1415 lines
115 KiB
HTML
1415 lines
115 KiB
HTML
<!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">
|
||
|
||
<meta name="description" content="Reinforcement Learning from Human Feedback is a method whereby a language model is optimized from data using human feedback.">
|
||
|
||
<title>RLHF (Beta) – 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"><li class="breadcrumb-item"><a href="../docs/multimodal.html">How To Guides</a></li><li class="breadcrumb-item"><a href="../docs/rlhf.html">RLHF (Beta)</a></li></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/cli.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">CLI Reference</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</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 active">
|
||
<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>
|
||
<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-8" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Reference</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-8" 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-8" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<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 options</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" data-toc-expanded="2">
|
||
<h2 id="toc-title">On this page</h2>
|
||
|
||
<ul>
|
||
<li><a href="#overview" id="toc-overview" class="nav-link active" data-scroll-target="#overview">Overview</a></li>
|
||
<li><a href="#rlhf-using-axolotl" id="toc-rlhf-using-axolotl" class="nav-link" data-scroll-target="#rlhf-using-axolotl">RLHF using Axolotl</a>
|
||
<ul>
|
||
<li><a href="#dpo" id="toc-dpo" class="nav-link" data-scroll-target="#dpo">DPO</a>
|
||
<ul class="collapse">
|
||
<li><a href="#chatml.argilla" id="toc-chatml.argilla" class="nav-link" data-scroll-target="#chatml.argilla">chatml.argilla</a></li>
|
||
<li><a href="#chatml.argilla_chat" id="toc-chatml.argilla_chat" class="nav-link" data-scroll-target="#chatml.argilla_chat">chatml.argilla_chat</a></li>
|
||
<li><a href="#chatml.icr" id="toc-chatml.icr" class="nav-link" data-scroll-target="#chatml.icr">chatml.icr</a></li>
|
||
<li><a href="#chatml.intel" id="toc-chatml.intel" class="nav-link" data-scroll-target="#chatml.intel">chatml.intel</a></li>
|
||
<li><a href="#chatml.prompt_pairs" id="toc-chatml.prompt_pairs" class="nav-link" data-scroll-target="#chatml.prompt_pairs">chatml.prompt_pairs</a></li>
|
||
<li><a href="#chatml.ultra" id="toc-chatml.ultra" class="nav-link" data-scroll-target="#chatml.ultra">chatml.ultra</a></li>
|
||
<li><a href="#llama3.argilla" id="toc-llama3.argilla" class="nav-link" data-scroll-target="#llama3.argilla">llama3.argilla</a></li>
|
||
<li><a href="#llama3.argilla_chat" id="toc-llama3.argilla_chat" class="nav-link" data-scroll-target="#llama3.argilla_chat">llama3.argilla_chat</a></li>
|
||
<li><a href="#llama3.icr" id="toc-llama3.icr" class="nav-link" data-scroll-target="#llama3.icr">llama3.icr</a></li>
|
||
<li><a href="#llama3.intel" id="toc-llama3.intel" class="nav-link" data-scroll-target="#llama3.intel">llama3.intel</a></li>
|
||
<li><a href="#llama3.prompt_pairs" id="toc-llama3.prompt_pairs" class="nav-link" data-scroll-target="#llama3.prompt_pairs">llama3.prompt_pairs</a></li>
|
||
<li><a href="#llama3.ultra" id="toc-llama3.ultra" class="nav-link" data-scroll-target="#llama3.ultra">llama3.ultra</a></li>
|
||
<li><a href="#zephyr.nectar" id="toc-zephyr.nectar" class="nav-link" data-scroll-target="#zephyr.nectar">zephyr.nectar</a></li>
