Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -218,8 +218,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth1 show">
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/dataset-formats/conversation.html" class="sidebar-item-text sidebar-link active">
|
||||
<span class="menu-text">Conversation</span></a>
|
||||
<a href="../../docs/dataset-formats/pretraining.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Pre-training</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
@@ -230,8 +230,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
<div class="sidebar-item-container">
|
||||
<a href="../../docs/dataset-formats/pretraining.html" class="sidebar-item-text sidebar-link">
|
||||
<span class="menu-text">Pre-training</span></a>
|
||||
<a href="../../docs/dataset-formats/conversation.html" class="sidebar-item-text sidebar-link active">
|
||||
<span class="menu-text">Conversation</span></a>
|
||||
</div>
|
||||
</li>
|
||||
<li class="sidebar-item">
|
||||
@@ -281,15 +281,11 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<h2 id="toc-title">On this page</h2>
|
||||
|
||||
<ul>
|
||||
<li><a href="#formats" id="toc-formats" class="nav-link active" data-scroll-target="#formats">Formats</a>
|
||||
<ul class="collapse">
|
||||
<li><a href="#sharegpt" id="toc-sharegpt" class="nav-link" data-scroll-target="#sharegpt">sharegpt</a></li>
|
||||
<li><a href="#sharegpt" id="toc-sharegpt" class="nav-link active" data-scroll-target="#sharegpt">sharegpt</a></li>
|
||||
<li><a href="#pygmalion" id="toc-pygmalion" class="nav-link" data-scroll-target="#pygmalion">pygmalion</a></li>
|
||||
<li><a href="#sharegpt.load_role" id="toc-sharegpt.load_role" class="nav-link" data-scroll-target="#sharegpt.load_role">sharegpt.load_role</a></li>
|
||||
<li><a href="#sharegpt.load_guanaco" id="toc-sharegpt.load_guanaco" class="nav-link" data-scroll-target="#sharegpt.load_guanaco">sharegpt.load_guanaco</a></li>
|
||||
<li><a href="#sharegpt_jokes" id="toc-sharegpt_jokes" class="nav-link" data-scroll-target="#sharegpt_jokes">sharegpt_jokes</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#how-to-add-custom-prompts-for-instruction-tuning" id="toc-how-to-add-custom-prompts-for-instruction-tuning" class="nav-link" data-scroll-target="#how-to-add-custom-prompts-for-instruction-tuning">How to add custom prompts for instruction-tuning</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
@@ -320,10 +316,8 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
</header>
|
||||
|
||||
|
||||
<section id="formats" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="formats">Formats</h2>
|
||||
<section id="sharegpt" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sharegpt">sharegpt</h3>
|
||||
<section id="sharegpt" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="sharegpt">sharegpt</h2>
|
||||
<p>conversations where <code>from</code> is <code>human</code>/<code>gpt</code>. (optional: first row with role <code>system</code> to override default system prompt)</p>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
@@ -331,20 +325,21 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
</div>
|
||||
<div class="sourceCode" id="cb1" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
<p>Note: <code>type: sharegpt</code> opens a special config <code>conversation:</code> that enables conversions to many Conversation types. See <a href="../docs/config.qmd">the docs</a> for all config options.</p>
|
||||
<p>Note: <code>type: sharegpt</code> opens special configs: - <code>conversation</code>: enables conversions to many Conversation types. Refer to the ‘name’ <a href="https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py">here</a> for options. - <code>roles</code>: allows you to specify the roles for input and output. This is useful for datasets with custom roles such as <code>tool</code> etc to support masking. - <code>field_human</code>: specify the key to use instead of <code>human</code> in the conversation. - <code>field_model</code>: specify the key to use instead of <code>gpt</code> in the conversation.</p>
|
||||
<div class="sourceCode" id="cb2"><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">datasets</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="fu">path</span><span class="kw">:</span><span class="at"> ...</span></span>
|
||||
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> sharegpt</span></span>
|
||||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">conversation</span><span class="kw">:</span><span class="co"> # Options (see Conversation 'name'): https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py</span></span>
|
||||
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_human</span><span class="kw">:</span><span class="co"> # Optional[str]. Human key to use for conversation.</span></span>
|
||||
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_model</span><span class="kw">:</span><span class="co"> # Optional[str]. Assistant key to use for conversation.</span></span>
|
||||
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="co"> # Add additional keys from your dataset as input or output roles</span></span>
|
||||
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">roles</span><span class="kw">:</span></span>
|
||||
<span id="cb2-10"><a href="#cb2-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">input</span><span class="kw">:</span><span class="co"> # Optional[List[str]]. These will be masked based on train_on_input</span></span>
|
||||
