Built site for gh-pages

This commit is contained in:
Quarto GHA Workflow Runner
2025-06-13 14:02:59 +00:00
parent 7cd59362e8
commit 84db47f3c0
4 changed files with 197 additions and 197 deletions

View File

@@ -614,7 +614,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="axolotl.common.datasets.load_preference_datasets" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.common.datasets.load_preference_datasets">load_preference_datasets</h3>
<div class="sourceCode" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>common.datasets.load_preference_datasets(cfg, cli_args)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>common.datasets.load_preference_datasets(cfg, cli_args<span class="op">=</span><span class="va">None</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Loads one or more training or evaluation datasets for RL training using paired
preference data, calling <code>axolotl.utils.data.rl.prepare_preference_datasets</code>.
Optionally, logs out debug information.</p>
@@ -623,8 +623,8 @@ Optionally, logs out debug information.</p>
<table class="caption-top table">
<colgroup>
<col style="width: 8%">
<col style="width: 33%">
<col style="width: 47%">
<col style="width: 37%">
<col style="width: 44%">
<col style="width: 10%">
</colgroup>
<thead>
@@ -644,9 +644,9 @@ Optionally, logs out debug information.</p>
</tr>
<tr class="even">
<td>cli_args</td>
<td>PreprocessCliArgs | TrainerCliArgs</td>
<td>PreprocessCliArgs | TrainerCliArgs | None</td>
<td>Command-specific CLI arguments.</td>
<td><em>required</em></td>
<td><code>None</code></td>
</tr>
</tbody>
</table>