Files
axolotl/docs/api/utils.samplers.multipack.html
Quarto GHA Workflow Runner 3c421e0170 Built site for gh-pages
2026-03-22 13:17:42 +00:00

1733 lines
71 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!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-1.9.36">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
<title>utils.samplers.multipack Axolotl</title>
<style>
/* Default styles provided by pandoc.
** See https://pandoc.org/MANUAL.html#variables-for-html for config info.
*/
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 */
html { -webkit-text-size-adjust: 100%; }
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { display: inline-block; 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 { 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" type="module"></script>
<script src="../../site_libs/quarto-html/tabsets/tabsets.js" type="module"></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-f418161beb48e0141c760e455f12af2c.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-f15b14cef494beb09422a8174b542cad.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>
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-9KYCVJBNMQ"></script>
<script type="text/javascript">
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</script>
<link rel="stylesheet" href="../../styles.css">
</head>
<body class="nav-sidebar docked nav-fixed quarto-light">
<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 light-content">
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo dark-content">
</a>
</div>
<div class="quarto-navbar-tools tools-wide tools-end">
<a href="https://twitter.com/axolotl_ai" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-twitter"></i></a>
<a href="https://github.com/axolotl-ai-cloud/axolotl/" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-github"></i></a>
<a href="https://discord.gg/7m9sfhzaf3" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-discord"></i></a>
</div>
<div id="quarto-search" class="" title="Search"></div>
</div> <!-- /container-fluid -->
</nav>
<nav class="quarto-secondary-nav">
<div class="container-fluid d-flex">
<button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
<i class="bi bi-layout-text-sidebar-reverse"></i>
</button>
<nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"></ol></nav>
<a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
</a>
</div>
</nav>
</header>
<!-- content -->
<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article page-navbar">
<!-- sidebar -->
<nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto">
<div class="sidebar-menu-container">
<ul class="list-unstyled mt-1">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../index.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Home</span></a>
</div>
</li>
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true">
<span class="menu-text">Getting Started</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/getting-started.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Quickstart</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/installation.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Installation</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/inference.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Inference and Merging</span></a>
</div>
</li>
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a class="sidebar-item-text sidebar-link text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="false">
<span class="menu-text">Model Guides</span></a>
<a class="sidebar-item-toggle text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="false" 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 depth2 ">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/kimi-linear.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Kimi Linear</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/plano.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Plano Orchestrator</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/mimo.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">MiMo</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/internvl3_5.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">InternVL 3.5</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/olmo3.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">OLMo 3</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/trinity.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Trinity</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/arcee.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Arcee AFM</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 collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="false">
<span class="menu-text">Ministral3</span></a>
<a class="sidebar-item-toggle text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="false" 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 depth3 ">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/ministral3.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Ministral3</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/ministral3/think.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Ministral 3 Thinking</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/ministral3/vision.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Ministral 3 Vision</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 collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="false">
<span class="menu-text">Magistral</span></a>
<a class="sidebar-item-toggle text-start collapsed" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="false" 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 depth3 ">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/magistral.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Magistral</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/magistral/think.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Magistral Thinking</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/magistral/vision.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Magistral Vision</span></a>
</div>
</li>