|
||
<li><a href="#chat_template.default" id="toc-chat_template.default" class="nav-link" data-scroll-target="#chat_template.default">chat_template.default</a></li>
|
||
<li><a href="#user_defined.default" id="toc-user_defined.default" class="nav-link" data-scroll-target="#user_defined.default">user_defined.default</a></li>
|
||
</ul></li>
|
||
<li><a href="#ipo" id="toc-ipo" class="nav-link" data-scroll-target="#ipo">IPO</a></li>
|
||
<li><a href="#orpo" id="toc-orpo" class="nav-link" data-scroll-target="#orpo">ORPO</a>
|
||
<ul class="collapse">
|
||
<li><a href="#chat_template.argilla" id="toc-chat_template.argilla" class="nav-link" data-scroll-target="#chat_template.argilla">chat_template.argilla</a></li>
|
||
</ul></li>
|
||
<li><a href="#kto" id="toc-kto" class="nav-link" data-scroll-target="#kto">KTO</a>
|
||
<ul class="collapse">
|
||
<li><a href="#chatml.argilla-1" id="toc-chatml.argilla-1" class="nav-link" data-scroll-target="#chatml.argilla-1">chatml.argilla</a></li>
|
||
<li><a href="#chatml.argilla_chat-1" id="toc-chatml.argilla_chat-1" class="nav-link" data-scroll-target="#chatml.argilla_chat-1">chatml.argilla_chat</a></li>
|
||
<li><a href="#chatml.intel-1" id="toc-chatml.intel-1" class="nav-link" data-scroll-target="#chatml.intel-1">chatml.intel</a></li>
|
||
<li><a href="#chatml.prompt_pairs-1" id="toc-chatml.prompt_pairs-1" class="nav-link" data-scroll-target="#chatml.prompt_pairs-1">chatml.prompt_pairs</a></li>
|
||
<li><a href="#chatml.ultra-1" id="toc-chatml.ultra-1" class="nav-link" data-scroll-target="#chatml.ultra-1">chatml.ultra</a></li>
|
||
<li><a href="#llama3.argilla-1" id="toc-llama3.argilla-1" class="nav-link" data-scroll-target="#llama3.argilla-1">llama3.argilla</a></li>
|
||
<li><a href="#llama3.argilla_chat-1" id="toc-llama3.argilla_chat-1" class="nav-link" data-scroll-target="#llama3.argilla_chat-1">llama3.argilla_chat</a></li>
|
||
<li><a href="#llama3.intel-1" id="toc-llama3.intel-1" class="nav-link" data-scroll-target="#llama3.intel-1">llama3.intel</a></li>
|
||
<li><a href="#llama3.prompt_pairs-1" id="toc-llama3.prompt_pairs-1" class="nav-link" data-scroll-target="#llama3.prompt_pairs-1">llama3.prompt_pairs</a></li>
|
||
<li><a href="#llama3.ultra-1" id="toc-llama3.ultra-1" class="nav-link" data-scroll-target="#llama3.ultra-1">llama3.ultra</a></li>
|
||
<li><a href="#user_defined.default-1" id="toc-user_defined.default-1" class="nav-link" data-scroll-target="#user_defined.default-1">user_defined.default</a></li>
|
||
</ul></li>
|
||
<li><a href="#grpo" id="toc-grpo" class="nav-link" data-scroll-target="#grpo">GRPO</a></li>
|
||
<li><a href="#using-local-dataset-files" id="toc-using-local-dataset-files" class="nav-link" data-scroll-target="#using-local-dataset-files">Using local dataset files</a></li>
|
||
<li><a href="#trl-auto-unwrapping-for-peft" id="toc-trl-auto-unwrapping-for-peft" class="nav-link" data-scroll-target="#trl-auto-unwrapping-for-peft">TRL auto-unwrapping for PEFT</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
<!-- main -->
|
||
<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/rlhf.html">RLHF (Beta)</a></li></ol></nav>
|
||
<div class="quarto-title">
|
||
<h1 class="title">RLHF (Beta)</h1>
|
||
</div>
|
||
|
||
<div>
|
||
<div class="description">
|
||
Reinforcement Learning from Human Feedback is a method whereby a language model is optimized from data using human feedback.
