00.171Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.903Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.models.html</loc>
-    <lastmod>2025-03-23T00:34:00.155Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.887Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.chatml.html</loc>
-    <lastmod>2025-03-23T00:33:59.862Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.589Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.distributed.html</loc>
-    <lastmod>2025-03-23T00:34:00.256Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.988Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.utils.html</loc>
-    <lastmod>2025-03-23T00:34:00.098Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.829Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.utils.html</loc>
-    <lastmod>2025-03-23T00:34:00.344Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.084Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_expand_mask.html</loc>
-    <lastmod>2025-03-23T00:34:00.068Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.799Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.datasets.html</loc>
-    <lastmod>2025-03-23T00:34:00.447Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.188Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/logging_config.html</loc>
-    <lastmod>2025-03-23T00:33:59.392Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.114Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.quantize.html</loc>
-    <lastmod>2025-03-23T00:34:00.016Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.model.html</loc>
-    <lastmod>2025-03-23T00:34:00.287Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
-    <lastmod>2025-03-23T00:34:00.106Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.mixtral.html</loc>
-    <lastmod>2025-03-23T00:34:00.127Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.tokenization.html</loc>
-    <lastmod>2025-03-23T00:34:00.162Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.kd.trainer.html</loc>
-    <lastmod>2025-03-23T00:34:00.419Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.datasets.html</loc>
-    <lastmod>2025-03-23T00:34:00.309Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.core.html</loc>
-    <lastmod>2025-03-23T00:34:00.450Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
-    <lastmod>2025-03-23T00:34:00.099Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.optimizers.adopt.html</loc>
-    <lastmod>2025-03-23T00:34:00.266Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.input_output.html</loc>
-    <lastmod>2025-03-23T00:33:59.814Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/index.html</loc>
-    <lastmod>2025-03-23T00:33:59.255Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.modal_.html</loc>
-    <lastmod>2025-03-23T00:33:59.698Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.llama3.html</loc>
-    <lastmod>2025-03-23T00:33:59.852Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.train.html</loc>
-    <lastmod>2025-03-23T00:33:59.565Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainer_builder.html</loc>
-    <lastmod>2025-03-23T00:33:59.407Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.perplexity.html</loc>
-    <lastmod>2025-03-23T00:34:00.495Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/getting-started.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/inference.html</loc>
-    <lastmod>2025-03-23T00:33:31.705Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multipack.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-node.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/FAQS.html</loc>
-    <lastmod>2025-03-23T00:33:31.699Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
-    <lastmod>2025-03-23T00:33:31.722Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/index.html</loc>
-    <lastmod>2025-03-23T00:33:31.718Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/LICENSE.html</loc>
-    <lastmod>2025-03-23T00:33:31.721Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/TODO.html</loc>
-    <lastmod>2025-03-23T00:33:31.699Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lr_groups.html</loc>
-    <lastmod>2025-03-23T00:33:31.705Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/debugging.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/faq.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/batch_vs_grad.html</loc>
-    <lastmod>2025-03-23T00:33:31.701Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lora_optims.html</loc>
-    <lastmod>2025-03-23T00:33:31.705Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora_embeddings.html</loc>
-    <lastmod>2025-03-23T00:34:00.180Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.utils.html</loc>
-    <lastmod>2025-03-23T00:34:00.018Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.chat_template.html</loc>
-    <lastmod>2025-03-23T00:33:59.754Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/convert.html</loc>
-    <lastmod>2025-03-23T00:33:59.346Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.const.html</loc>
-    <lastmod>2025-03-23T00:34:00.431Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.base.html</loc>
-    <lastmod>2025-03-23T00:33:59.692Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.relora.html</loc>
-    <lastmod>2025-03-23T00:34:00.066Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora.html</loc>
-    <lastmod>2025-03-23T00:34:00.176Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_lora.html</loc>
-    <lastmod>2025-03-23T00:33:59.632Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
-    <lastmod>2025-03-23T00:33:59.908Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
-    <lastmod>2025-03-23T00:33:59.644Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.spectrum.args.html</loc>
-    <lastmod>2025-03-23T00:34:00.428Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/models.mamba.modeling_mamba.html</loc>
-    <lastmod>2025-03-23T00:34:00.448Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.architectures.html</loc>
-    <lastmod>2025-03-23T00:34:00.430Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.trainer.html</loc>
-    <lastmod>2025-03-23T00:34:00.213Z</lastmod>
-  </url>
-  <url>
-    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.comet_.html</loc>
-    <lastmod>2025-03-23T00:34:00.508Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.745Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_patch_multipack.html</loc>
-    <lastmod>2025-03-23T00:34:00.101Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.832Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.comet_.html</loc>
+    <lastmod>2025-03-23T15:09:31.249Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.trainer.html</loc>
+    <lastmod>2025-03-23T15:09:30.945Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.architectures.html</loc>
