Built site for gh-pages
This commit is contained in:
@@ -70,10 +70,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-2f5df379a58b258e96c21c0638c20c03.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.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-141b2cdb37a94fcfd6825c1581ff795f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
|
||||
<link href="../../site_libs/bootstrap/bootstrap-0cda210ced8960466d2ee7bf22d15016.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,
|
||||
@@ -113,8 +113,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||||
<div class="navbar-container container-fluid">
|
||||
<div class="navbar-brand-container mx-auto">
|
||||
<a class="navbar-brand" href="../../index.html">
|
||||
<span class="navbar-title">Axolotl</span>
|
||||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||||
</a>
|
||||
</div>
|
||||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||||
@@ -151,7 +151,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">How-To Guides</span></a>
|
||||
<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>
|
||||
@@ -160,91 +160,25 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">Getting Started with Axolotl</span></a>
|
||||
<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 Guide</span></a>
|
||||
<span class="menu-text">Installation</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>
|
||||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">CLI Reference</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 Guide</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Template-free prompt construction</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/nccl.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">NCCL</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>
|
||||
<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 Training Guide</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/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/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Training with AMD GPUs on HPC Systems</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 integration</span></a>
|
||||
<span class="menu-text">Inference</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -299,7 +233,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-3" role="navigation" aria-expanded="true">
|
||||
<span class="menu-text">Reference</span></a>
|
||||
<span class="menu-text">Deployments</span></a>
|
||||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||||
<i class="bi bi-chevron-right ms-2"></i>
|
||||
</a>
|
||||
@@ -307,18 +241,187 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<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-4" 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-4" 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-4" 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>
|
||||
</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-5" 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-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/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/multipack.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Multipack (Sample Packing)</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">Advanced Features</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + 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>
|
||||
</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">Troubleshooting</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/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>
|
||||
<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">Reference</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/config.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Config options</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<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>
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
@@ -368,7 +471,19 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
|
||||
<section id="sharegpt" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="sharegpt">sharegpt</h2>
|
||||
<p>IMPORTANT: ShareGPT is deprecated!. Please see <a href="#chat_template">chat_template</a> section below.</p>
|
||||
<div class="callout callout-style-default callout-important callout-titled">
|
||||
<div class="callout-header d-flex align-content-center">
|
||||
<div class="callout-icon-container">
|
||||
<i class="callout-icon"></i>
|
||||
</div>
|
||||
<div class="callout-title-container flex-fill">
|
||||
Important
|
||||
</div>
|
||||
</div>
|
||||
<div class="callout-body-container callout-body">
|
||||
<p>ShareGPT is deprecated!. Please see <a href="#chat_template">chat_template</a> section below.</p>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="pygmalion" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="pygmalion">pygmalion</h2>
|
||||
|
||||
@@ -70,10 +70,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-2f5df379a58b258e96c21c0638c20c03.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.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-141b2cdb37a94fcfd6825c1581ff795f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
|
||||
<link href="../../site_libs/bootstrap/bootstrap-0cda210ced8960466d2ee7bf22d15016.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,
|
||||
@@ -113,8 +113,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||||
<div class="navbar-container container-fluid">
|
||||
<div class="navbar-brand-container mx-auto">
|
||||
<a class="navbar-brand" href="../../index.html">
|
||||
<span class="navbar-title">Axolotl</span>
|
||||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||||
</a>
|
||||
</div>
|
||||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||||
@@ -151,7 +151,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">How-To Guides</span></a>
|
||||
<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>
|
||||
@@ -160,91 +160,25 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">Getting Started with Axolotl</span></a>
|
||||
<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 Guide</span></a>
|
||||
<span class="menu-text">Installation</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>
|
||||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">CLI Reference</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 Guide</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Template-free prompt construction</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/nccl.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">NCCL</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>
|
||||
<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 Training Guide</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/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/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Training with AMD GPUs on HPC Systems</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 integration</span></a>
|
||||
<span class="menu-text">Inference</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -299,7 +233,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-3" role="navigation" aria-expanded="true">
|
||||
<span class="menu-text">Reference</span></a>
|
||||
<span class="menu-text">Deployments</span></a>
|
||||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||||
<i class="bi bi-chevron-right ms-2"></i>
|
||||
</a>
|
||||
@@ -307,18 +241,187 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<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-4" 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-4" 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-4" 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>
|
||||
</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-5" 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-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/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/multipack.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Multipack (Sample Packing)</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">Advanced Features</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + 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>
|
||||
</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">Troubleshooting</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/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>
|
||||
<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">Reference</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/config.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Config options</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<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>
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
@@ -339,6 +442,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<li><a href="#setting-max_steps" id="toc-setting-max_steps" class="nav-link" data-scroll-target="#setting-max_steps">Setting max_steps</a></li>
|
||||
<li><a href="#group_by_length" id="toc-group_by_length" class="nav-link" data-scroll-target="#group_by_length">Group_by_length</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#reference" id="toc-reference" class="nav-link" data-scroll-target="#reference">Reference</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#supervised-fine-tuning-sft" id="toc-supervised-fine-tuning-sft" class="nav-link" data-scroll-target="#supervised-fine-tuning-sft">Supervised fine-tuning (SFT)</a>
|
||||
<ul>
|
||||
@@ -353,9 +457,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<li><a href="#choosing-a-chat_template" id="toc-choosing-a-chat_template" class="nav-link" data-scroll-target="#choosing-a-chat_template">Choosing a <code>chat_template</code></a></li>