<span id="cb2-11"><a href="#cb2-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">output</span><span class="kw">:</span><span class="co"> # Optional[List[str]].</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</section>
|
||||
<section id="pygmalion" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="pygmalion">pygmalion</h3>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>data.jsonl</strong></pre>
|
||||
</div>
|
||||
<div class="sourceCode" id="cb2" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="sharegpt.load_role" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sharegpt.load_role">sharegpt.load_role</h3>
|
||||
<p>conversations where <code>role</code> is used instead of <code>from</code></p>
|
||||
<section id="pygmalion" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="pygmalion">pygmalion</h2>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>data.jsonl</strong></pre>
|
||||
@@ -352,52 +347,35 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<div class="sourceCode" id="cb3" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="sharegpt.load_guanaco" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sharegpt.load_guanaco">sharegpt.load_guanaco</h3>
|
||||
<section id="sharegpt.load_role" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="sharegpt.load_role">sharegpt.load_role</h2>
|
||||
<p>conversations where <code>role</code> is used instead of <code>from</code></p>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>data.jsonl</strong></pre>
|
||||
</div>
|
||||
<div class="sourceCode" id="cb4" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"role"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="sharegpt.load_guanaco" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="sharegpt.load_guanaco">sharegpt.load_guanaco</h2>
|
||||
<p>conversations where <code>from</code> is <code>prompter</code> <code>assistant</code> instead of default sharegpt</p>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>data.jsonl</strong></pre>
|
||||
</div>
|
||||
<div class="sourceCode" id="cb4" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb5" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"from"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"value"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="sharegpt_jokes" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sharegpt_jokes">sharegpt_jokes</h3>
|
||||
<section id="sharegpt_jokes" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="sharegpt_jokes">sharegpt_jokes</h2>
|
||||
<p>creates a chat where bot is asked to tell a joke, then explain why the joke is funny</p>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>data.jsonl</strong></pre>
|
||||
</div>
|
||||
<div class="sourceCode" id="cb5" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"title"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"explanation"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb6" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"conversations"</span><span class="fu">:</span> <span class="ot">[</span><span class="fu">{</span><span class="dt">"title"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"explanation"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span><span class="ot">]</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="how-to-add-custom-prompts-for-instruction-tuning" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="how-to-add-custom-prompts-for-instruction-tuning">How to add custom prompts for instruction-tuning</h2>
|
||||
<p>For a dataset that is preprocessed for instruction purposes:</p>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>data.jsonl</strong></pre>
|
||||
</div>
|
||||
<div class="sourceCode" id="cb6" data-filename="data.jsonl"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="fu">{</span><span class="dt">"input"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">,</span> <span class="dt">"output"</span><span class="fu">:</span> <span class="st">"..."</span><span class="fu">}</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
<p>You can use this example in your YAML config:</p>
|
||||
<div class="code-with-filename">
|
||||
<div class="code-with-filename-file">
|
||||
<pre><strong>config.yaml</strong></pre>
|
||||
</div>
|
||||
<div class="sourceCode" id="cb7" data-filename="config.yaml"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> repo</span></span>
|
||||
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span></span>
|
||||
<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">system_prompt</span><span class="kw">:</span><span class="at"> </span><span class="st">""</span></span>
|
||||
<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_system</span><span class="kw">:</span><span class="at"> system</span></span>
|
||||
<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_instruction</span><span class="kw">:</span><span class="at"> input</span></span>
|
||||
<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_output</span><span class="kw">:</span><span class="at"> output</span></span>
|
||||
<span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">format</span><span class="kw">:</span><span class="at"> </span><span class="st">"[INST] {instruction} [/INST]"</span></span>
|
||||
<span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">no_input_format</span><span class="kw">:</span><span class="at"> </span><span class="st">"[INST] {instruction} [/INST]"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
<p>See full config options under <a href="../docs/config.qmd">here</a>.</p>
|
||||
|
||||
|
||||
</section>
|
||||
|
||||
Reference in New Issue
Block a user