|
||
</div>
|
||
</div>
|
||
|
||
|
||
<div class="quarto-title-meta">
|
||
|
||
|
||
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</header>
|
||
|
||
|
||
<section id="overview" class="level2">
|
||
<h2 class="anchored" data-anchor-id="overview">Overview</h2>
|
||
<p>Reinforcement Learning from Human Feedback is a method whereby a language model is optimized from data using human feedback. Various methods include, but not limited to:</p>
|
||
<ul>
|
||
<li><a href="#dpo">Direct Preference Optimization (DPO)</a></li>
|
||
<li><a href="#ipo">Identity Preference Optimization (IPO)</a></li>
|
||
<li><a href="#kto">Kahneman-Tversky Optimization (KTO)</a></li>
|
||
<li><a href="#orpo">Odds Ratio Preference Optimization (ORPO)</a></li>
|
||
<li>Proximal Policy Optimization (PPO) (not yet supported in axolotl)</li>
|
||
</ul>
|
||
</section>
|
||
<section id="rlhf-using-axolotl" class="level2">
|
||
<h2 class="anchored" data-anchor-id="rlhf-using-axolotl">RLHF using Axolotl</h2>
|
||
<div class="callout callout-style-default callout-important 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">
|
||
Important
|
||
</div>
|
||
</div>
|
||
<div class="callout-body-container callout-body">
|
||
<p>This is a BETA feature and many features are not fully implemented. You are encouraged to open new PRs to improve the integration and functionality.</p>
|
||
</div>
|
||
</div>
|
||
<p>We rely on the <a href="https://github.com/huggingface/trl">TRL</a> library for implementations of various RL training methods, which we wrap around to expose in axolotl. Each method has their own supported ways of loading datasets and prompt formats.</p>
|
||
<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>You can find what each method supports by going into <code>src/axolotl/prompt_strategies/{method}</code> where <code>{method}</code> is one of our supported methods. The <code>type:</code> can be retrieved from <code>{method}.{function_name}</code>.</p>
|
||
</div>
|
||
</div>
|
||
<section id="dpo" class="level3">
|
||
<h3 class="anchored" data-anchor-id="dpo">DPO</h3>
|
||
<p>Example config:</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">rl</span><span class="kw">:</span><span class="at"> dpo</span></span>
|
||
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> Intel/orca_dpo_pairs</span></span>
|
||
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
|
||
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chatml.intel</span></span>
|
||
<span id="cb1-6"><a href="#cb1-6" 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"> argilla/ultrafeedback-binarized-preferences</span></span>
|
||
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
|
||
<span id="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"> chatml</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>DPO supports the following types with the following dataset format:</p>
|
||
<section id="chatml.argilla" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.argilla">chatml.argilla</h4>
|
||
<div class="sourceCode" id="cb2"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen_response"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected_response"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.argilla_chat" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.argilla_chat">chatml.argilla_chat</h4>
|
||
<div class="sourceCode" id="cb3"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
|
||
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb3-10"><a href="#cb3-10" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.icr" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.icr">chatml.icr</h4>
|
||
<div class="sourceCode" id="cb4"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb4-6"><a href="#cb4-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.intel" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.intel">chatml.intel</h4>
|
||
<div class="sourceCode" id="cb5"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"question"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.prompt_pairs" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.prompt_pairs">chatml.prompt_pairs</h4>
|
||
<div class="sourceCode" id="cb6"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.ultra" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.ultra">chatml.ultra</h4>
|
||
<div class="sourceCode" id="cb7"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
|
||
<span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb7-10"><a href="#cb7-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb7-11"><a href="#cb7-11" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb7-12"><a href="#cb7-12" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.argilla" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.argilla">llama3.argilla</h4>
|
||
<div class="sourceCode" id="cb8"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen_response"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected_response"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb8-6"><a href="#cb8-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.argilla_chat" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.argilla_chat">llama3.argilla_chat</h4>
|
||
<div class="sourceCode" id="cb9"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
|
||
<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</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">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.icr" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.icr">llama3.icr</h4>
|
||
<div class="sourceCode" id="cb10"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb10-6"><a href="#cb10-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.intel" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.intel">llama3.intel</h4>
|
||
<div class="sourceCode" id="cb11"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"question"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb11-6"><a href="#cb11-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.prompt_pairs" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.prompt_pairs">llama3.prompt_pairs</h4>
|
||
<div class="sourceCode" id="cb12"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb12-4"><a href="#cb12-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb12-5"><a href="#cb12-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb12-6"><a href="#cb12-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.ultra" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.ultra">llama3.ultra</h4>
|
||