|
||||
<li><a href="#setting-chat_template-dataset-keys" id="toc-setting-chat_template-dataset-keys" class="nav-link" data-scroll-target="#setting-chat_template-dataset-keys">Setting <code>chat_template</code> dataset keys</a></li>
|
||||
<li><a href="#handling-masking" id="toc-handling-masking" class="nav-link" data-scroll-target="#handling-masking">Handling masking</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#applying-chat_template" id="toc-applying-chat_template" class="nav-link" data-scroll-target="#applying-chat_template">Applying <code>chat_template</code></a></li>
|
||||
</ul></li>
|
||||
<li><a href="#reference-1" id="toc-reference-1" class="nav-link" data-scroll-target="#reference-1">Reference</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#instruction-dataset" id="toc-instruction-dataset" class="nav-link" data-scroll-target="#instruction-dataset">Instruction Dataset</a>
|
||||
<ul>
|
||||
<li><a href="#custom-instruct-prompt-format" id="toc-custom-instruct-prompt-format" class="nav-link" data-scroll-target="#custom-instruct-prompt-format">Custom Instruct Prompt Format</a></li>
|
||||
@@ -396,7 +501,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<p>As there are a lot of available options in Axolotl, this guide aims to provide an simplify the user experience to choosing the proper choice.</p>
|
||||
<p>Axolotl supports 3 kinds of training methods: pre-training, supervised fine-tuning, and preference-based post-training (e.g. DPO, ORPO, PRMs). Each method has their own dataset format which are described below.</p>
|
||||
<section id="pre-training" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="pre-training"><a href="../../docs/dataset-formats/pretraining.html">Pre-training</a></h2>
|
||||
<h2 class="anchored" data-anchor-id="pre-training">Pre-training</h2>
|
||||
<p>When aiming to train on large corpora of text datasets, pre-training is your go-to choice. Due to the size of these datasets, downloading the entire-datasets before beginning training would be prohibitively time-consuming. Axolotl supports <a href="https://huggingface.co/docs/datasets/en/stream">streaming</a> to only load batches into memory at a time.</p>
|
||||
<p>A sample format for a pre-training dataset is as follows:</p>
|
||||
<div class="sourceCode" id="cb1"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"text"</span><span class="fu">:</span> <span class="st">"first row"</span><span class="fu">}</span></span>
|
||||
@@ -463,6 +568,10 @@ Important
|
||||
<p>It is recommended to leave this off if downloading from Hugging Face hub as it would download the entire dataset which can be very large.</p>
|
||||
</section>
|
||||
</section>
|
||||
<section id="reference" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="reference">Reference</h3>
|
||||
<p>Please see docs <a href="../../docs/dataset-formats/pretraining.html">here</a>.</p>
|
||||
</section>
|
||||
</section>
|
||||
<section id="supervised-fine-tuning-sft" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="supervised-fine-tuning-sft">Supervised fine-tuning (SFT)</h2>
|
||||
@@ -491,7 +600,7 @@ Tip
|
||||
</div>
|
||||
</div>
|
||||
<section id="pre-tokenized-dataset" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="pre-tokenized-dataset"><a href="../../docs/dataset-formats/tokenized.html">Pre-Tokenized Dataset</a></h3>
|
||||
<h3 class="anchored" data-anchor-id="pre-tokenized-dataset">Pre-Tokenized Dataset</h3>
|
||||
<p>We suggest this approach when you want to bring your own tokenized dataset.</p>
|
||||
<p>Axolotl expects the dataset to have three keys: - <code>input_ids</code>: from tokenizing formatted prompt - <code>attention_mask</code>: for masking padding. If you don’t add padding, it would be equal to <code>len(input_ids) * [1]</code> - <code>labels</code>: this is the same as <code>input_ids</code>, however, if you want to mask certain tokens, you would set those indices to <code>-100</code>.</p>
|
||||
<div class="callout callout-style-default callout-tip callout-titled">
|
||||
@@ -524,9 +633,10 @@ Note
|
||||
<p><code>type:</code> is empty!</p>
|
||||
</div>
|
||||
</div>
|
||||
<p>Reference: <a href="../../docs/dataset-formats/tokenized.html">Pre-Tokenized Dataset Documentation</a>.</p>
|
||||
</section>
|
||||
<section id="template-free-dataset" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="template-free-dataset"><a href="../../docs/dataset-formats/template_free.html">Template Free Dataset</a></h3>
|
||||
<h3 class="anchored" data-anchor-id="template-free-dataset">Template Free Dataset</h3>
|
||||
<p>We reccomend this approach when you want granular control over the prompt formatting, special tokens, and masking, whilst letting Axolotl handle the tokenization. This is very useful if your dataset has unique prompts that differ across samples and where one single general template wouldn’t suffice.</p>
|
||||
<p>In the example below, you could see that there is no proper structure. At the same time, it’s very flexible as there are no constraints on how your prompt can look.</p>
|
||||
<div class="sourceCode" id="cb7"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span></span>
|
||||
@@ -553,9 +663,10 @@ Note
|
||||
<div class="sourceCode" id="cb8"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb8-2"><a href="#cb8-2" 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"> A.jsonl</span></span>
|
||||
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> input_output</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>Reference: <a href="../../docs/dataset-formats/template_free.html">Template Free Documentation</a>.</p>
|
||||
</section>
|
||||
<section id="conversation-dataset" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="conversation-dataset"><a href="../../docs/dataset-formats/conversation.html">Conversation Dataset</a></h3>
|
||||
<h3 class="anchored" data-anchor-id="conversation-dataset">Conversation Dataset</h3>
|
||||
<p><code>conversation</code> messages are a list of messages which usually contain a <code>role</code> and <code>content</code> key.</p>
|
||||
<div class="callout callout-style-default callout-tip callout-titled">
|
||||
<div class="callout-header d-flex align-content-center">
|
||||
@@ -618,7 +729,7 @@ The answer is 8.<|im_end|></code></pre>
|
||||
<p>Axolotl supports both as well as allowing customization of any kind of key.</p>
|
||||
</section>
|
||||
<section id="chat-template-usage" class="level4">
|
||||
<h4 class="anchored" data-anchor-id="chat-template-usage"><a href="../../docs/dataset-formats/conversation.html#chat_template">Chat Template Usage</a></h4>
|
||||
<h4 class="anchored" data-anchor-id="chat-template-usage">Chat Template Usage</h4>
|
||||
<p>To properly use this method, it is important to identify three things:</p>
|
||||
<ol type="1">
|
||||
<li><p>Which <code>chat_template</code> would you use?</p></li>
|
||||
@@ -673,39 +784,53 @@ The answer is 8.<|im_end|></code></pre>
|
||||
<span id="cb18-8"><a href="#cb18-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">user</span><span class="kw">:</span></span>
|
||||
<span id="cb18-9"><a href="#cb18-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> human</span></span>
|
||||
<span id="cb18-10"><a href="#cb18-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">narrator</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"narrator"</span><span class="kw">]</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></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">
|
||||
<i class="callout-icon"></i>
|
||||
</div>
|
||||
<div class="callout-title-container flex-fill">
|
||||
Tip
|
||||
</div>
|
||||
</div>
|
||||
<div class="callout-body-container callout-body">
|
||||
<p>As chat_templates may use hardcoded EOS/EOT tokens that are different from the tokenizer’s EOS, it is highly recommended to set them. For example, <code>ChatML</code> uses <code><|im_end|></code> to end turns.</p>
|
||||
<div class="sourceCode" id="cb19"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb19-1"><a href="#cb19-1" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
|
||||
<span id="cb19-2"><a href="#cb19-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">eos_token</span><span class="kw">:</span><span class="at"> <|im_end|></span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="applying-chat_template" class="level4">
|
||||
<h4 class="anchored" data-anchor-id="applying-chat_template">Applying <code>chat_template</code></h4>
|
||||
<p>Once all the above steps are completed, you could combine all these configs together to form a bespoke configuration for your custom dataset. The final step would be to correctly set the EOS token in your config:</p>
|
||||
<div class="sourceCode" id="cb19"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb19-1"><a href="#cb19-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb19-2"><a href="#cb19-2" 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"> A.jsonl</span></span>
|
||||
<span id="cb19-3"><a href="#cb19-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
|
||||
<span id="cb19-4"><a href="#cb19-4" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb19-5"><a href="#cb19-5" aria-hidden="true" tabindex="-1"></a><span class="co"> # step 1</span></span>
|
||||
<span id="cb19-6"><a href="#cb19-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> chatml</span></span>
|
||||
<span id="cb19-7"><a href="#cb19-7" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb19-8"><a href="#cb19-8" aria-hidden="true" tabindex="-1"></a><span class="co"> # step 2</span></span>
