Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -2,7 +2,7 @@
|
||||
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
|
||||
|
||||
<meta charset="utf-8">
|
||||
<meta name="generator" content="quarto-1.7.34">
|
||||
<meta name="generator" content="quarto-1.8.24">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
|
||||
|
||||
@@ -68,14 +68,15 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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/axe/axe-check.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-befe23ebd2f54d8af2c8a89d1a1611f1.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../site_libs/quarto-html/quarto-syntax-highlighting-dark-b651517ce65839d647a86e2780455cfb.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-e9895ec3143e9833a687747e8d39d226.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
|
||||
<link href="../site_libs/bootstrap/bootstrap-f9d679a32da2b248d4ca48a0e58e089e.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,
|
||||
@@ -125,7 +126,8 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<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">
|
||||
<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">
|
||||
@@ -151,6 +153,10 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<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="pt-lg-2 mt-2 text-left sidebar-header">
|
||||
<a href="../index.html" class="sidebar-logo-link">
|
||||
</a>
|
||||
</div>
|
||||
<div class="sidebar-menu-container">
|
||||
<ul class="list-unstyled mt-1">
|
||||
<li class="sidebar-item">
|
||||
@@ -573,12 +579,12 @@ Note
|
||||
<section id="basic-streaming" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="basic-streaming">Basic Streaming</h3>
|
||||
<p>Enable streaming mode by setting the <code>streaming</code> flag:</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">streaming</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>
|
||||
<div class="code-copy-outer-scaffold"><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">streaming</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="pretraining-with-streaming" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="pretraining-with-streaming">Pretraining with Streaming</h3>
|
||||
<p>For pretraining tasks, streaming is automatically enabled when using <code>pretraining_dataset</code>:</p>
|
||||
<div class="sourceCode" id="cb2"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb2"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
|
||||
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> HuggingFaceFW/fineweb-edu</span></span>
|
||||
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> pretrain</span></span>
|
||||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">text_column</span><span class="kw">:</span><span class="at"> text</span></span>
|
||||
@@ -586,12 +592,12 @@ Note
|
||||
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Optionally, enable sample packing</span></span>
|
||||
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="fu">streaming_multipack_buffer_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">10000</span></span>
|
||||
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</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>
|
||||
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sft-with-streaming" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sft-with-streaming">SFT with Streaming</h3>
|
||||
<p>For supervised fine-tuning with streaming:</p>
|
||||
<div class="sourceCode" id="cb3"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">streaming</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb3"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">streaming</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb3-3"><a href="#cb3-3" 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"> tatsu-lab/alpaca</span></span>
|
||||
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> alpaca</span></span>
|
||||
@@ -599,7 +605,7 @@ Note
|
||||
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Optionally, enable sample packing</span></span>
|
||||
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a><span class="fu">streaming_multipack_buffer_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">10000</span></span>
|
||||
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</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>
|
||||
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="configuration-options" class="level2">
|
||||
@@ -620,12 +626,12 @@ memory for the shuffle buffer.</p>
|
||||
<h2 class="anchored" data-anchor-id="sample-packing-with-streaming">Sample Packing with Streaming</h2>
|
||||
<p>Sample packing is supported for streaming datasets. When enabled, multiple samples are
|
||||
packed into a single sequence to maximize GPU utilization:</p>
|
||||
<div class="sourceCode" id="cb4"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb4"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a><span class="fu">streaming_multipack_buffer_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">10000</span></span>
|
||||
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a><span class="co"># For SFT: attention is automatically isolated between packed samples</span></span>
|
||||
<span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a><span class="co"># For pretraining: control with pretrain_multipack_attn</span></span>
|
||||
<span id="cb4-6"><a href="#cb4-6" aria-hidden="true" tabindex="-1"></a><span class="fu">pretrain_multipack_attn</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span><span class="co"> # prevent cross-attention between packed samples</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<span id="cb4-6"><a href="#cb4-6" aria-hidden="true" tabindex="-1"></a><span class="fu">pretrain_multipack_attn</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span><span class="co"> # prevent cross-attention between packed samples</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
<p>For more information, see our <a href="../docs/multipack.html">documentation</a> on multipacking.</p>
|
||||
</section>
|
||||
<section id="important-considerations" class="level2">
|
||||
@@ -717,13 +723,14 @@ loaded normally even when training uses streaming.</p>
|
||||
e.clearSelection();
|
||||
}
|
||||
const getTextToCopy = function(trigger) {
|
||||
const codeEl = trigger.previousElementSibling.cloneNode(true);
|
||||
for (const childEl of codeEl.children) {
|
||||
if (isCodeAnnotation(childEl)) {
|
||||
childEl.remove();
|
||||
}
|
||||
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;
|
||||
}
|
||||
return codeEl.innerText;
|
||||
}
|
||||
const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
|
||||
text: getTextToCopy
|
||||
|
||||
Reference in New Issue
Block a user