<div class="sourceCode" id="cb13"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb13-4"><a href="#cb13-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb13-5"><a href="#cb13-5" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb13-6"><a href="#cb13-6" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb13-7"><a href="#cb13-7" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
|
||
<span id="cb13-8"><a href="#cb13-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb13-9"><a href="#cb13-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb13-10"><a href="#cb13-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb13-11"><a href="#cb13-11" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb13-12"><a href="#cb13-12" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="zephyr.nectar" class="level4">
|
||
<h4 class="anchored" data-anchor-id="zephyr.nectar">zephyr.nectar</h4>
|
||
<div class="sourceCode" id="cb14"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb14-2"><a href="#cb14-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb14-3"><a href="#cb14-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"answers"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb14-4"><a href="#cb14-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||
<span id="cb14-5"><a href="#cb14-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"answer"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb14-6"><a href="#cb14-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rank"</span><span class="fu">:</span> <span class="dv">1</span></span>
|
||
<span id="cb14-7"><a href="#cb14-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb14-8"><a href="#cb14-8" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||
<span id="cb14-9"><a href="#cb14-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">"answer"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb14-10"><a href="#cb14-10" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rank"</span><span class="fu">:</span> <span class="dv">2</span></span>
|
||
<span id="cb14-11"><a href="#cb14-11" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||
<span id="cb14-12"><a href="#cb14-12" aria-hidden="true" tabindex="-1"></a> <span class="er">//</span> <span class="er">...</span> <span class="er">more</span> <span class="er">answers</span> <span class="er">with</span> <span class="er">ranks</span></span>
|
||
<span id="cb14-13"><a href="#cb14-13" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb14-14"><a href="#cb14-14" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chat_template.default" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chat_template.default">chat_template.default</h4>
|
||
<div class="sourceCode" id="cb15"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> dpo</span></span>
|
||
<span id="cb15-2"><a href="#cb15-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb15-3"><a href="#cb15-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> ...</span></span>
|
||
<span id="cb15-4"><a href="#cb15-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
|
||
<span id="cb15-5"><a href="#cb15-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template.default</span></span>
|
||
<span id="cb15-6"><a href="#cb15-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> </span><span class="st">"messages"</span></span>
|
||
<span id="cb15-7"><a href="#cb15-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_chosen</span><span class="kw">:</span><span class="at"> </span><span class="st">"chosen"</span></span>
|
||
<span id="cb15-8"><a href="#cb15-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_rejected</span><span class="kw">:</span><span class="at"> </span><span class="st">"rejected"</span></span>
|
||
<span id="cb15-9"><a href="#cb15-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_property_mappings</span><span class="kw">:</span></span>
|
||
<span id="cb15-10"><a href="#cb15-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">role</span><span class="kw">:</span><span class="at"> role</span></span>
|
||
<span id="cb15-11"><a href="#cb15-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">content</span><span class="kw">:</span><span class="at"> content</span></span>
|
||
<span id="cb15-12"><a href="#cb15-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles</span><span class="kw">:</span></span>
|
||
<span id="cb15-13"><a href="#cb15-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">user</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"user"</span><span class="kw">]</span></span>
|
||
<span id="cb15-14"><a href="#cb15-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">assistant</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"assistant"</span><span class="kw">]</span></span>
|
||
<span id="cb15-15"><a href="#cb15-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">system</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"system"</span><span class="kw">]</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>Sample input format:</p>
|
||
<div class="sourceCode" id="cb16"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb16-2"><a href="#cb16-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"messages"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb16-3"><a href="#cb16-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||
<span id="cb16-4"><a href="#cb16-4" 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="cb16-5"><a href="#cb16-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb16-6"><a href="#cb16-6" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb16-7"><a href="#cb16-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||
<span id="cb16-8"><a href="#cb16-8" 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="cb16-9"><a href="#cb16-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb16-10"><a href="#cb16-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb16-11"><a href="#cb16-11" aria-hidden="true" tabindex="-1"></a> <span class="er">//</span> <span class="er">...</span> <span class="er">more</span> <span class="er">messages</span></span>
|
||
<span id="cb16-12"><a href="#cb16-12" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
|
||
<span id="cb16-13"><a href="#cb16-13" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="fu">{</span></span>
|
||
<span id="cb16-14"><a href="#cb16-14" 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="cb16-15"><a href="#cb16-15" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb16-16"><a href="#cb16-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">},</span></span>
|
||