|
||||
<span id="cb19-9"><a href="#cb19-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> messages</span></span>
|
||||
<span id="cb19-10"><a href="#cb19-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_property_mappings</span><span class="kw">:</span></span>
|
||||
<span id="cb19-11"><a href="#cb19-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">role</span><span class="kw">:</span><span class="at"> role</span></span>
|
||||
<span id="cb19-12"><a href="#cb19-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">content</span><span class="kw">:</span><span class="at"> content</span></span>
|
||||
<span id="cb19-13"><a href="#cb19-13" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb19-14"><a href="#cb19-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles</span><span class="kw">:</span></span>
|
||||
<span id="cb19-15"><a href="#cb19-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">assistant</span><span class="kw">:</span></span>
|
||||
<span id="cb19-16"><a href="#cb19-16" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> gpt</span></span>
|
||||
<span id="cb19-17"><a href="#cb19-17" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> model</span></span>
|
||||
<span id="cb19-18"><a href="#cb19-18" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> assistant</span></span>
|
||||
<span id="cb19-19"><a href="#cb19-19" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">user</span><span class="kw">:</span></span>
|
||||
<span id="cb19-20"><a href="#cb19-20" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> human</span></span>
|
||||
<span id="cb19-21"><a href="#cb19-21" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> user</span></span>
|
||||
<span id="cb19-22"><a href="#cb19-22" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb19-23"><a href="#cb19-23" aria-hidden="true" tabindex="-1"></a><span class="co"> # step 3</span></span>
|
||||
<span id="cb19-24"><a href="#cb19-24" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles_to_train</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"assistant"</span><span class="kw">]</span></span>
|
||||
<span id="cb19-25"><a href="#cb19-25" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">train_on_eos</span><span class="kw">:</span><span class="at"> </span><span class="st">"turn"</span></span>
|
||||
<span id="cb19-26"><a href="#cb19-26" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb19-27"><a href="#cb19-27" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
|
||||
<span id="cb19-28"><a href="#cb19-28" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">eos_token</span><span class="kw">:</span><span class="at"> <|im_end|></span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<section id="applying-chat_template" class="level5">
|
||||
<h5 class="anchored" data-anchor-id="applying-chat_template">Applying <code>chat_template</code></h5>
|
||||
<p>Once all the above steps are completed, you could combine all these configs together to form a bespoke configuration for your custom dataset.</p>
|
||||
<div class="sourceCode" id="cb20"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb20-1"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb20-2"><a href="#cb20-2" 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"> A.jsonl</span></span>
|
||||
<span id="cb20-3"><a href="#cb20-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chat_template</span></span>
|
||||
<span id="cb20-4"><a href="#cb20-4" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb20-5"><a href="#cb20-5" aria-hidden="true" tabindex="-1"></a><span class="co"> # step 1</span></span>
|
||||
<span id="cb20-6"><a href="#cb20-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> chatml</span></span>
|
||||
<span id="cb20-7"><a href="#cb20-7" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb20-8"><a href="#cb20-8" aria-hidden="true" tabindex="-1"></a><span class="co"> # step 2</span></span>
|
||||
<span id="cb20-9"><a href="#cb20-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> messages</span></span>
|
||||
<span id="cb20-10"><a href="#cb20-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">message_property_mappings</span><span class="kw">:</span></span>
|
||||
<span id="cb20-11"><a href="#cb20-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">role</span><span class="kw">:</span><span class="at"> role</span></span>
|
||||
<span id="cb20-12"><a href="#cb20-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">content</span><span class="kw">:</span><span class="at"> content</span></span>
|
||||
<span id="cb20-13"><a href="#cb20-13" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb20-14"><a href="#cb20-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles</span><span class="kw">:</span></span>
|
||||
<span id="cb20-15"><a href="#cb20-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">assistant</span><span class="kw">:</span></span>
|
||||
<span id="cb20-16"><a href="#cb20-16" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> gpt</span></span>
|
||||
<span id="cb20-17"><a href="#cb20-17" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> model</span></span>
|
||||
<span id="cb20-18"><a href="#cb20-18" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> assistant</span></span>
|
||||
<span id="cb20-19"><a href="#cb20-19" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">user</span><span class="kw">:</span></span>
|
||||
<span id="cb20-20"><a href="#cb20-20" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> human</span></span>
|
||||
<span id="cb20-21"><a href="#cb20-21" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> user</span></span>
|
||||
<span id="cb20-22"><a href="#cb20-22" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb20-23"><a href="#cb20-23" aria-hidden="true" tabindex="-1"></a><span class="co"> # step 3</span></span>
|
||||
<span id="cb20-24"><a href="#cb20-24" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles_to_train</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"assistant"</span><span class="kw">]</span></span>
|
||||
<span id="cb20-25"><a href="#cb20-25" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">train_on_eos</span><span class="kw">:</span><span class="at"> </span><span class="st">"turn"</span></span>
|
||||
<span id="cb20-26"><a href="#cb20-26" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb20-27"><a href="#cb20-27" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
|
||||
<span id="cb20-28"><a href="#cb20-28" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">eos_token</span><span class="kw">:</span><span class="at"> <|im_end|></span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>If this config were to be applied to the sample dataset above, the output would look as such (which can be retrieved via <code>axolotl preprocess config.yaml --debug</code>):</p>
|
||||
<pre><code><|im_start|>(-100, 128256) user(-100, 882)
|
||||
(-100, 198) Hi(-100, 13347) <|im_end|>(-100, 128257)
|
||||
@@ -717,13 +842,31 @@ The answer is 8.<|im_end|></code></pre>
|
||||
(-100, 198) The(791, 791) answer(4320, 4320) is(374, 374) (220, 220) 8(23, 23) .(13, 13) <|im_end|>(128257, 128257)
|
||||
(-100, 198)</code></pre>
|
||||
<p>The first number refers to the label, the second refers to the <code>token_id</code>. For example, <code>-100</code> labels appear on non-assistant portions, meaning that they are masked during. For assistant portions, the label is the same as the <code>token_id</code>.</p>
|
||||
<div class="callout callout-style-default callout-note callout-titled">
|
||||
<div class="callout-header d-flex align-content-center">
|
||||
<div class="callout-icon-container">
|
||||
<i class="callout-icon"></i>
|
||||
</div>
|
||||
<div class="callout-title-container flex-fill">
|
||||
Note
|
||||
</div>
|
||||
</div>
|
||||
<div class="callout-body-container callout-body">
|
||||
<p>If during <code>preprocess</code>, there are a lot of warnings of <code>Could not find content __ boundary</code>, please check the FAQ section for <a href="../../docs/faq.html#chat-templates">chat_templates</a>.</p>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="reference-1" class="level4">
|
||||
<h4 class="anchored" data-anchor-id="reference-1">Reference</h4>
|
||||
<p>Please see docs <a href="../../docs/dataset-formats/conversation.html">here</a>.</p>
|
||||
</section>
|
||||
</section>
|
||||
<section id="instruction-dataset" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="instruction-dataset"><a href="../../docs/dataset-formats/inst_tune.html">Instruction Dataset</a></h3>
|
||||
<h3 class="anchored" data-anchor-id="instruction-dataset">Instruction Dataset</h3>
|
||||
<p>Instruction datasets are used to train instruction-following models and comprise a prompt, containing an instruction, and a single response. In contrast to chat datasets which may be multi-turn, instruct datasets are typically single-turn.</p>
|
||||
<p>An example is of a common format called Alpaca:</p>
|
||||
<div class="sourceCode" id="cb21"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb21-1"><a href="#cb21-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"..."</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="sourceCode" id="cb22"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb22-1"><a href="#cb22-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"instruction"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"input"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>Using those keys, a prompt can be built based on it.</p>
|
||||
