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

57
docs/getting-started.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">
@@ -545,11 +551,11 @@ Assuming <code>axolotl</code> is installed (if not, see our <a href="../docs/ins
<ol type="1">
<li>Download example configs:</li>
</ol>
<div class="sourceCode" id="cb1"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> fetch examples</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 bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> fetch examples</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<ol start="2" type="1">
<li>Run the training:</li>
</ol>
<div class="sourceCode" id="cb2"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train examples/llama-3/lora-1b.yml</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="cb2"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train examples/llama-3/lora-1b.yml</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>That’s it! Let’s understand what just happened.</p>
</section>
<section id="sec-understanding" class="level2" data-number="2">
@@ -557,7 +563,7 @@ Assuming <code>axolotl</code> is installed (if not, see our <a href="../docs/ins
<section id="sec-config" class="level3" data-number="2.1">
<h3 data-number="2.1" class="anchored" data-anchor-id="sec-config"><span class="header-section-number">2.1</span> The Configuration File</h3>
<p>The YAML configuration file controls everything about your training. Here’s what (part of) our example config looks like:</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">base_model</span><span class="kw">:</span><span class="at"> NousResearch/Llama-3.2-1B</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">base_model</span><span class="kw">:</span><span class="at"> NousResearch/Llama-3.2-1B</span></span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="fu">load_in_8bit</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> lora</span></span>
@@ -567,7 +573,7 @@ Assuming <code>axolotl</code> is installed (if not, see our <a href="../docs/ins
<span id="cb3-8"><a href="#cb3-8" 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>
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a><span class="fu">dataset_prepared_path</span><span class="kw">:</span><span class="at"> last_run_prepared</span></span>
<span id="cb3-10"><a href="#cb3-10" aria-hidden="true" tabindex="-1"></a><span class="fu">val_set_size</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.1</span></span>
<span id="cb3-11"><a href="#cb3-11" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="at"> ./outputs/lora-out</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb3-11"><a href="#cb3-11" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="at"> ./outputs/lora-out</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<div class="callout callout-style-default callout-tip callout-titled">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
@@ -605,7 +611,7 @@ Tip
<ol type="1">
<li>Create a new config file <code>my_training.yml</code>:</li>
</ol>
<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">base_model</span><span class="kw">:</span><span class="at"> NousResearch/Nous-Hermes-llama-1b-v1</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">base_model</span><span class="kw">:</span><span class="at"> NousResearch/Nous-Hermes-llama-1b-v1</span></span>
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a><span class="fu">load_in_8bit</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> lora</span></span>
@@ -618,26 +624,26 @@ Tip
<span id="cb4-11"><a href="#cb4-11" aria-hidden="true" tabindex="-1"></a><span class="co"># Your dataset</span></span>
<span id="cb4-12"><a href="#cb4-12" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb4-13"><a href="#cb4-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> my_data.jsonl</span><span class="co"> # Your local data file</span></span>
<span id="cb4-14"><a href="#cb4-14" 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 class="co"> # Or other format</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb4-14"><a href="#cb4-14" 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 class="co"> # Or other format</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>This specific config is for LoRA fine-tuning a model with instruction tuning data using
the <code>alpaca</code> dataset format, which has the following format:</p>
<div class="sourceCode" id="cb5"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb5"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"Write a description of alpacas."</span><span class="fu">,</span></span>
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">""</span><span class="fu">,</span></span>
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"Alpacas are domesticated South American camelids..."</span></span>
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a><span class="fu">}</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Please see our <a href="dataset-formats">Dataset Formats</a> for more dataset formats and how to
format them.</p>
<ol start="2" type="1">
<li>Prepare your JSONL data in the specified format (in this case, the expected <code>alpaca</code>
format):</li>
</ol>
<div class="sourceCode" id="cb6"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"Classify this text"</span><span class="fu">,</span> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"I love this!"</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"positive"</span><span class="fu">}</span></span>
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"Classify this text"</span><span class="fu">,</span> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"Not good at all"</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"negative"</span><span class="fu">}</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="cb6"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"Classify this text"</span><span class="fu">,</span> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"I love this!"</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"positive"</span><span class="fu">}</span></span>
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"Classify this text"</span><span class="fu">,</span> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"Not good at all"</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"negative"</span><span class="fu">}</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<ol start="3" type="1">
<li>Run the training:</li>
</ol>
<div class="sourceCode" id="cb7"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train my_training.yml</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="cb7"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train my_training.yml</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
</section>
<section id="sec-common-tasks" class="level2" data-number="4">
<h2 data-number="4" class="anchored" data-anchor-id="sec-common-tasks"><span class="header-section-number">4</span> Common Tasks</h2>
@@ -657,25 +663,25 @@ Tip
<section id="sec-testing" class="level3" data-number="4.1">
<h3 data-number="4.1" class="anchored" data-anchor-id="sec-testing"><span class="header-section-number">4.1</span> Testing Your Model</h3>
<p>After training, test your model:</p>
<div class="sourceCode" id="cb8"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> inference my_training.yml <span class="at">--lora-model-dir</span><span class="op">=</span><span class="st">"./outputs/lora-out"</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="cb8"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> inference my_training.yml <span class="at">--lora-model-dir</span><span class="op">=</span><span class="st">"./outputs/lora-out"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>More details can be found in <a href="../docs/inference.html">Inference</a>.</p>
</section>
<section id="sec-ui" class="level3" data-number="4.2">
<h3 data-number="4.2" class="anchored" data-anchor-id="sec-ui"><span class="header-section-number">4.2</span> Using a UI</h3>
<p>Launch a Gradio interface:</p>
<div class="sourceCode" id="cb9"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> inference my_training.yml <span class="at">--lora-model-dir</span><span class="op">=</span><span class="st">"./outputs/lora-out"</span> <span class="at">--gradio</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="cb9"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> inference my_training.yml <span class="at">--lora-model-dir</span><span class="op">=</span><span class="st">"./outputs/lora-out"</span> <span class="at">--gradio</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
</section>
<section id="sec-preprocessing" class="level3" data-number="4.3">
<h3 data-number="4.3" class="anchored" data-anchor-id="sec-preprocessing"><span class="header-section-number">4.3</span> Preprocessing Data</h3>
<p>For large datasets, preprocess first:</p>
<div class="sourceCode" id="cb10"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> preprocess my_training.yml</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="cb10"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> preprocess my_training.yml</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Please make sure to set <code>dataset_prepared_path:</code> in your config to set the path to save the prepared dataset.</p>
<p>More details can be found in <a href="../docs/dataset_preprocessing.html">Dataset Preprocessing</a>.</p>
</section>
<section id="sec-merging-lora" class="level3" data-number="4.4">
<h3 data-number="4.4" class="anchored" data-anchor-id="sec-merging-lora"><span class="header-section-number">4.4</span> Merging LoRA weights</h3>
<p>To merge the LoRA weights back into the base model, run:</p>
<div class="sourceCode" id="cb11"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> merge-lora my_training.yml <span class="at">--lora-model-dir</span><span class="op">=</span><span class="st">"./outputs/lora-out"</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="cb11"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> merge-lora my_training.yml <span class="at">--lora-model-dir</span><span class="op">=</span><span class="st">"./outputs/lora-out"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>The merged model will be saved in the <code>{output_dir}/merged</code> directory.</p>
<p>More details can be found in <a href="../docs/inference.html#sec-merging">Merging LoRA weights</a>.</p>
</section>
@@ -753,13 +759,14 @@ Tip
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