tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Built site for gh-pages

Browse Source
This commit is contained in:
Quarto GHA Workflow Runner
2025-07-12 14:23:07 +00:00
parent 5efa2959d4
commit 1dae0505ba
193 changed files with 4705 additions and 4574 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/api/core.trainers.trl.html
View File

@@ -74,7 +74,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-2fef5ea3f8957b3e4ecc936fc74692ca.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-ed9d63b928ec3538d7b05c99c63ac09f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
<link href="../../site_libs/bootstrap/bootstrap-4286dd70669dc30dbb11cd1e43bae81e.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,
@@ -476,7 +476,6 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<li><a href="#axolotl.core.trainers.trl.AxolotlORPOTrainer" id="toc-axolotl.core.trainers.trl.AxolotlORPOTrainer" class="nav-link" data-scroll-target="#axolotl.core.trainers.trl.AxolotlORPOTrainer">AxolotlORPOTrainer</a></li>
<li><a href="#axolotl.core.trainers.trl.AxolotlPRMTrainer" id="toc-axolotl.core.trainers.trl.AxolotlPRMTrainer" class="nav-link" data-scroll-target="#axolotl.core.trainers.trl.AxolotlPRMTrainer">AxolotlPRMTrainer</a></li>
<li><a href="#axolotl.core.trainers.trl.AxolotlRewardTrainer" id="toc-axolotl.core.trainers.trl.AxolotlRewardTrainer" class="nav-link" data-scroll-target="#axolotl.core.trainers.trl.AxolotlRewardTrainer">AxolotlRewardTrainer</a></li>
<li><a href="#axolotl.core.trainers.trl.TRLPPOTrainer" id="toc-axolotl.core.trainers.trl.TRLPPOTrainer" class="nav-link" data-scroll-target="#axolotl.core.trainers.trl.TRLPPOTrainer">TRLPPOTrainer</a></li>
</ul></li>
</ul></li>
</ul>
@@ -491,7 +490,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<section id="axolotl.core.trainers.trl" class="level1">
<h1>core.trainers.trl</h1>
<p><code>core.trainers.trl</code></p>
<p>Module for TRL PPO trainer</p>
<p>Module for TRL RL trainers</p>
<section id="classes" class="level2">
<h2 class="anchored" data-anchor-id="classes">Classes</h2>
<table class="caption-top table">
@@ -522,10 +521,6 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<td><a href="#axolotl.core.trainers.trl.AxolotlRewardTrainer">AxolotlRewardTrainer</a></td>
<td>Extend the base RewardTrainer for axolotl helpers</td>
</tr>
<tr class="even">
<td><a href="#axolotl.core.trainers.trl.TRLPPOTrainer">TRLPPOTrainer</a></td>
<td>Wrapper for TRL PPO trainer to handle customizations</td>
</tr>
</tbody>
</table>
<section id="axolotl.core.trainers.trl.AxolotlCPOTrainer" class="level3">
@@ -552,11 +547,6 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<h3 class="anchored" data-anchor-id="axolotl.core.trainers.trl.AxolotlRewardTrainer">AxolotlRewardTrainer</h3>
<div class="sourceCode" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a>core.trainers.trl.AxolotlRewardTrainer(<span class="op">*</span>args, <span class="op">**</span>kwargs)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Extend the base RewardTrainer for axolotl helpers</p>
</section>
<section id="axolotl.core.trainers.trl.TRLPPOTrainer" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.core.trainers.trl.TRLPPOTrainer">TRLPPOTrainer</h3>
<div class="sourceCode" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>core.trainers.trl.TRLPPOTrainer()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Wrapper for TRL PPO trainer to handle customizations</p>
</section>