<pre><code>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
|
||||
|
||||
@@ -736,38 +879,40 @@ The answer is 8.<|im_end|></code></pre>
|
||||
### Response:
|
||||
{output}</code></pre>
|
||||
<p>This can be configured as such:</p>
|
||||
<div class="sourceCode" id="cb23"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb23-1"><a href="#cb23-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb23-2"><a href="#cb23-2" 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"> A.jsonl</span></span>
|
||||
<span id="cb23-3"><a href="#cb23-3" 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></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb24"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb24-1"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb24-2"><a href="#cb24-2" 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"> A.jsonl</span></span>
|
||||
<span id="cb24-3"><a href="#cb24-3" 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></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>Axolotl supports many kinds of instruction dataset. All of them can be found here (https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/inst_tune.html) with their respective type and sample row format.</p>
|
||||
<p>Reference: <a href="../../docs/dataset-formats/inst_tune.html">Instruction Dataset Documentation</a>.</p>
|
||||
<section id="custom-instruct-prompt-format" class="level4">
|
||||
<h4 class="anchored" data-anchor-id="custom-instruct-prompt-format">Custom Instruct Prompt Format</h4>
|
||||
<p>Due to the myriad possibilities of instruction formats, Axolotl allows customizing your own instruction format without having to dive into the code directly.</p>
|
||||
<p>In the example below, a sample row is used to output in <code>mistral_v1</code> format.</p>
|
||||
<div class="sourceCode" id="cb24"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb24-1"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"input"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"..."</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="sourceCode" id="cb25"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb25-1"><a href="#cb25-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb25-2"><a href="#cb25-2" 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"> repo</span></span>
|
||||
<span id="cb25-3"><a href="#cb25-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span></span>
|
||||
<span id="cb25-4"><a href="#cb25-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">system_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">""</span></span>
|
||||
<span id="cb25-5"><a href="#cb25-5" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb25-6"><a href="#cb25-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_system</span><span class="kw">:</span></span>
|
||||
<span id="cb25-7"><a href="#cb25-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_instruction</span><span class="kw">:</span><span class="at"> input</span></span>
|
||||
<span id="cb25-8"><a href="#cb25-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_input</span><span class="kw">:</span></span>
|
||||
<span id="cb25-9"><a href="#cb25-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_output</span><span class="kw">:</span><span class="at"> output</span></span>
|
||||
<span id="cb25-10"><a href="#cb25-10" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb25-11"><a href="#cb25-11" aria-hidden="true" tabindex="-1"></a><span class="co"> # multi-line example with input</span></span>
|
||||
<span id="cb25-12"><a href="#cb25-12" aria-hidden="true" tabindex="-1"></a><span class="fu"> format</span><span class="kw">: </span><span class="ch">|-</span></span>
|
||||
<span id="cb25-13"><a href="#cb25-13" aria-hidden="true" tabindex="-1"></a> [INST] {instruction} {input} [/INST]</span>
|
||||
<span id="cb25-14"><a href="#cb25-14" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb25-15"><a href="#cb25-15" aria-hidden="true" tabindex="-1"></a><span class="co"> # single-line example without input</span></span>
|
||||
<span id="cb25-16"><a href="#cb25-16" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">no_input_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"[INST] {instruction} [/INST]"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb25"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb25-1"><a href="#cb25-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"input"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"..."</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="sourceCode" id="cb26"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb26-1"><a href="#cb26-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb26-2"><a href="#cb26-2" 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"> repo</span></span>
|
||||
<span id="cb26-3"><a href="#cb26-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span></span>
|
||||
<span id="cb26-4"><a href="#cb26-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">system_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">""</span></span>
|
||||
<span id="cb26-5"><a href="#cb26-5" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb26-6"><a href="#cb26-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_system</span><span class="kw">:</span></span>
|
||||
<span id="cb26-7"><a href="#cb26-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_instruction</span><span class="kw">:</span><span class="at"> input</span></span>
|
||||
<span id="cb26-8"><a href="#cb26-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_input</span><span class="kw">:</span></span>
|
||||
<span id="cb26-9"><a href="#cb26-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_output</span><span class="kw">:</span><span class="at"> output</span></span>
|
||||
<span id="cb26-10"><a href="#cb26-10" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb26-11"><a href="#cb26-11" aria-hidden="true" tabindex="-1"></a><span class="co"> # multi-line example with input</span></span>
|
||||
<span id="cb26-12"><a href="#cb26-12" aria-hidden="true" tabindex="-1"></a><span class="fu"> format</span><span class="kw">: </span><span class="ch">|-</span></span>
|
||||
<span id="cb26-13"><a href="#cb26-13" aria-hidden="true" tabindex="-1"></a> [INST] {instruction} {input} [/INST]</span>
|
||||
<span id="cb26-14"><a href="#cb26-14" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb26-15"><a href="#cb26-15" aria-hidden="true" tabindex="-1"></a><span class="co"> # single-line example without input</span></span>
|
||||
<span id="cb26-16"><a href="#cb26-16" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">no_input_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"[INST] {instruction} [/INST]"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>The config sets that the <code>field_instruction</code> is actually named <code>input</code>, and the <code>field_input</code> is empty as we don’t have an <code>input</code> in this sample. Generally, <code>instruction</code> can be thought as the question to the model, and <code>input</code> as the additional information with <code>output</code> being the response. It is not necessary to have an <code>input</code> nor <code>system</code>. In the end, the most important part is to understand what format you want it to look like and how you can customize this to your use case.</p>
|
||||
<p>Reference: <a href="../../docs/dataset-formats/inst_tune.html#how-to-add-custom-prompt-format">Custom Instruct Prompt Format Documentation</a>.</p>
|
||||
</section>
|
||||
</section>
|
||||
</section>
|
||||
<section id="reinforcement-learning-from-human-feedback-rlhf" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="reinforcement-learning-from-human-feedback-rlhf">Reinforcement Learning from Human Feedback (RLHF)</h2>
|
||||
<p>As there are multiple RLHF methods with their own dataset requirements. Please see <a href="../../docs/rlhf.html">RLHF datasets</a> documentation for more detail.</p>
|
||||
<p>As there are multiple RLHF methods with their own dataset requirements. Please see <a href="../../docs/rlhf.html">RLHF documentation</a> for more detail.</p>
|
||||
|
||||
|
||||
</section>
|
||||
|
||||
@@ -70,10 +70,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-2f5df379a58b258e96c21c0638c20c03.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.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-141b2cdb37a94fcfd6825c1581ff795f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
|
||||
<link href="../../site_libs/bootstrap/bootstrap-0cda210ced8960466d2ee7bf22d15016.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,
|
||||
@@ -113,8 +113,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||||
<div class="navbar-container container-fluid">
|
||||
<div class="navbar-brand-container mx-auto">
|
||||
<a class="navbar-brand" href="../../index.html">
|
||||
<span class="navbar-title">Axolotl</span>
|
||||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||||
</a>
|
||||
</div>
|
||||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||||
@@ -151,7 +151,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">How-To Guides</span></a>
|
||||
<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>
|
||||
@@ -160,91 +160,25 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">Getting Started with Axolotl</span></a>
|
||||
<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 Guide</span></a>
|
||||
<span class="menu-text">Installation</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>
|