</ul>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/ministral.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Ministral</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/mistral-small.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Mistral Small 3.1/3.2</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/voxtral.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Voxtral</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/devstral.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Devstral</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/mistral.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Mistral 7B</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/llama-4.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Llama 4</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/llama-2.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Llama 2</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/qwen3-next.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Qwen 3 Next</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/qwen3.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Qwen 3</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/gemma3n.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Gemma 3n</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/apertus.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Apertus</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/gpt-oss.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">GPT-OSS</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/seed-oss.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Seed-OSS</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/phi.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Phi</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/smolvlm2.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">SmolVLM 2</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/granite4.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Granite 4</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/LiquidAI.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Liquid Foundation Models 2</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/hunyuan.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Hunyuan</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/jamba.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Jamba</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/models/orpheus.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Orpheus</span></a>
</div>
</li>
</ul>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Command Line Interface (CLI)</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/telemetry.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Telemetry</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/config-reference.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Config Reference</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/api" class="sidebar-item-text sidebar-link">
<span class="menu-text">API Reference</span></a>
</div>
</li>
</ul>
</li>
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a href="../../docs/dataset-formats/index.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Dataset Formats</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-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/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-6" 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-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/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-7" 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-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/multimodal.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">MultiModal / Vision Language Models (BETA)</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/rlhf.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">RLHF (Beta)</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/reward_modelling.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Reward Modelling</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/lr_groups.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Learning Rate Groups</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/lora_optims.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">LoRA Optimizations</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/dataset_loading.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Dataset Loading</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/qat.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Quantization Aware Training (QAT)</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/quantize.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Quantization with torchao</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/optimizations.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Optimizations Guide</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">Core Concepts</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/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/streaming.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Streaming Datasets</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>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/mixed_precision.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Mixed Precision Training</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/optimizers.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Optimizers</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/attention.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Attention</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-9" 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-9" 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-9" 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">FSDP + 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>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/sequence_parallelism.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Sequence Parallelism</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/gradient_checkpointing.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Gradient Checkpointing, Activation Offloading, and Layer Offloading</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/nd_parallelism.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">N-D Parallelism (Beta)</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/expert_quantization.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">MoE Expert Quantization</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-10" 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-10" 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-10" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/faq.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">FAQ</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/debugging.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Debugging</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/nccl.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">NCCL</span></a>