<span id="cb16-17"><a href="#cb16-17" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="fu">{</span></span>
|
||
<span id="cb16-18"><a href="#cb16-18" 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="cb16-19"><a href="#cb16-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb16-20"><a href="#cb16-20" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||
<span id="cb16-21"><a href="#cb16-21" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="user_defined.default" class="level4">
|
||
<h4 class="anchored" data-anchor-id="user_defined.default">user_defined.default</h4>
|
||
<p>For custom behaviors,</p>
|
||
<div class="sourceCode" id="cb17"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb17-1"><a href="#cb17-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> dpo</span></span>
|
||
<span id="cb17-2"><a href="#cb17-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb17-3"><a href="#cb17-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> ...</span></span>
|
||
<span id="cb17-4"><a href="#cb17-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
|
||
<span id="cb17-5"><a href="#cb17-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> user_defined.default</span></span>
|
||
<span id="cb17-6"><a href="#cb17-6" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb17-7"><a href="#cb17-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">"prompt"</span></span>
|
||
<span id="cb17-8"><a href="#cb17-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_system</span><span class="kw">:</span><span class="at"> </span><span class="st">"system"</span></span>
|
||
<span id="cb17-9"><a href="#cb17-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_chosen</span><span class="kw">:</span><span class="at"> </span><span class="st">"chosen"</span></span>
|
||
<span id="cb17-10"><a href="#cb17-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_rejected</span><span class="kw">:</span><span class="at"> </span><span class="st">"rejected"</span></span>
|
||
<span id="cb17-11"><a href="#cb17-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">prompt_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{prompt}"</span></span>
|
||
<span id="cb17-12"><a href="#cb17-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">chosen_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{chosen}"</span></span>
|
||
<span id="cb17-13"><a href="#cb17-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">rejected_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{rejected}"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>The input format is a simple JSON input with customizable fields based on the above config.</p>
|
||
<div class="sourceCode" id="cb18"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb18-1"><a href="#cb18-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb18-2"><a href="#cb18-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb18-3"><a href="#cb18-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb18-4"><a href="#cb18-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb18-5"><a href="#cb18-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb18-6"><a href="#cb18-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
</section>
|
||
<section id="ipo" class="level3">
|
||
<h3 class="anchored" data-anchor-id="ipo">IPO</h3>
|
||
<p>As IPO is just DPO with a different loss function, all supported options for DPO works here.</p>
|
||
<div class="sourceCode" id="cb19"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb19-1"><a href="#cb19-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> ipo</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="orpo" class="level3">
|
||
<h3 class="anchored" data-anchor-id="orpo">ORPO</h3>
|
||
<p>Paper: https://arxiv.org/abs/2403.07691</p>
|
||
<div class="sourceCode" id="cb20"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb20-1"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> orpo</span></span>
|
||
<span id="cb20-2"><a href="#cb20-2" aria-hidden="true" tabindex="-1"></a><span class="fu">orpo_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.1</span></span>
|
||
<span id="cb20-3"><a href="#cb20-3" 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="cb20-4"><a href="#cb20-4" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb20-5"><a href="#cb20-5" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> chatml</span></span>
|
||
<span id="cb20-6"><a href="#cb20-6" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb20-7"><a href="#cb20-7" 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"> argilla/ultrafeedback-binarized-preferences-cleaned</span></span>
|
||
<span id="cb20-8"><a href="#cb20-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template.argilla</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>ORPO supports the following types with the following dataset format:</p>
|
||
<section id="chat_template.argilla" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chat_template.argilla">chat_template.argilla</h4>
|
||
<div class="sourceCode" id="cb21"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb21-1"><a href="#cb21-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb21-2"><a href="#cb21-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb21-3"><a href="#cb21-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">if</span> <span class="er">available</span><span class="fu">,</span> <span class="er">will</span> <span class="er">be</span> <span class="er">taken</span> <span class="er">as</span> <span class="er">user</span> <span class="er">message</span> <span class="er">for</span> <span class="er">single-turn</span> <span class="er">instead</span> <span class="er">of</span> <span class="er">from</span> <span class="er">list</span> <span class="er">below</span></span>
|
||
<span id="cb21-4"><a href="#cb21-4" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb21-5"><a href="#cb21-5" aria-hidden="true" tabindex="-1"></a> <span class="er">//</span> <span class="er">chosen/rejected</span> <span class="er">should</span> <span class="er">be</span> <span class="er">same</span> <span class="er">till</span> <span class="er">last</span> <span class="er">content</span> <span class="er">and</span> <span class="er">only</span> <span class="er">even-number</span> <span class="er">of</span> <span class="er">alternating</span> <span class="er">user/assistant</span> <span class="er">turns</span></span>
|
||
