Built site for gh-pages

axolotl-ai-cloud · Oct 3, 2024 · ad40f7b · ad40f7b
1 parent 517ed33
commit ad40f7b
Show file tree

Hide file tree

Showing 6 changed files with 944 additions and 167 deletions.
diff --git a/.nojekyll b/.nojekyll
@@ -1 +1 @@
-4eda9161
+c81fd013
diff --git a/docs/dataset-formats/index.html b/docs/dataset-formats/index.html
@@ -363,39 +363,39 @@ <h1 class="title">Dataset Formats</h1>
 </tr>
 </thead>
 <tbody class="list">
-<tr data-index="0" data-listing-file-modified-sort="1727718988927" 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="1727917381030" data-listing-reading-time-sort="1" data-listing-word-count-sort="47" 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>
 <td>
 <span class="listing-description">Data format for a pre-training completion task.</span>
 </td>
 </tr>
-<tr data-index="1" data-listing-file-modified-sort="1727718988927" 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="1727917381030" 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>
 <td>
 <span class="listing-description">Instruction tuning formats for supervised fine-tuning.</span>
 </td>
 </tr>
-<tr data-index="2" data-listing-file-modified-sort="1727718988926" data-listing-reading-time-sort="2" data-listing-word-count-sort="254" data-listing-title-sort="Conversation" data-listing-filename-sort="conversation.qmd">
+<tr data-index="2" data-listing-file-modified-sort="1727917381030" data-listing-reading-time-sort="2" data-listing-word-count-sort="254" 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>
 <td>
 <span class="listing-description">Conversation format for supervised fine-tuning.</span>
 </td>
 </tr>
-<tr data-index="3" data-listing-file-modified-sort="1727718988927" 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="1727917381030" 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>
 <td>
 <span class="listing-description">Construct prompts without a template.</span>
 </td>
 </tr>
-<tr data-index="4" data-listing-file-modified-sort="1727718988927" 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="1727917381030" 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>

diff --git a/docs/input_output.html b/docs/input_output.html
@@ -474,7 +474,7 @@ <h3 class="anchored" data-anchor-id="check-the-prompts">3. Check the prompts</h3
 <span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a><span class="op">&gt;&gt;&gt;</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">&lt;</span>s<span class="op">&gt;</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">&lt;/</span>s<span class="op">&gt;</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 ingored by comparing the labels to each token:</p>
+<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>