+    <lastmod>2025-03-23T15:09:31.170Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/models.mamba.modeling_mamba.html</loc>
+    <lastmod>2025-03-23T15:09:31.189Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.spectrum.args.html</loc>
+    <lastmod>2025-03-23T15:09:31.169Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
+    <lastmod>2025-03-23T15:09:30.370Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
+    <lastmod>2025-03-23T15:09:30.635Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_lora.html</loc>
+    <lastmod>2025-03-23T15:09:30.358Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora.html</loc>
+    <lastmod>2025-03-23T15:09:30.908Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.relora.html</loc>
+    <lastmod>2025-03-23T15:09:30.798Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.base.html</loc>
+    <lastmod>2025-03-23T15:09:30.418Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.const.html</loc>
+    <lastmod>2025-03-23T15:09:31.172Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/convert.html</loc>
+    <lastmod>2025-03-23T15:09:30.067Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.chat_template.html</loc>
+    <lastmod>2025-03-23T15:09:30.481Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.utils.html</loc>
+    <lastmod>2025-03-23T15:09:30.746Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora_embeddings.html</loc>
+    <lastmod>2025-03-23T15:09:30.911Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lora_optims.html</loc>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/batch_vs_grad.html</loc>
+    <lastmod>2025-03-23T15:09:01.812Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/faq.html</loc>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/debugging.html</loc>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lr_groups.html</loc>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/TODO.html</loc>
+    <lastmod>2025-03-23T15:09:01.811Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/LICENSE.html</loc>
+    <lastmod>2025-03-23T15:09:01.835Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/index.html</loc>
+    <lastmod>2025-03-23T15:09:01.831Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
+    <lastmod>2025-03-23T15:09:01.835Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/FAQS.html</loc>
+    <lastmod>2025-03-23T15:09:01.810Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-node.html</loc>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html</loc>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multipack.html</loc>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/inference.html</loc>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/getting-started.html</loc>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.perplexity.html</loc>
+    <lastmod>2025-03-23T15:09:31.237Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainer_builder.html</loc>
+    <lastmod>2025-03-23T15:09:30.129Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.train.html</loc>
+    <lastmod>2025-03-23T15:09:30.291Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.llama3.html</loc>
+    <lastmod>2025-03-23T15:09:30.579Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.modal_.html</loc>
+    <lastmod>2025-03-23T15:09:30.425Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/index.html</loc>
+    <lastmod>2025-03-23T15:09:29.976Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.input_output.html</loc>
+    <lastmod>2025-03-23T15:09:30.541Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.optimizers.adopt.html</loc>
+    <lastmod>2025-03-23T15:09:30.999Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
+    <lastmod>2025-03-23T15:09:30.830Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.core.html</loc>
+    <lastmod>2025-03-23T15:09:31.191Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.datasets.html</loc>
+    <lastmod>2025-03-23T15:09:31.042Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.kd.trainer.html</loc>
+    <lastmod>2025-03-23T15:09:31.159Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.tokenization.html</loc>
+    <lastmod>2025-03-23T15:09:30.893Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.mixtral.html</loc>
+    <lastmod>2025-03-23T15:09:30.858Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
+    <lastmod>2025-03-23T15:09:30.837Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.model.html</loc>
+    <lastmod>2025-03-23T15:09:31.020Z</lastmod>
+  </url>
+  <url>
+    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.multimodal.html</loc>
+    <lastmod>2025-03-23T15:09:31.059Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.gradient_checkpointing.unsloth.html</loc>
-    <lastmod>2025-03-23T00:34:00.272Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.005Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.base.html</loc>
-    <lastmod>2025-03-23T00:33:59.715Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.442Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.unsloth_.html</loc>
-    <lastmod>2025-03-23T00:34:00.117Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.848Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.samplers.multipack.html</loc>
-    <lastmod>2025-03-23T00:34:00.489Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.230Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.profiler.html</loc>
-    <lastmod>2025-03-23T00:34:00.499Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.240Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.lm_eval.args.html</loc>
-    <lastmod>2025-03-23T00:34:00.425Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.166Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.data.pretraining.html</loc>
-    <lastmod>2025-03-23T00:34:00.268Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.000Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/evaluate.html</loc>
-    <lastmod>2025-03-23T00:33:59.325Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.046Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.dict.html</loc>
-    <lastmod>2025-03-23T00:34:00.259Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.991Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.utils.html</loc>
-    <lastmod>2025-03-23T00:33:59.688Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.415Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.pygmalion.html</loc>
-    <lastmod>2025-03-23T00:33:59.836Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.563Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.training_args.html</loc>
-    <lastmod>2025-03-23T00:33:59.487Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.213Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.inference.html</loc>
-    <lastmod>2025-03-23T00:33:59.624Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.350Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.lora.html</loc>