<span id="cb21-6"><a href="#cb21-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb21-7"><a href="#cb21-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb21-8"><a href="#cb21-8" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb21-9"><a href="#cb21-9" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
|
||
<span id="cb21-10"><a href="#cb21-10" aria-hidden="true" tabindex="-1"></a> <span class="dt">"rejected"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb21-11"><a href="#cb21-11" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb21-12"><a href="#cb21-12" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb21-13"><a href="#cb21-13" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb21-14"><a href="#cb21-14" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
</section>
|
||
<section id="kto" class="level3">
|
||
<h3 class="anchored" data-anchor-id="kto">KTO</h3>
|
||
<div class="sourceCode" id="cb22"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb22-1"><a href="#cb22-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> kto</span></span>
|
||
<span id="cb22-2"><a href="#cb22-2" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_beta</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.5</span></span>
|
||
<span id="cb22-3"><a href="#cb22-3" aria-hidden="true" tabindex="-1"></a><span class="fu">kto_desirable_weight</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.2</span></span>
|
||
<span id="cb22-4"><a href="#cb22-4" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb22-5"><a href="#cb22-5" 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="cb22-6"><a href="#cb22-6" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb22-7"><a href="#cb22-7" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb22-8"><a href="#cb22-8" 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"> argilla/ultrafeedback-binarized-preferences-cleaned-kto</span></span>
|
||
<span id="cb22-9"><a href="#cb22-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> llama3.ultra</span></span>
|
||
<span id="cb22-10"><a href="#cb22-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
|
||
<span id="cb22-11"><a href="#cb22-11" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb22-12"><a href="#cb22-12" aria-hidden="true" tabindex="-1"></a><span class="fu">gradient_checkpointing</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb22-13"><a href="#cb22-13" aria-hidden="true" tabindex="-1"></a><span class="fu">gradient_checkpointing_kwargs</span><span class="kw">:</span></span>
|
||
<span id="cb22-14"><a href="#cb22-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">use_reentrant</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>KTO supports the following types with the following dataset format:</p>
|
||
<section id="chatml.argilla-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.argilla-1">chatml.argilla</h4>
|
||
<div class="sourceCode" id="cb23"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb23-1"><a href="#cb23-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb23-2"><a href="#cb23-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb23-3"><a href="#cb23-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb23-4"><a href="#cb23-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb23-5"><a href="#cb23-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.argilla_chat-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.argilla_chat-1">chatml.argilla_chat</h4>
|
||
<div class="sourceCode" id="cb24"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb24-1"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb24-2"><a href="#cb24-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"chosen"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb24-3"><a href="#cb24-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb24-4"><a href="#cb24-4" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span><span class="fu">,</span></span>
|
||
<span id="cb24-5"><a href="#cb24-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb24-6"><a href="#cb24-6" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb24-7"><a href="#cb24-7" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb24-8"><a href="#cb24-8" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.intel-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.intel-1">chatml.intel</h4>
|
||
<div class="sourceCode" id="cb25"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb25-1"><a href="#cb25-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb25-2"><a href="#cb25-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb25-3"><a href="#cb25-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"question"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb25-4"><a href="#cb25-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb25-5"><a href="#cb25-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.prompt_pairs-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.prompt_pairs-1">chatml.prompt_pairs</h4>
|
||
<div class="sourceCode" id="cb26"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb26-1"><a href="#cb26-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb26-2"><a href="#cb26-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb26-3"><a href="#cb26-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb26-4"><a href="#cb26-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb26-5"><a href="#cb26-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="chatml.ultra-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="chatml.ultra-1">chatml.ultra</h4>
|
||
<div class="sourceCode" id="cb27"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb27-1"><a href="#cb27-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb27-2"><a href="#cb27-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb27-3"><a href="#cb27-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb27-4"><a href="#cb27-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb27-5"><a href="#cb27-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.argilla-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.argilla-1">llama3.argilla</h4>
|
||
<div class="sourceCode" id="cb28"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb28-1"><a href="#cb28-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb28-2"><a href="#cb28-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb28-3"><a href="#cb28-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb28-4"><a href="#cb28-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb28-5"><a href="#cb28-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.argilla_chat-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.argilla_chat-1">llama3.argilla_chat</h4>
|
||