</div>
</li>
</ul>
</li>
</ul>
</div>
</nav>
<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
<!-- margin-sidebar -->
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
<nav id="TOC" role="doc-toc" class="toc-active">
<h2 id="toc-title">On this page</h2>
<ul>
<li><a href="#axolotl.utils.samplers.multipack" id="toc-axolotl.utils.samplers.multipack" class="nav-link active" data-scroll-target="#axolotl.utils.samplers.multipack">utils.samplers.multipack</a>
<ul class="collapse">
<li><a href="#classes" id="toc-classes" class="nav-link" data-scroll-target="#classes">Classes</a>
<ul class="collapse">
<li><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler" id="toc-axolotl.utils.samplers.multipack.MultipackBatchSampler" class="nav-link" data-scroll-target="#axolotl.utils.samplers.multipack.MultipackBatchSampler">MultipackBatchSampler</a></li>
</ul></li>
<li><a href="#functions" id="toc-functions" class="nav-link" data-scroll-target="#functions">Functions</a>
<ul class="collapse">
<li><a href="#axolotl.utils.samplers.multipack.allocate_sequentially" id="toc-axolotl.utils.samplers.multipack.allocate_sequentially" class="nav-link" data-scroll-target="#axolotl.utils.samplers.multipack.allocate_sequentially">allocate_sequentially</a></li>
<li><a href="#axolotl.utils.samplers.multipack.ffd_check" id="toc-axolotl.utils.samplers.multipack.ffd_check" class="nav-link" data-scroll-target="#axolotl.utils.samplers.multipack.ffd_check">ffd_check</a></li>
<li><a href="#axolotl.utils.samplers.multipack.pack_group" id="toc-axolotl.utils.samplers.multipack.pack_group" class="nav-link" data-scroll-target="#axolotl.utils.samplers.multipack.pack_group">pack_group</a></li>
<li><a href="#axolotl.utils.samplers.multipack.pack_parallel" id="toc-axolotl.utils.samplers.multipack.pack_parallel" class="nav-link" data-scroll-target="#axolotl.utils.samplers.multipack.pack_parallel">pack_parallel</a></li>
</ul></li>
</ul></li>
</ul>
</nav>
</div>
<!-- main -->
<main class="content" id="quarto-document-content"><header id="title-block-header" class="quarto-title-block"></header>
<section id="axolotl.utils.samplers.multipack" class="level1">
<h1>utils.samplers.multipack</h1>
<p><code>utils.samplers.multipack</code></p>
<p>Multipack Batch Sampler - An efficient batch sampler for packing variable-length sequences
into fixed-capacity batches to optimize memory usage and training throughput.</p>
<section id="classes" class="level2">
<h2 class="anchored" data-anchor-id="classes">Classes</h2>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler">MultipackBatchSampler</a></td>
<td>Batch sampler class for efficient packing of variable-length sequences</td>
</tr>
</tbody>
</table>
<section id="axolotl.utils.samplers.multipack.MultipackBatchSampler" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.MultipackBatchSampler">MultipackBatchSampler</h3>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.MultipackBatchSampler(</span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a> sampler,</span>
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a> batch_size,</span>
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a> batch_max_len,</span>
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a> lengths,</span>
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a> bin_size,</span>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a> packing_efficiency_estimate<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a> drop_last<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a> num_count_samples<span class="op">=</span><span class="dv">4</span>,</span>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a> sequential<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a> group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a> num_processes<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a> safe_mode<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a> mp_start_method<span class="op">=</span><span class="st">'fork'</span>,</span>
<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a> <span class="op">**</span>kwargs,</span>
<span id="cb1-16"><a href="#cb1-16" aria-hidden="true" tabindex="-1"></a>)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Batch sampler class for efficient packing of variable-length sequences</p>
<p>This sampler packs sequences into fixed-capacity bins (batches) to maximize
GPU memory utilization and training throughput by reducing padding.</p>
<p>It supports both parallel packing (using FFD algorithm) and
sequential packing (preserving original sequence order).</p>
<section id="methods" class="level4">
<h4 class="anchored" data-anchor-id="methods">Methods</h4>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler.efficiency">efficiency</a></td>
<td>Calculate the packing efficiency (ratio of tokens used to total token slots).</td>
</tr>
<tr class="even">
<td><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler.gather_efficiency">gather_efficiency</a></td>
<td>Gather and synchronize packing efficiency estimates across all distributed</td>
</tr>
<tr class="odd">
<td><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler.gather_len_batches">gather_len_batches</a></td>
<td>Gather and synchronize batch counts across all distributed ranks. Returns</td>
</tr>
<tr class="even">
<td><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler.generate_batches">generate_batches</a></td>
<td>Generate packed batches for training.</td>
</tr>
<tr class="odd">
<td><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler.set_epoch">set_epoch</a></td>
<td>Set the epoch number, used for reproducible shuffling across epochs</td>
</tr>
</tbody>
</table>
<section id="axolotl.utils.samplers.multipack.MultipackBatchSampler.efficiency" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.MultipackBatchSampler.efficiency">efficiency</h5>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.MultipackBatchSampler.efficiency()</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Calculate the packing efficiency (ratio of tokens used to total token slots).
Higher is better - 1.0 would mean perfect packing with no wasted space.</p>
</section>
<section id="axolotl.utils.samplers.multipack.MultipackBatchSampler.gather_efficiency" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.MultipackBatchSampler.gather_efficiency">gather_efficiency</h5>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.MultipackBatchSampler.gather_efficiency()</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Gather and synchronize packing efficiency estimates across all distributed
ranks.</p>