-    <lastmod>2025-03-23T00:33:59.989Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.717Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.evaluate.html</loc>
-    <lastmod>2025-03-23T00:33:59.573Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.300Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.batching.html</loc>
-    <lastmod>2025-03-23T00:34:00.475Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.217Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.completion.html</loc>
-    <lastmod>2025-03-23T00:33:59.808Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.535Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.zephyr.html</loc>
-    <lastmod>2025-03-23T00:33:59.864Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.591Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.metharme.html</loc>
-    <lastmod>2025-03-23T00:33:59.825Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.552Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.orpo.chat_template.html</loc>
-    <lastmod>2025-03-23T00:33:59.904Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.632Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.alpaca_w_system.html</loc>
-    <lastmod>2025-03-23T00:33:59.781Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.508Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.model_shard_quant.html</loc>
-    <lastmod>2025-03-23T00:34:00.185Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.917Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.config.html</loc>
-    <lastmod>2025-03-23T00:33:59.610Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.336Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.enums.html</loc>
-    <lastmod>2025-03-23T00:34:00.339Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.078Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.preprocess.html</loc>
-    <lastmod>2025-03-23T00:33:59.652Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.378Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.messages.html</loc>
-    <lastmod>2025-03-23T00:33:59.509Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.235Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.chat_template.html</loc>
-    <lastmod>2025-03-23T00:33:59.842Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.569Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.peft.html</loc>
-    <lastmod>2025-03-23T00:34:00.317Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.051Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/train.html</loc>
-    <lastmod>2025-03-23T00:33:59.315Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.036Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.messages.chat.html</loc>
-    <lastmod>2025-03-23T00:33:59.840Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.567Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.orcamini.html</loc>
-    <lastmod>2025-03-23T00:33:59.829Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.556Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.mm_chat.html</loc>
-    <lastmod>2025-03-23T00:34:00.484Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.225Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.kto.llama3.html</loc>
-    <lastmod>2025-03-23T00:33:59.875Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.602Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.attention.mllama.html</loc>
-    <lastmod>2025-03-23T00:34:00.124Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.855Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.checks.html</loc>
-    <lastmod>2025-03-23T00:33:59.593Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.319Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.transformers_fa_utils.html</loc>
-    <lastmod>2025-03-23T00:34:00.116Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.847Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_attn_hijack_xformers.html</loc>
-    <lastmod>2025-03-23T00:34:00.044Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.775Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.dpo.trainer.html</loc>
-    <lastmod>2025-03-23T00:33:59.734Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.461Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.user_defined.html</loc>
-    <lastmod>2025-03-23T00:33:59.789Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.516Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.args.html</loc>
-    <lastmod>2025-03-23T00:33:59.587Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.313Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.llama2_chat.html</loc>
-    <lastmod>2025-03-23T00:33:59.802Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.529Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.config.html</loc>
-    <lastmod>2025-03-23T00:34:00.280Z</lastmod>
+    <lastmod>2025-03-23T15:09:31.013Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.grpo.trainer.html</loc>
-    <lastmod>2025-03-23T00:33:59.738Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.465Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.format.chatml.html</loc>
-    <lastmod>2025-03-23T00:33:59.511Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.237Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.lora_kernels.html</loc>
-    <lastmod>2025-03-23T00:34:00.090Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.821Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.base.html</loc>
-    <lastmod>2025-03-23T00:33:59.739Z</lastmod>
+    <lastmod>2025-03-23T15:09:30.466Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/rlhf.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/cli.html</loc>
-    <lastmod>2025-03-23T00:33:31.701Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.812Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/unsloth.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/fsdp_qlora.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset_preprocessing.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/custom_integrations.html</loc>
-    <lastmod>2025-03-23T00:33:31.701Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.812Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/mac.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.817Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/docker.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/ray-integration.html</loc>
-    <lastmod>2025-03-23T00:33:31.706Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.818Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/index.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/conversation.html</loc>
-    <lastmod>2025-03-23T00:33:31.701Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/pretraining.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
  <url>
    <loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/inst_tune.html</loc>
-    <lastmod>2025-03-23T00:33:31.702Z</lastmod>
+    <lastmod>2025-03-23T15:09:01.813Z</lastmod>
  </url>
 </urlset>