<div class="sourceCode" id="cb29"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb29-1"><a href="#cb29-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb29-2"><a href="#cb29-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||
<span id="cb29-3"><a href="#cb29-3" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">,</span></span>
|
||
<span id="cb29-4"><a href="#cb29-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span> <span class="dt">"content"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span>
|
||
<span id="cb29-5"><a href="#cb29-5" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||
<span id="cb29-6"><a href="#cb29-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.intel-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.intel-1">llama3.intel</h4>
|
||
<div class="sourceCode" id="cb30"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb30-1"><a href="#cb30-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb30-2"><a href="#cb30-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb30-3"><a href="#cb30-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"question"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb30-4"><a href="#cb30-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb30-5"><a href="#cb30-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.prompt_pairs-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.prompt_pairs-1">llama3.prompt_pairs</h4>
|
||
<div class="sourceCode" id="cb31"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb31-1"><a href="#cb31-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb31-2"><a href="#cb31-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb31-3"><a href="#cb31-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb31-4"><a href="#cb31-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb31-5"><a href="#cb31-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="llama3.ultra-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="llama3.ultra-1">llama3.ultra</h4>
|
||
<div class="sourceCode" id="cb32"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb32-1"><a href="#cb32-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb32-2"><a href="#cb32-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb32-3"><a href="#cb32-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb32-4"><a href="#cb32-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb32-5"><a href="#cb32-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="user_defined.default-1" class="level4">
|
||
<h4 class="anchored" data-anchor-id="user_defined.default-1">user_defined.default</h4>
|
||
<p>For custom behaviors,</p>
|
||
<div class="sourceCode" id="cb33"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb33-1"><a href="#cb33-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> kto</span></span>
|
||
<span id="cb33-2"><a href="#cb33-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb33-3"><a href="#cb33-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> ...</span></span>
|
||
<span id="cb33-4"><a href="#cb33-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
|
||
<span id="cb33-5"><a href="#cb33-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> user_defined.default</span></span>
|
||
<span id="cb33-6"><a href="#cb33-6" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb33-7"><a href="#cb33-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">"prompt"</span></span>
|
||
<span id="cb33-8"><a href="#cb33-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_system</span><span class="kw">:</span><span class="at"> </span><span class="st">"system"</span></span>
|
||
<span id="cb33-9"><a href="#cb33-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_completion</span><span class="kw">:</span><span class="at"> </span><span class="st">"completion"</span></span>
|
||
<span id="cb33-10"><a href="#cb33-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_label</span><span class="kw">:</span><span class="at"> </span><span class="st">"label"</span></span>
|
||
<span id="cb33-11"><a href="#cb33-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">prompt_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{prompt}"</span></span>
|
||
<span id="cb33-12"><a href="#cb33-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">completion_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"{completion}"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>The input format is a simple JSON input with customizable fields based on the above config.</p>
|
||
<div class="sourceCode" id="cb34"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb34-1"><a href="#cb34-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||
<span id="cb34-2"><a href="#cb34-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"system"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="er">//</span> <span class="er">optional</span></span>
|
||
<span id="cb34-3"><a href="#cb34-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"prompt"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb34-4"><a href="#cb34-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"completion"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span></span>
|
||
<span id="cb34-5"><a href="#cb34-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"label"</span><span class="fu">:</span> <span class="st">"..."</span></span>
|
||
<span id="cb34-6"><a href="#cb34-6" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
</section>
|
||
<section id="grpo" class="level3">
|
||
<h3 class="anchored" data-anchor-id="grpo">GRPO</h3>
|
||
<p>GRPO uses custom reward functions and transformations. Please have them ready locally.</p>
|
||
<p>For ex, to load OpenAI’s GSM8K and use a random reward for completions:</p>
|
||
<div class="sourceCode" id="cb35"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb35-1"><a href="#cb35-1" aria-hidden="true" tabindex="-1"></a><span class="co"># rewards.py</span></span>
|
||
<span id="cb35-2"><a href="#cb35-2" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> random</span>
|
||
<span id="cb35-3"><a href="#cb35-3" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb35-4"><a href="#cb35-4" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> rand_reward_func(completions, <span class="op">**</span>kwargs) <span class="op">-></span> <span class="bu">list</span>[<span class="bu">float</span>]:</span>
|
||
<span id="cb35-5"><a href="#cb35-5" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> [random.uniform(<span class="dv">0</span>, <span class="dv">1</span>) <span class="cf">for</span> _ <span class="kw">in</span> completions]</span>