||||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">CLI Reference</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 Guide</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Template-free prompt construction</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/nccl.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">NCCL</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>
|
||||
<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 Training Guide</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/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/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Training with AMD GPUs on HPC Systems</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 integration</span></a>
|
||||
<span class="menu-text">Inference</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -299,7 +233,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-3" role="navigation" aria-expanded="true">
|
||||
<span class="menu-text">Reference</span></a>
|
||||
<span class="menu-text">Deployments</span></a>
|
||||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||||
<i class="bi bi-chevron-right ms-2"></i>
|
||||
</a>
|
||||
@@ -307,18 +241,187 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<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-4" 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-4" 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-4" 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>
|
||||
</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-5" 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-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/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/multipack.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Multipack (Sample Packing)</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">Advanced Features</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + 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>
|
||||
</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">Troubleshooting</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/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>
|
||||
<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">Reference</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/config.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Config options</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<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>
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
@@ -70,10 +70,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-2f5df379a58b258e96c21c0638c20c03.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.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-141b2cdb37a94fcfd6825c1581ff795f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
|
||||
<link href="../../site_libs/bootstrap/bootstrap-0cda210ced8960466d2ee7bf22d15016.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,
|
||||
@@ -113,8 +113,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||||
<div class="navbar-container container-fluid">
|
||||
<div class="navbar-brand-container mx-auto">
|
||||
<a class="navbar-brand" href="../../index.html">
|
||||
<span class="navbar-title">Axolotl</span>
|
||||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||||
</a>
|
||||
</div>
|
||||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||||
@@ -151,7 +151,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">How-To Guides</span></a>
|
||||
<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>
|
||||
@@ -160,91 +160,25 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">Getting Started with Axolotl</span></a>
|
||||
<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 Guide</span></a>
|
||||
<span class="menu-text">Installation</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>
|
||||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">CLI Reference</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 Guide</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Template-free prompt construction</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/nccl.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">NCCL</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>
|
||||
<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 Training Guide</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/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/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Training with AMD GPUs on HPC Systems</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 integration</span></a>
|
||||
<span class="menu-text">Inference</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -299,7 +233,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-3" role="navigation" aria-expanded="true">
|
||||
<span class="menu-text">Reference</span></a>
|
||||
<span class="menu-text">Deployments</span></a>
|
||||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||||
<i class="bi bi-chevron-right ms-2"></i>
|
||||
</a>
|
||||
@@ -307,18 +241,187 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<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-4" 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-4" 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-4" 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>
|
||||
</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-5" 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-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/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/multipack.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Multipack (Sample Packing)</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">Advanced Features</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + 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>
|
||||
</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">Troubleshooting</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/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>
|
||||
<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">Reference</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/config.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Config options</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<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>
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
@@ -385,8 +488,7 @@ Streaming is recommended for large datasets
|
||||
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">text_column</span><span class="kw">:</span><span class="co"> # column in dataset with the data, usually `text`</span></span>
|
||||
<span id="cb2-6"><a href="#cb2-6" 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="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">trust_remote_code</span><span class="kw">:</span></span>
|
||||
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">skip</span><span class="kw">:</span><span class="co"> # number of rows of data to skip over from the beginning</span></span>
|
||||
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a><span class="co">...</span></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="at"> </span><span class="fu">skip</span><span class="kw">:</span><span class="co"> # number of rows of data to skip over from the beginning</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -70,10 +70,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-2f5df379a58b258e96c21c0638c20c03.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.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-141b2cdb37a94fcfd6825c1581ff795f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
|
||||
<link href="../../site_libs/bootstrap/bootstrap-0cda210ced8960466d2ee7bf22d15016.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,
|
||||
@@ -113,8 +113,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||||
<div class="navbar-container container-fluid">
|
||||
<div class="navbar-brand-container mx-auto">
|
||||
<a class="navbar-brand" href="../../index.html">
|
||||
<span class="navbar-title">Axolotl</span>
|
||||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||||
</a>
|
||||
</div>
|
||||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||||
@@ -151,7 +151,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">How-To Guides</span></a>
|
||||
<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>
|
||||
@@ -160,91 +160,25 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">Getting Started with Axolotl</span></a>
|
||||
<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 Guide</span></a>
|
||||
<span class="menu-text">Installation</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>
|
||||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">CLI Reference</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 Guide</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Template-free prompt construction</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/nccl.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">NCCL</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>
|
||||
<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 Training Guide</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/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/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Training with AMD GPUs on HPC Systems</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 integration</span></a>
|
||||
<span class="menu-text">Inference</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -299,7 +233,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-3" role="navigation" aria-expanded="true">
|
||||
<span class="menu-text">Reference</span></a>
|
||||