<section id="returns" class="level6 doc-section doc-section-returns">
<h6 class="doc-section doc-section-returns anchored" data-anchor-id="returns">Returns</h6>
<table class="caption-top table">
<colgroup>
<col style="width: 10%">
<col style="width: 10%">
<col style="width: 79%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td></td>
<td>float</td>
<td>A conservative efficiency estimate based on the measurements.</td>
</tr>
</tbody>
</table>
</section>
</section>
<section id="axolotl.utils.samplers.multipack.MultipackBatchSampler.gather_len_batches" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.MultipackBatchSampler.gather_len_batches">gather_len_batches</h5>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.MultipackBatchSampler.gather_len_batches(num)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Gather and synchronize batch counts across all distributed ranks. Returns
the minimum number of batches available on any rank.</p>
</section>
<section id="axolotl.utils.samplers.multipack.MultipackBatchSampler.generate_batches" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.MultipackBatchSampler.generate_batches">generate_batches</h5>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.MultipackBatchSampler.generate_batches(set_stats<span class="op">=</span><span class="va">False</span>)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Generate packed batches for training.</p>
<section id="parameters" class="level6 doc-section doc-section-parameters">
<h6 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters">Parameters</h6>
<table class="caption-top table">
<colgroup>
<col style="width: 15%">
<col style="width: 11%">
<col style="width: 58%">
<col style="width: 15%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>set_stats</td>
<td>bool</td>
<td>Whether to update efficiency statistics.</td>
<td><code>False</code></td>
</tr>
</tbody>
</table>
</section>
<section id="returns-1" class="level6 doc-section doc-section-returns">
<h6 class="doc-section doc-section-returns anchored" data-anchor-id="returns-1">Returns</h6>
<table class="caption-top table">
<colgroup>
<col style="width: 5%">
<col style="width: 20%">
<col style="width: 74%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td></td>
<td>list[list[list[int]]]</td>
<td>List of batches, where each batch contains multiple bins, and each bin contains multiple sequence indices.</td>
</tr>
</tbody>
</table>
</section>
</section>
<section id="axolotl.utils.samplers.multipack.MultipackBatchSampler.set_epoch" class="level5">
<h5 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.MultipackBatchSampler.set_epoch">set_epoch</h5>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.MultipackBatchSampler.set_epoch(epoch)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Set the epoch number, used for reproducible shuffling across epochs</p>
</section>
</section>
</section>
</section>
<section id="functions" class="level2">
<h2 class="anchored" data-anchor-id="functions">Functions</h2>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td><a href="#axolotl.utils.samplers.multipack.allocate_sequentially">allocate_sequentially</a></td>
<td>Sequential allocator that preserves example order.</td>
</tr>
<tr class="even">
<td><a href="#axolotl.utils.samplers.multipack.ffd_check">ffd_check</a></td>
<td>First-fit-decreasing bin packing algorithm check.</td>
</tr>
<tr class="odd">
<td><a href="#axolotl.utils.samplers.multipack.pack_group">pack_group</a></td>
<td>Pack a group of sequences into bins using First-Fit Decreasing algorithm.</td>
</tr>
<tr class="even">
<td><a href="#axolotl.utils.samplers.multipack.pack_parallel">pack_parallel</a></td>
<td>Pack sequences into bins using parallel processing.</td>
</tr>
</tbody>
</table>
<section id="axolotl.utils.samplers.multipack.allocate_sequentially" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.allocate_sequentially">allocate_sequentially</h3>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb7"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.allocate_sequentially(</span>
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a> sequence_lengths,</span>
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a> rank,</span>
<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a> bin_capacity,</span>
<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a> num_ranks,</span>
<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a>)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Sequential allocator that preserves example order.</p>
<section id="parameters-1" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-1">Parameters</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 18%">
<col style="width: 12%">
<col style="width: 55%">
<col style="width: 12%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>sequence_lengths</td>
<td>np.ndarray</td>
<td>The lengths of all examples.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>rank</td>
<td>int</td>
<td>The current rank (for distributed training).</td>
<td><em>required</em></td>
</tr>
<tr class="odd">
<td>bin_capacity</td>
<td>int</td>
<td>The capacity of each bin (maximum sequence length).</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>num_ranks</td>
<td>int</td>
<td>Number of ranks (processes / GPUs).</td>
<td><em>required</em></td>
</tr>
</tbody>
</table>
</section>
<section id="returns-2" class="level4 doc-section doc-section-returns">
<h4 class="doc-section doc-section-returns anchored" data-anchor-id="returns-2">Returns</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 15%">
<col style="width: 17%">
<col style="width: 66%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>rank_batches</td>
<td>list[list[int]]</td>
<td>List of batches for the current rank.</td>
</tr>
<tr class="even">
<td>total_tokens_used</td>
<td>int</td>
<td>Number of actual example tokens.</td>
</tr>
<tr class="odd">
<td>total_token_slots</td>
<td>int</td>
<td>Maximum theoretical number of example tokens (number of bins * bin capacity).</td>
</tr>
</tbody>
</table>
</section>
</section>
<section id="axolotl.utils.samplers.multipack.ffd_check" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.ffd_check">ffd_check</h3>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb8"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.ffd_check(sequence_lengths, bin_capacity, num_bins)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>First-fit-decreasing bin packing algorithm check.</p>
<p>Checks if sequences with the given lengths could fit in the specified number of
bins.</p>
