Built site for gh-pages

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

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">
@@ -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">
@@ -555,7 +561,7 @@ Important
<h2 class="anchored" data-anchor-id="accelerate">Accelerate</h2>
<p>You will need to create a configuration for accelerate, either by using <code>accelerate config</code> and follow the instructions or you can use one of the preset below:</p>
<p>~/.cache/huggingface/accelerate/default_config.yaml</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">compute_environment</span><span class="kw">:</span><span class="at"> LOCAL_MACHINE</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">compute_environment</span><span class="kw">:</span><span class="at"> LOCAL_MACHINE</span></span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">debug</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="fu">distributed_type</span><span class="kw">:</span><span class="at"> FSDP</span></span>
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="fu">downcast_bf16</span><span class="kw">:</span><span class="at"> </span><span class="st">'no'</span></span>
@@ -571,15 +577,15 @@ Important
<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a><span class="fu">tpu_env</span><span class="kw">:</span><span class="at"> </span><span class="kw">[]</span></span>
<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a><span class="fu">tpu_use_cluster</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
<span id="cb1-16"><a href="#cb1-16" aria-hidden="true" tabindex="-1"></a><span class="fu">tpu_use_sudo</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
<span id="cb1-17"><a href="#cb1-17" aria-hidden="true" tabindex="-1"></a><span class="fu">use_cpu</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb1-17"><a href="#cb1-17" aria-hidden="true" tabindex="-1"></a><span class="fu">use_cpu</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Configure your model to use FSDP in the Axolotl yaml. For example:</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">fsdp_version</span><span class="kw">:</span><span class="at"> </span><span class="dv">2</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">fsdp_version</span><span class="kw">:</span><span class="at"> </span><span class="dv">2</span></span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</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">offload_params</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">state_dict_type</span><span class="kw">:</span><span class="at"> FULL_STATE_DICT</span></span>
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">auto_wrap_policy</span><span class="kw">:</span><span class="at"> TRANSFORMER_BASED_WRAP</span></span>
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">transformer_layer_cls_to_wrap</span><span class="kw">:</span><span class="at"> LlamaDecoderLayer</span></span>
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reshard_after_forward</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="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reshard_after_forward</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>
<p>All you have to do now is launch using accelerate as you would usually do on each machine and voila, the processes will start once you have launched accelerate on every machine.</p>
</section>
<section id="raytrain" class="level2">
@@ -590,17 +596,17 @@ Important
<h2 class="anchored" data-anchor-id="torchrun">Torchrun</h2>
<p>If you are using Infiniband, we recommend torchrun to utilize the full bandwidth.</p>
<p>Set the following env (change buffersize/socketname depending on your system):</p>
<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="bu">export</span> <span class="va">NCCL_IB_DISABLE</span><span class="op">=</span>0</span>
<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="bu">export</span> <span class="va">NCCL_IB_DISABLE</span><span class="op">=</span>0</span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="bu">export</span> <span class="va">NCCL_SOCKET_IFNAME</span><span class="op">=</span><span class="st">"eth0,en,eth,em,bond"</span></span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="bu">export</span> <span class="va">NCCL_BUFFSIZE</span><span class="op">=</span>2097152</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="bu">export</span> <span class="va">NCCL_BUFFSIZE</span><span class="op">=</span>2097152</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Run the following on each node:</p>
<section id="option-1-new-axolotl-cli-with-launcher-args-recommended" class="level3">
<h3 class="anchored" data-anchor-id="option-1-new-axolotl-cli-with-launcher-args-recommended">Option 1: New Axolotl CLI with launcher args (Recommended)</h3>
<div class="sourceCode" id="cb4"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train config.yaml <span class="at">--launcher</span> torchrun <span class="at">--</span> <span class="at">--nnodes</span> <span class="va">$num_nodes</span> <span class="at">--nproc_per_node</span> <span class="va">$gpu_per_node</span> <span class="at">--rdzv_id</span> <span class="va">$rdzv_id</span> <span class="at">--rdzv_backend</span> c10d <span class="at">--rdzv_endpoint</span> <span class="st">"</span><span class="va">$head_node_ip</span><span class="st">:</span><span class="va">$head_node_port</span><span class="st">"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb4"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train config.yaml <span class="at">--launcher</span> torchrun <span class="at">--</span> <span class="at">--nnodes</span> <span class="va">$num_nodes</span> <span class="at">--nproc_per_node</span> <span class="va">$gpu_per_node</span> <span class="at">--rdzv_id</span> <span class="va">$rdzv_id</span> <span class="at">--rdzv_backend</span> c10d <span class="at">--rdzv_endpoint</span> <span class="st">"</span><span class="va">$head_node_ip</span><span class="st">:</span><span class="va">$head_node_port</span><span class="st">"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
</section>
<section id="option-2-direct-torchrun-legacy" class="level3">
<h3 class="anchored" data-anchor-id="option-2-direct-torchrun-legacy">Option 2: Direct torchrun (Legacy)</h3>
<div class="sourceCode" id="cb5"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="ex">torchrun</span> <span class="at">--nnodes</span> <span class="va">$num_nodes</span> <span class="at">--nproc_per_node</span> <span class="va">$gpu_per_node</span> <span class="at">--rdzv_id</span> <span class="va">$rdzv_id</span> <span class="at">--rdzv_backend</span> c10d <span class="at">--rdzv_endpoint</span> <span class="st">"</span><span class="va">$head_node_ip</span><span class="st">:</span><span class="va">$head_node_port</span><span class="st">"</span> <span class="at">-m</span> axolotl.cli.train config.yaml</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb5"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="ex">torchrun</span> <span class="at">--nnodes</span> <span class="va">$num_nodes</span> <span class="at">--nproc_per_node</span> <span class="va">$gpu_per_node</span> <span class="at">--rdzv_id</span> <span class="va">$rdzv_id</span> <span class="at">--rdzv_backend</span> c10d <span class="at">--rdzv_endpoint</span> <span class="st">"</span><span class="va">$head_node_ip</span><span class="st">:</span><span class="va">$head_node_port</span><span class="st">"</span> <span class="at">-m</span> axolotl.cli.train config.yaml</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Please make sure to substitute the placeholder variables:</p>
<ul>
<li><code>num_nodes</code>: Number of nodes (containing GPUs)</li>
@@ -668,13 +674,14 @@ Important
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