<span class="menu-text">Deployments</span></a>
|
||||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||||
<i class="bi bi-chevron-right ms-2"></i>
|
||||
</a>
|
||||
@@ -307,18 +241,187 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<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-4" 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-4" 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-4" 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>
|
||||
</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-5" 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-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/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/multipack.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Multipack (Sample Packing)</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">Advanced Features</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + 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>
|
||||
</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">Troubleshooting</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/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>
|
||||
<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">Reference</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/config.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Config options</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<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>
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
@@ -21,6 +21,40 @@ ul.task-list li input[type="checkbox"] {
|
||||
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 */
|
||||
pre > code.sourceCode { white-space: pre; position: relative; }
|
||||
pre > code.sourceCode > span { 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 { display: inline-block; 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>
|
||||
|
||||
|
||||
@@ -36,10 +70,10 @@ ul.task-list li input[type="checkbox"] {
|
||||
<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-2f5df379a58b258e96c21c0638c20c03.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.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-141b2cdb37a94fcfd6825c1581ff795f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
|
||||
<link href="../../site_libs/bootstrap/bootstrap-0cda210ced8960466d2ee7bf22d15016.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,
|
||||
@@ -79,8 +113,8 @@ ul.task-list li input[type="checkbox"] {
|
||||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||||
<div class="navbar-container container-fluid">
|
||||
<div class="navbar-brand-container mx-auto">
|
||||
<a class="navbar-brand" href="../../index.html">
|
||||
<span class="navbar-title">Axolotl</span>
|
||||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||||
</a>
|
||||
</div>
|
||||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||||
@@ -117,7 +151,7 @@ ul.task-list li input[type="checkbox"] {
|
||||
<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">How-To Guides</span></a>
|
||||
<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>
|
||||
@@ -126,91 +160,25 @@ ul.task-list li input[type="checkbox"] {
|
||||
<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">Getting Started with Axolotl</span></a>
|
||||
<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 Guide</span></a>
|
||||
<span class="menu-text">Installation</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>
|
||||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">CLI Reference</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 Guide</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Template-free prompt construction</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/nccl.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">NCCL</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>
|
||||
<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 Training Guide</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/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/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Training with AMD GPUs on HPC Systems</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 integration</span></a>
|
||||
<span class="menu-text">Inference</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -265,7 +233,7 @@ ul.task-list li input[type="checkbox"] {
|
||||
<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-3" role="navigation" aria-expanded="true">
|
||||
<span class="menu-text">Reference</span></a>
|
||||
<span class="menu-text">Deployments</span></a>
|
||||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||||
<i class="bi bi-chevron-right ms-2"></i>
|
||||
</a>
|
||||
@@ -273,25 +241,211 @@ ul.task-list li input[type="checkbox"] {
|
||||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<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-4" 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-4" 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-4" 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>
|
||||
</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-5" 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-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/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/multipack.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Multipack (Sample Packing)</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">Advanced Features</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + 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>
|
||||
</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">Troubleshooting</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/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>
|
||||
<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">Reference</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/config.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Config options</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<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>
|
||||
</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 zindex-bottom">
|
||||
|
||||
<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="#sec-background" id="toc-sec-background" class="nav-link active" data-scroll-target="#sec-background">Background</a>
|
||||
<ul class="collapse">
|
||||
<li><a href="#masking-inputs" id="toc-masking-inputs" class="nav-link" data-scroll-target="#masking-inputs">Masking Inputs</a></li>
|
||||
<li><a href="#sec-you-may-not-want-prompt-templates" id="toc-sec-you-may-not-want-prompt-templates" class="nav-link" data-scroll-target="#sec-you-may-not-want-prompt-templates">You may not want prompt templates</a></li>
|
||||
<li><a href="#sec-the-inputoutput-format" id="toc-sec-the-inputoutput-format" class="nav-link" data-scroll-target="#sec-the-inputoutput-format">The <code>input_output</code> format</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#sec-usage" id="toc-sec-usage" class="nav-link" data-scroll-target="#sec-usage">Usage</a>
|
||||
<ul class="collapse">
|
||||
<li><a href="#sec-1-prepare-data" id="toc-sec-1-prepare-data" class="nav-link" data-scroll-target="#sec-1-prepare-data">1. Prepare Data</a></li>
|
||||
<li><a href="#sec-2-use-type-inputoutput" id="toc-sec-2-use-type-inputoutput" class="nav-link" data-scroll-target="#sec-2-use-type-inputoutput">2. Use <code>type: input_output</code></a></li>
|
||||
<li><a href="#sec-3-check-the-prompts" id="toc-sec-3-check-the-prompts" class="nav-link" data-scroll-target="#sec-3-check-the-prompts">3. Check the prompts</a></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
<!-- main -->
|
||||
<main class="content" id="quarto-document-content">
|
||||
@@ -320,9 +474,234 @@ ul.task-list li input[type="checkbox"] {
|
||||
</header>
|
||||
|
||||
|
||||
<p>See <a href="../../docs/input_output.html">these docs</a>.</p>
|
||||
<section id="sec-background" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="sec-background">Background</h2>
|
||||
<section id="masking-inputs" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="masking-inputs">Masking Inputs</h3>
|
||||
<p>One of the most popular features of <a href="https://github.com/axolotl-ai-cloud/axolotl">axolotl</a> is setting the following configuration value:</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">train_on_inputs</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>
|
||||
<p>If you declare a <a href="https://github.com/axolotl-ai-cloud/axolotl?tab=readme-ov-file#dataset">dataset formats</a> such as <code>alpaca</code> or <code>chatml</code>, axolotl knows what is an input (i.e. human) vs. an output (i.e. the assistant) and masks the input labels so that your model can focus on predicting the outputs only.</p>
|
||||
</section>
|
||||
<section id="sec-you-may-not-want-prompt-templates" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-you-may-not-want-prompt-templates">You may not want prompt templates</h3>
|
||||
<p>However, there are many situations where you don’t want to use one of these formats or templates. This is because they can:</p>
|
||||
<ul>
|
||||
<li>Add unnecessary boilerplate to your prompts.</li>
|
||||
<li>Create artifacts like special delimiters <code><|im_start|></code> that can quickly become footguns if you don’t include them correctly at inference time.</li>
|
||||
<li>Enforce a <em>chat</em> interface when you do not want one. Sometimes you just want to fine-tune a model to a very specific task and do NOT want multi-turn conversations, roles, etc.</li>
|
||||
<li>Limit you to only certain roles that the template allows.</li>
|