<section id="parameters-2" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-2">Parameters</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 24%">
<col style="width: 16%">
<col style="width: 42%">
<col style="width: 16%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>sequence_lengths</td>
<td>np.ndarray</td>
<td>Array of sequence lengths.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>bin_capacity</td>
<td>int</td>
<td>Maximum capacity of each bin.</td>
<td><em>required</em></td>
</tr>
<tr class="odd">
<td>num_bins</td>
<td>int</td>
<td>Number of bins available.</td>
<td><em>required</em></td>
</tr>
</tbody>
</table>
</section>
<section id="returns-3" class="level4 doc-section doc-section-returns">
<h4 class="doc-section doc-section-returns anchored" data-anchor-id="returns-3">Returns</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 10%">
<col style="width: 10%">
<col style="width: 78%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td></td>
<td>bool</td>
<td><code>True</code> if all sequences can be packed, <code>False</code> otherwise.</td>
</tr>
</tbody>
</table>
</section>
</section>
<section id="axolotl.utils.samplers.multipack.pack_group" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.pack_group">pack_group</h3>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb9"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.pack_group(</span>
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a> sequence_lengths,</span>
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a> group_offset,</span>
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a> bin_capacity,</span>
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a> max_bins,</span>
<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a> bin_size,</span>
<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a> safe_mode<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a>)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Pack a group of sequences into bins using First-Fit Decreasing algorithm.</p>
<section id="parameters-3" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-3">Parameters</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 19%">
<col style="width: 12%">
<col style="width: 55%">
<col style="width: 12%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>sequence_lengths</td>
<td>np.ndarray</td>
<td>Array of sequence lengths.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>group_offset</td>
<td>int</td>
<td>Offset to apply to indices when returning results.</td>
<td><em>required</em></td>
</tr>
<tr class="odd">
<td>bin_capacity</td>
<td>int</td>
<td>Maximum capacity of each bin.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>max_bins</td>
<td>int</td>
<td>Maximum number of bins to use.</td>
<td><em>required</em></td>
</tr>
<tr class="odd">
<td>bin_size</td>
<td>int</td>
<td>Maximum number of sequences per bin.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>safe_mode</td>
<td>bool</td>
<td>If True, use a more conservative packing approach.</td>
<td><code>True</code></td>
</tr>
</tbody>
</table>
</section>
<section id="returns-4" class="level4 doc-section doc-section-returns">
<h4 class="doc-section doc-section-returns anchored" data-anchor-id="returns-4">Returns</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 7%">
<col style="width: 20%">
<col style="width: 72%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td></td>
<td>list[list[int]]</td>
<td>List of bins, where each bin contains indices of sequences assigned to it.</td>
</tr>
</tbody>
</table>
</section>
</section>
<section id="axolotl.utils.samplers.multipack.pack_parallel" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.pack_parallel">pack_parallel</h3>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>utils.samplers.multipack.pack_parallel(</span>
<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a> sequence_lengths,</span>
<span id="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a> bin_capacity,</span>
<span id="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a> group_size,</span>
<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a> bin_size,</span>
<span id="cb10-6"><a href="#cb10-6" aria-hidden="true" tabindex="-1"></a> num_processes<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb10-7"><a href="#cb10-7" aria-hidden="true" tabindex="-1"></a> safe_mode<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb10-8"><a href="#cb10-8" aria-hidden="true" tabindex="-1"></a> mp_start_method<span class="op">=</span><span class="st">'fork'</span>,</span>
<span id="cb10-9"><a href="#cb10-9" aria-hidden="true" tabindex="-1"></a>)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Pack sequences into bins using parallel processing.</p>
<section id="parameters-4" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-4">Parameters</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 8%">
<col style="width: 6%">
<col style="width: 79%">
<col style="width: 5%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>sequence_lengths</td>
<td>np.ndarray</td>
<td>Array of sequence lengths.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>bin_capacity</td>
<td>int</td>
<td>Maximum capacity of each bin as total number of tokens.</td>
<td><em>required</em></td>
</tr>
<tr class="odd">
<td>group_size</td>
<td>int</td>
<td>Number of sequences to process in each group.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>bin_size</td>
<td>int</td>
<td>Maximum number of bins to use.</td>
<td><em>required</em></td>
</tr>
<tr class="odd">
<td>num_processes</td>
<td>int | None</td>
<td>Number of parallel processes to use.</td>
<td><code>None</code></td>
</tr>
<tr class="even">
<td>safe_mode</td>
<td>bool</td>
<td>If True, use a more conservative packing approach.</td>
<td><code>True</code></td>
</tr>
<tr class="odd">
<td>mp_start_method</td>
<td>str | None</td>
<td>Multiprocessing start method (fork, spawn, forkserver). spawn is often safer with Numba/PyTorch. Set to None to use system default.</td>
<td><code>'fork'</code></td>
</tr>
</tbody>
</table>
<p>Returns:
List of bins, where each bin contains indices of sequences assigned to it.</p>
</section>
</section>
</section>
</section>
</main> <!-- /main -->
<script id="quarto-html-after-body" type="application/javascript">
window.document.addEventListener("DOMContentLoaded", function (event) {
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 outerScaffold = trigger.parentElement.cloneNode(true);
const codeEl = outerScaffold.querySelector('code');
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:\/\/docs\.axolotl\.ai");
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>