Built site for gh-pages
This commit is contained in:
@@ -363,7 +363,7 @@ Description
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody class="list">
|
||||
<tr data-index="0" data-listing-file-modified-sort="1736783064835" data-listing-reading-time-sort="1" data-listing-word-count-sort="47" data-listing-title-sort="Pre-training" data-listing-filename-sort="pretraining.qmd">
|
||||
<tr data-index="0" data-listing-file-modified-sort="1736783098940" data-listing-reading-time-sort="1" data-listing-word-count-sort="92" data-listing-title-sort="Pre-training" data-listing-filename-sort="pretraining.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/pretraining.html" class="title listing-title">Pre-training</a>
|
||||
</td>
|
||||
@@ -371,7 +371,7 @@ Description
|
||||
<span class="listing-description">Data format for a pre-training completion task.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="1" data-listing-file-modified-sort="1736783064835" data-listing-reading-time-sort="2" data-listing-word-count-sort="308" data-listing-title-sort="Instruction Tuning" data-listing-filename-sort="inst_tune.qmd">
|
||||
<tr data-index="1" data-listing-file-modified-sort="1736783098940" data-listing-reading-time-sort="2" data-listing-word-count-sort="308" data-listing-title-sort="Instruction Tuning" data-listing-filename-sort="inst_tune.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/inst_tune.html" class="title listing-title">Instruction Tuning</a>
|
||||
</td>
|
||||
@@ -379,7 +379,7 @@ Description
|
||||
<span class="listing-description">Instruction tuning formats for supervised fine-tuning.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="2" data-listing-file-modified-sort="1736783064835" data-listing-reading-time-sort="4" data-listing-word-count-sort="625" data-listing-title-sort="Conversation" data-listing-filename-sort="conversation.qmd">
|
||||
<tr data-index="2" data-listing-file-modified-sort="1736783098940" data-listing-reading-time-sort="4" data-listing-word-count-sort="625" data-listing-title-sort="Conversation" data-listing-filename-sort="conversation.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/conversation.html" class="title listing-title">Conversation</a>
|
||||
</td>
|
||||
@@ -387,7 +387,7 @@ Description
|
||||
<span class="listing-description">Conversation format for supervised fine-tuning.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="3" data-listing-file-modified-sort="1736783064835" data-listing-reading-time-sort="1" data-listing-word-count-sort="3" data-listing-title-sort="Template-Free" data-listing-filename-sort="template_free.qmd">
|
||||
<tr data-index="3" data-listing-file-modified-sort="1736783098940" data-listing-reading-time-sort="1" data-listing-word-count-sort="3" data-listing-title-sort="Template-Free" data-listing-filename-sort="template_free.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/template_free.html" class="title listing-title">Template-Free</a>
|
||||
</td>
|
||||
@@ -395,7 +395,7 @@ Description
|
||||
<span class="listing-description">Construct prompts without a template.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="4" data-listing-file-modified-sort="1736783064835" data-listing-reading-time-sort="1" data-listing-word-count-sort="92" data-listing-title-sort="Custom Pre-Tokenized Dataset" data-listing-filename-sort="tokenized.qmd">
|
||||
<tr data-index="4" data-listing-file-modified-sort="1736783098940" data-listing-reading-time-sort="1" data-listing-word-count-sort="92" data-listing-title-sort="Custom Pre-Tokenized Dataset" data-listing-filename-sort="tokenized.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/tokenized.html" class="title listing-title">Custom Pre-Tokenized Dataset</a>
|
||||
</td>
|
||||
|
||||
@@ -342,8 +342,15 @@ Streaming is recommended for large datasets
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>config.yaml</strong></pre>
|
||||
</div>
|
||||
<div class="sourceCode" id="cb2" data-filename="config.yaml"><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">pretraining_dataset</span><span class="kw">:</span><span class="co"> # hf path only</span></span>
|
||||
<span id="cb2-2"><a href="#cb2-2" 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>
|
||||
<div class="sourceCode" id="cb2" data-filename="config.yaml"><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">pretraining_dataset</span><span class="kw">:</span></span>
|
||||
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">name</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="fu">path</span><span class="kw">:</span></span>
|
||||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span></span>
|
||||
<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>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
Reference in New Issue
Block a user