||||
</ul>
|
||||
</section>
|
||||
<section id="sec-the-inputoutput-format" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-the-inputoutput-format">The <code>input_output</code> format</h3>
|
||||
<p>You can construct your prompts without a template by using the <code>input_output</code> format, by setting <code>type: input_output</code> in your configuration file like this:</p>
|
||||
<p><strong>config.yml</strong></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">train_on_inputs</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span><span class="co"> # Mask segments of your data</span></span>
|
||||
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</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="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> output.jsonl</span></span>
|
||||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> input_output</span><span class="co"> # use template free prompt construction</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>Unlike <code>type: completion</code>, which is also template-free, <code>type: input_output</code> allows you to mask segments of your text. More details on how this works are described below.</p>
|
||||
</section>
|
||||
</section>
|
||||
<section id="sec-usage" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="sec-usage">Usage</h2>
|
||||
<p>This is how you can use the <code>input_output</code> format:</p>
|
||||
<section id="sec-1-prepare-data" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-1-prepare-data">1. Prepare Data</h3>
|
||||
<p>To use the <code>input_output</code> format, collect your data in the following format into a jsonl file (below is the first row from the file <code>output</code>.jsonl` pretty printed):</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="ex">$</span> head <span class="at">-n1</span> output.jsonl <span class="kw">|</span> <span class="ex">python</span> <span class="at">-m</span> json.tool</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="cell-output cell-output-stdout">
|
||||
<pre><code>{
|
||||
"segments": [
|
||||
{
|
||||
"label": true,
|
||||
"text": "<s>Hello\n"
|
||||
},
|
||||
{
|
||||
"label": true,
|
||||
"text": "hi there!. "
|
||||
},
|
||||
{
|
||||
"label": false,
|
||||
"text": "goodbye "
|
||||
},
|
||||
{
|
||||
"label": true,
|
||||
"text": "farewell</s>"
|
||||
}
|
||||
]
|
||||
}</code></pre>
|
||||
</div>
|
||||
<p>Set <code>label:false</code> when you want to mask a segment of text so that the model isn’t trained on it. Some things to keep in mind:</p>
|
||||
<blockquote class="blockquote">
|
||||
<p>[!IMPORTANT] 1. <strong>EOS, BOS, spaces, newlines etc. are entirely up to you. Axolotl concatenates all the segments as-is.</strong> The tokenizer doesn’t add anything additional. Notice how I added spaces, newlines, <code><s></code> (BOS), and <code></s></code> (EOS) myself. 2. Make sure you check the materialized output to validate that the prompt is getting assembled how you like.</p>
|
||||
</blockquote>
|
||||
</section>
|
||||
<section id="sec-2-use-type-inputoutput" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-2-use-type-inputoutput">2. Use <code>type: input_output</code></h3>
|
||||
<p>Let’s materialize data with our <code>output.jsonl</code> file by setting <code>type: input_output</code> in our axolotl config:</p>
|
||||
<div class="sourceCode" id="cb5"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="co"># training_config.yaml</span></span>
|
||||
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> mistralai/Mistral-7B-v0.1</span></span>
|
||||
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a><span class="fu">data_seed</span><span class="kw">:</span><span class="at"> </span><span class="dv">49</span></span>
|
||||
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a><span class="fu">seed</span><span class="kw">:</span><span class="at"> </span><span class="dv">49</span></span>
|
||||
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb5-7"><a href="#cb5-7" 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"> output.jsonl</span></span>
|
||||
<span id="cb5-8"><a href="#cb5-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> input_output</span></span>
|
||||
<span id="cb5-9"><a href="#cb5-9" 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="cb5-10"><a href="#cb5-10" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb5-11"><a href="#cb5-11" aria-hidden="true" tabindex="-1"></a><span class="fu">sequence_len</span><span class="kw">:</span><span class="at"> </span><span class="dv">896</span></span>
|
||||
<span id="cb5-12"><a href="#cb5-12" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
|
||||
<span id="cb5-13"><a href="#cb5-13" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb5-14"><a href="#cb5-14" aria-hidden="true" tabindex="-1"></a><span class="fu">micro_batch_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">2</span></span>
|
||||
<span id="cb5-15"><a href="#cb5-15" aria-hidden="true" tabindex="-1"></a><span class="fu">gradient_accumulation_steps</span><span class="kw">:</span><span class="at"> </span><span class="dv">3</span></span>
|
||||
<span id="cb5-16"><a href="#cb5-16" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_batch_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">2</span></span>
|
||||
<span id="cb5-17"><a href="#cb5-17" aria-hidden="true" tabindex="-1"></a><span class="fu">num_epochs</span><span class="kw">:</span><span class="at"> </span><span class="dv">1</span></span>
|
||||
<span id="cb5-18"><a href="#cb5-18" aria-hidden="true" tabindex="-1"></a><span class="fu">learning_rate</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.0002</span></span>
|
||||
<span id="cb5-19"><a href="#cb5-19" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb5-20"><a href="#cb5-20" aria-hidden="true" tabindex="-1"></a><span class="fu">train_on_inputs</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
|
||||
<span id="cb5-21"><a href="#cb5-21" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
|
||||
<span id="cb5-22"><a href="#cb5-22" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">bos_token</span><span class="kw">:</span><span class="at"> </span><span class="st">"<s>"</span></span>
|
||||
<span id="cb5-23"><a href="#cb5-23" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">eos_token</span><span class="kw">:</span><span class="at"> </span><span class="st">"</s>"</span></span>
|
||||
<span id="cb5-24"><a href="#cb5-24" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">unk_token</span><span class="kw">:</span><span class="at"> </span><span class="st">"<unk>"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>You can use the following command to materialize your data. The <code>--debug</code> flag will print the tokens, along with the labels so you can verify that the correct items are being ignored:</p>
|
||||
<div class="sourceCode" id="cb6"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> preprocess training_config.yaml <span class="at">--debug</span></span>
|
||||
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a><span class="ex">...</span></span>
|
||||
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a><span class="ex">[2024-03-05</span> 23:36:46,969] <span class="pp">[</span><span class="ss">INFO</span><span class="pp">]</span> <span class="pp">[</span><span class="ss">axolotl.check_example_labels:35</span><span class="pp">]</span> <span class="pp">[</span><span class="ss">PID:607731</span><span class="pp">]</span> <span class="pp">[</span><span class="ss">RANK:0</span><span class="pp">]</span> <span class="op"><</span>s<span class="op">>(</span><span class="ex">1,</span> 1<span class="op">)</span> Hello<span class="er">(</span><span class="ex">22557,</span> 22557<span class="kw">)</span></span>
|
||||
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a><span class="kw">(</span><span class="ex">13,</span> 13<span class="kw">)</span> <span class="ex">hi</span><span class="er">(</span><span class="ex">12014,</span> 12014<span class="kw">)</span> <span class="ex">there</span><span class="er">(</span><span class="ex">736,</span> 736<span class="kw">)</span> <span class="ex">!</span><span class="er">(</span><span class="ex">28808,</span> 28808<span class="kw">)</span> <span class="bu">.</span><span class="er">(</span><span class="ex">28723,</span> 28723<span class="kw">)</span> <span class="kw">(</span><span class="ex">28705,</span> 28705<span class="kw">)</span> <span class="ex">good</span><span class="er">(</span><span class="ex">-100,</span> 1179<span class="kw">)</span> <span class="ex">bye</span><span class="er">(</span><span class="ex">-100,</span> 17664<span class="kw">)</span> <span class="kw">(</span><span class="ex">-100,</span> 28705<span class="kw">)</span> <span class="ex">fare</span><span class="er">(</span><span class="ex">19111,</span> 19111<span class="kw">)</span> <span class="ex">well</span><span class="er">(</span><span class="ex">5458,</span> 5458<span class="kw">)</span> <span class="op"><</span>/s<span class="op">>(</span><span class="ex">2,</span> 2<span class="op">)</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>The format is <code>decoded_token</code>(<code>label</code>, <code>token_id</code>), for example, <code><s>(1, 1)</code> means that the token is <code><s></code>, the label is <code>1</code> and the token_id is <code>1</code>. When the label is <code>-100</code> then that token is ignored for training.</p>
|
||||
</section>
|
||||
<section id="sec-3-check-the-prompts" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-3-check-the-prompts">3. Check the prompts</h3>
