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

Built site for gh-pages

Browse Source
This commit is contained in:
Quarto GHA Workflow Runner
2025-09-16 18:58:53 +00:00
parent db626de56e
commit 421eea620c
209 changed files with 4822 additions and 3261 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
docs/quantize.html
View File

@@ -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">
@@ -67,14 +67,15 @@ 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,
@@ -124,7 +125,8 @@ 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">
@@ -150,6 +152,10 @@ 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">
@@ -540,26 +546,26 @@ Note
<section id="configuring-quantization-in-axolotl" class="level2">
<h2 class="anchored" data-anchor-id="configuring-quantization-in-axolotl">Configuring Quantization in Axolotl</h2>
<p>Quantization is configured using the <code>quantization</code> key in your configuration file.</p>
<div class="sourceCode" id="cb1"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="co"> # The path to the model to quantize.</span></span>
<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">base_model</span><span class="kw">:</span><span class="co"> # The path to the model to quantize.</span></span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">quantization</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="fu">weight_dtype</span><span class="kw">:</span><span class="co"> # Optional[str] = "int8". Fake quantization layout to use for weight quantization. Valid options are uintX for X in [1, 2, 3, 4, 5, 6, 7], or int4, or int8</span></span>
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">activation_dtype</span><span class="kw">:</span><span class="co"> # Optional[str] = "int8". Fake quantization layout to use for activation quantization. Valid options are "int4" and "int8"</span></span>
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">group_size</span><span class="kw">:</span><span class="co"> # Optional[int] = 32. The number of elements in each group for per-group fake quantization</span></span>
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">quantize_embedding</span><span class="kw">:</span><span class="co"> # Optional[bool] = False. Whether to quantize the embedding layer.</span></span>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="co"> # The path to the output directory.</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="co"> # The path to the output directory.</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Once quantization is complete, your quantized model will be saved in the <code>{output_dir}/quantized</code> directory.</p>
<p>You may also use the <code>quantize</code> command to quantize a model which has been trained with <a href="../docs/qat.html">QAT</a> - you can do this by using the existing QAT configuration file which
you used to train the model:</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="co"># qat.yml</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="co"># qat.yml</span></span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="fu">qat</span><span class="kw">:</span></span>
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">activation_dtype</span><span class="kw">:</span><span class="at"> int8</span></span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">weight_dtype</span><span class="kw">:</span><span class="at"> int8</span></span>
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">group_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">256</span></span>
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">quantize_embedding</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="co"> # The path to the output directory used during training where the final checkpoint has been saved.</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb3"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> quantize qat.yml</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="co"> # The path to the output directory used during training where the final checkpoint has been saved.</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb3"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> quantize qat.yml</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>This ensures that an identical quantization configuration is used to quantize the model as was used to train it.</p>
<div class="callout callout-style-default callout-note callout-titled">
<div class="callout-header d-flex align-content-center">
@@ -631,13 +637,14 @@ e.g.&nbsp;<code>axolotl-ai-cloud/qat-nvfp4-llama3B</code> will become <code>axol
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