Built site for gh-pages

This commit is contained in:
Quarto GHA Workflow Runner
2025-06-10 23:55:31 +00:00
parent 15858cd29a
commit 89d7105f8f
8 changed files with 453 additions and 288 deletions

View File

@@ -20,6 +20,41 @@ 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 */
html { -webkit-text-size-adjust: 100%; }
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { display: inline-block; 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 { 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>
@@ -432,7 +467,13 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<h2 id="toc-title">On this page</h2>
<ul>
<li><a href="#axolotl.utils.data.sft" id="toc-axolotl.utils.data.sft" class="nav-link active" data-scroll-target="#axolotl.utils.data.sft">utils.data.sft</a></li>
<li><a href="#axolotl.utils.data.sft" id="toc-axolotl.utils.data.sft" class="nav-link active" data-scroll-target="#axolotl.utils.data.sft">utils.data.sft</a>
<ul class="collapse">
<li><a href="#functions" id="toc-functions" class="nav-link" data-scroll-target="#functions">Functions</a>
<ul class="collapse">
<li><a href="#axolotl.utils.data.sft.prepare_datasets" id="toc-axolotl.utils.data.sft.prepare_datasets" class="nav-link" data-scroll-target="#axolotl.utils.data.sft.prepare_datasets">prepare_datasets</a></li>
</ul></li>
</ul></li>
</ul>
</nav>
</div>
@@ -445,9 +486,105 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<section id="axolotl.utils.data.sft" class="level1">
<h1>utils.data.sft</h1>
<p><code>utils.data.sft</code></p>
<p>data handling specific to SFT</p>
<p>Data handling specific to SFT.</p>
<section id="functions" class="level2">
<h2 class="anchored" data-anchor-id="functions">Functions</h2>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td><a href="#axolotl.utils.data.sft.prepare_datasets">prepare_datasets</a></td>
<td>Prepare training and evaluation datasets based on configuration.</td>
</tr>
</tbody>
</table>
<section id="axolotl.utils.data.sft.prepare_datasets" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.utils.data.sft.prepare_datasets">prepare_datasets</h3>
<div class="sourceCode" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a>utils.data.sft.prepare_datasets(</span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a> cfg,</span>
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a> tokenizer,</span>
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a> processor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a> preprocess_iterable<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Prepare training and evaluation datasets based on configuration.</p>
<section id="parameters" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters">Parameters</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 19%">
<col style="width: 21%">
<col style="width: 48%">
<col style="width: 10%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>cfg</td>
<td>DictDefault</td>
<td>Dictionary mapping <code>axolotl</code> config keys to values.</td>
<td><em>required</em></td>
</tr>
<tr class="even">
<td>tokenizer</td>
<td>PreTrainedTokenizer</td>
<td>Tokenizer to use for processing text.</td>
<td><em>required</em></td>
</tr>
<tr class="odd">
<td>processor</td>
<td>ProcessorMixin | None</td>
<td>Optional processor for multimodal datasets.</td>
<td><code>None</code></td>
</tr>
<tr class="even">
<td>preprocess_iterable</td>
<td>bool</td>
<td>Whether to use iterable preprocessing.</td>
<td><code>False</code></td>
</tr>
</tbody>
</table>
</section>
<section id="returns" class="level4 doc-section doc-section-returns">
<h4 class="doc-section doc-section-returns anchored" data-anchor-id="returns">Returns</h4>
<table class="caption-top table">
<colgroup>
<col style="width: 5%">
<col style="width: 53%">
<col style="width: 41%">
</colgroup>
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td></td>
<td>tuple[IterableDataset | Dataset, Dataset | None, int, list[Prompter | None]]</td>
<td>Tuple of (train_dataset, eval_dataset, total_steps, prompters).</td>
</tr>
</tbody>
</table>
</section>
</section>
</section>
</section>
</main> <!-- /main -->