|
||||
<p>Here is another way to check the materialized output:</p>
|
||||
<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><span class="im">from</span> transformers <span class="im">import</span> AutoTokenizer</span>
|
||||
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> datasets <span class="im">import</span> load_from_disk</span>
|
||||
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> yaml</span>
|
||||
<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a>directory <span class="op">=</span> <span class="op">!</span>ls last_run_prepared<span class="op">/</span></span>
|
||||
<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a><span class="cf">with</span> <span class="bu">open</span>(<span class="st">'training_config.yaml'</span>, <span class="st">'r'</span>) <span class="im">as</span> f:</span>
|
||||
<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a> cfg <span class="op">=</span> yaml.safe_load(f)</span>
|
||||
<span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a>model_id <span class="op">=</span> cfg[<span class="st">'base_model'</span>]</span>
|
||||
<span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a>tok <span class="op">=</span> AutoTokenizer.from_pretrained(model_id)</span>
|
||||
<span id="cb7-10"><a href="#cb7-10" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_from_disk(<span class="ss">f'last_run_prepared/</span><span class="sc">{</span>directory[<span class="dv">0</span>]<span class="sc">}</span><span class="ss">/'</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<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><span class="op">>>></span> row <span class="op">=</span> ds[<span class="dv">0</span>]</span>
|
||||
<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a><span class="op">>>></span> <span class="bu">print</span>(tok.decode(row[<span class="st">'input_ids'</span>]))</span>
|
||||
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a><span class="op"><</span>s<span class="op">></span> Hello</span>
|
||||
<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a> hi there<span class="op">!</span>. goodbye farewell<span class="op"></</span>s<span class="op">></span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>We can check that the right tokens are ignored by comparing the labels to each token:</p>
|
||||
<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><span class="im">import</span> pandas <span class="im">as</span> pd</span>
|
||||
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a>pd.DataFrame([{<span class="st">'token'</span>: tok.decode(i), <span class="st">'label'</span>: l, <span class="st">'id'</span>:i} <span class="cf">for</span> i,l <span class="kw">in</span></span>
|
||||
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a> <span class="bu">zip</span>(row[<span class="st">'input_ids'</span>], row[<span class="st">'labels'</span>])])</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<table class="caption-top table">
|
||||
<thead>
|
||||
<tr class="header">
|
||||
<th>token</th>
|
||||
<th>label</th>
|
||||
<th>id</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="odd">
|
||||
<td>0</td>
|
||||
<td><s></td>
|
||||
<td>1</td>
|
||||
</tr>
|
||||
<tr class="even">
|
||||
<td>1</td>
|
||||
<td>Hello</td>
|
||||
<td>22557</td>
|
||||
</tr>
|
||||
<tr class="odd">
|
||||
<td>2</td>
|
||||
<td>\n</td>
|
||||
<td>13</td>
|
||||
</tr>
|
||||
<tr class="even">
|
||||
<td>3</td>
|
||||
<td>hi</td>
|
||||
<td>12014</td>
|
||||
</tr>
|
||||
<tr class="odd">
|
||||
<td>4</td>
|
||||
<td>there</td>
|
||||
<td>736</td>
|
||||
</tr>
|
||||
<tr class="even">
|
||||
<td>5</td>
|
||||
<td>!</td>
|
||||
<td>28808</td>
|
||||
</tr>
|
||||
<tr class="odd">
|
||||
<td>6</td>
|
||||
<td>.</td>
|
||||
<td>28723</td>
|
||||
</tr>
|
||||
<tr class="even">
|
||||
<td>7</td>
|
||||
<td></td>
|
||||
<td>28705</td>
|
||||
</tr>
|
||||
<tr class="odd">
|
||||
<td>8</td>
|
||||
<td>good</td>
|
||||
<td>-100</td>
|
||||
</tr>
|
||||
<tr class="even">
|
||||
<td>9</td>
|
||||
<td>bye</td>
|
||||
<td>-100</td>
|
||||
</tr>
|
||||
<tr class="odd">
|
||||
<td>10</td>
|
||||
<td></td>
|
||||
<td>-100</td>
|
||||
</tr>
|
||||
<tr class="even">
|
||||
<td>11</td>
|
||||
<td>fare</td>
|
||||
<td>19111</td>
|
||||
</tr>
|
||||
<tr class="odd">
|
||||
<td>12</td>
|
||||
<td>well</td>
|
||||
<td>5458</td>
|
||||
</tr>
|
||||
<tr class="even">
|
||||
<td>13</td>
|
||||
<td></s></td>
|
||||
<td>2</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p>If we look at the input data, the above table seems correct! (The jsonl version is repeated below for reference):</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">$</span> head <span class="at">-n1</span> output.jsonl <span class="kw">|</span> <span class="ex">python</span> <span class="at">-m</span> json.tool</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="cell-output cell-output-stdout">
|
||||
<pre><code>{
|
||||
"segments": [
|
||||
{
|
||||
"label": true,
|
||||
"text": "<s>Hello\n"
|
||||
},
|
||||
{
|
||||
"label": true,
|
||||
"text": "hi there!. "
|
||||
},
|
||||
{
|
||||
"label": false,
|
||||
"text": "goodbye "
|
||||
},
|
||||
{
|
||||
"label": true,
|
||||
"text": "farewell</s>"
|
||||
}
|
||||
]
|
||||
}</code></pre>
|
||||
</div>
|
||||
|
||||
|
||||
</section>
|
||||
</section>
|
||||
|
||||
</main> <!-- /main -->
|
||||
<script id="quarto-html-after-body" type="application/javascript">
|
||||
|
||||
@@ -70,10 +70,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-2f5df379a58b258e96c21c0638c20c03.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.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-141b2cdb37a94fcfd6825c1581ff795f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
|
||||
<link href="../../site_libs/bootstrap/bootstrap-0cda210ced8960466d2ee7bf22d15016.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,
|
||||
@@ -113,8 +113,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||||
<div class="navbar-container container-fluid">
|
||||
<div class="navbar-brand-container mx-auto">
|
||||
<a class="navbar-brand" href="../../index.html">
|
||||
<span class="navbar-title">Axolotl</span>
|
||||
<a href="../../index.html" class="navbar-brand navbar-brand-logo">
|
||||
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||||
</a>
|
||||
</div>
|
||||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||||
@@ -151,7 +151,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">How-To Guides</span></a>
|
||||
<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>
|
||||
@@ -160,91 +160,25 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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">Getting Started with Axolotl</span></a>
|
||||
<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 Guide</span></a>
|
||||
<span class="menu-text">Installation</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>
|
||||
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">CLI Reference</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 Guide</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Template-free prompt construction</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/nccl.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">NCCL</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>
|
||||
<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 Training Guide</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/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/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Training with AMD GPUs on HPC Systems</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 integration</span></a>
|
||||
<span class="menu-text">Inference</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
@@ -299,7 +233,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<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-3" role="navigation" aria-expanded="true">
|
||||
<span class="menu-text">Reference</span></a>
|
||||
<span class="menu-text">Deployments</span></a>
|
||||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||||
<i class="bi bi-chevron-right ms-2"></i>
|
||||
</a>
|
||||
@@ -307,18 +241,187 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<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-4" 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-4" 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-4" 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>
|
||||
</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-5" 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-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/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/multipack.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Multipack (Sample Packing)</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">Advanced Features</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/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">FDSP + 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>
|
||||
</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">Troubleshooting</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/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>
|
||||
<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">Reference</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/config.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Config options</span></a>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<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>
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
Reference in New Issue
Block a user