|
||
<span id="cb35-6"><a href="#cb35-6" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb35-7"><a href="#cb35-7" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> oai_gsm8k_transform(cfg, <span class="op">*</span>args, <span class="op">**</span>kwargs):</span>
|
||
<span id="cb35-8"><a href="#cb35-8" aria-hidden="true" tabindex="-1"></a> <span class="kw">def</span> transform_fn(example, tokenizer<span class="op">=</span><span class="va">None</span>):</span>
|
||
<span id="cb35-9"><a href="#cb35-9" aria-hidden="true" tabindex="-1"></a> label <span class="op">=</span> example[<span class="st">"answer"</span>].split(<span class="st">"####"</span>)[<span class="op">-</span><span class="dv">1</span>].strip().replace(<span class="st">","</span>, <span class="st">""</span>)</span>
|
||
<span id="cb35-10"><a href="#cb35-10" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> {</span>
|
||
<span id="cb35-11"><a href="#cb35-11" aria-hidden="true" tabindex="-1"></a> <span class="st">"prompt"</span>: [{<span class="st">"role"</span>: <span class="st">"user"</span>, <span class="st">"content"</span>: example[<span class="st">"question"</span>]},],</span>
|
||
<span id="cb35-12"><a href="#cb35-12" aria-hidden="true" tabindex="-1"></a> <span class="st">"answer"</span>: label,</span>
|
||
<span id="cb35-13"><a href="#cb35-13" aria-hidden="true" tabindex="-1"></a> }</span>
|
||
<span id="cb35-14"><a href="#cb35-14" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> transform_fn, {<span class="st">"remove_columns"</span>: [<span class="st">"question"</span>]}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<div class="sourceCode" id="cb36"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb36-1"><a href="#cb36-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> grpo</span></span>
|
||
<span id="cb36-2"><a href="#cb36-2" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb36-3"><a href="#cb36-3" aria-hidden="true" tabindex="-1"></a><span class="fu">trl</span><span class="kw">:</span></span>
|
||
<span id="cb36-4"><a href="#cb36-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">beta</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.001</span></span>
|
||
<span id="cb36-5"><a href="#cb36-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">max_completion_length</span><span class="kw">:</span><span class="at"> </span><span class="dv">256</span></span>
|
||
<span id="cb36-6"><a href="#cb36-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">use_vllm</span><span class="kw">:</span><span class="at"> </span><span class="ch">True</span></span>
|
||
<span id="cb36-7"><a href="#cb36-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_device</span><span class="kw">:</span><span class="at"> auto</span></span>
|
||
<span id="cb36-8"><a href="#cb36-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_gpu_memory_utilization</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.15</span></span>
|
||
<span id="cb36-9"><a href="#cb36-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">num_generations</span><span class="kw">:</span><span class="at"> </span><span class="dv">4</span></span>
|
||
<span id="cb36-10"><a href="#cb36-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_funcs</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"rewards.rand_reward_func"</span><span class="kw">]</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span>
|
||
<span id="cb36-11"><a href="#cb36-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_weights</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="fl">1.0</span><span class="kw">]</span></span>
|
||
<span id="cb36-12"><a href="#cb36-12" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb36-13"><a href="#cb36-13" 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"> openai/gsm8k</span></span>
|
||
<span id="cb36-14"><a href="#cb36-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> main</span></span>
|
||
<span id="cb36-15"><a href="#cb36-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> rewards.oai_gsm8k_transform</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>To see other examples of custom reward functions, please see <a href="https://github.com/huggingface/trl/blob/main/docs/source/grpo_trainer.md#using-a-custom-reward-function">TRL GRPO Docs</a>.</p>
|
||
<p>To see description of the configs, please see <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/src/axolotl/utils/config/models/input/v0_4_1/trl.py">TRLConfig</a>.</p>
|
||
</section>
|
||
<section id="using-local-dataset-files" class="level3">
|
||
<h3 class="anchored" data-anchor-id="using-local-dataset-files">Using local dataset files</h3>
|
||
<div class="sourceCode" id="cb37"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb37-1"><a href="#cb37-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||
<span id="cb37-2"><a href="#cb37-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">ds_type</span><span class="kw">:</span><span class="at"> json</span></span>
|
||
<span id="cb37-3"><a href="#cb37-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">data_files</span><span class="kw">:</span></span>
|
||
<span id="cb37-4"><a href="#cb37-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> orca_rlhf.jsonl</span></span>
|
||
<span id="cb37-5"><a href="#cb37-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
|
||
<span id="cb37-6"><a href="#cb37-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chatml.intel</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="trl-auto-unwrapping-for-peft" class="level3">
|
||
<h3 class="anchored" data-anchor-id="trl-auto-unwrapping-for-peft">TRL auto-unwrapping for PEFT</h3>
|
||
<p>TRL supports auto-unwrapping PEFT models for RL training paradigms which rely on a reference model. This significantly reduces memory pressure as an additional refreference model does not need to be loaded, and reference model log-probabilities can be obtained by disabling PEFT adapters. This is enabled by default. To turn it off, pass the following config:</p>
|
||
<div class="sourceCode" id="cb38"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb38-1"><a href="#cb38-1" aria-hidden="true" tabindex="-1"></a><span class="co"># load ref model when adapter training.</span></span>
|
||
<span id="cb38-2"><a href="#cb38-2" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_adapter_ref_model</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
|
||
|
||
</section>
|
||
</section>
|
||
|
||
</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> |