Built site for gh-pages
This commit is contained in:
@@ -519,16 +519,21 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<section id="installation" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="installation">Installation</h3>
|
||||
<p>Run the following command to install <code>cut_cross_entropy[transformers]</code> if you don’t have it already.</p>
|
||||
<div class="sourceCode" id="cb1"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="ex">python</span> scripts/cutcrossentropy_install.py <span class="kw">|</span> <span class="fu">sh</span></span>
|
||||
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="ex">pip3</span> uninstall <span class="at">-y</span> cut-cross-entropy <span class="kw">&&</span> <span class="ex">pip3</span> install <span class="st">"cut-cross-entropy[transformers] @ git+https://github.com/apple/ml-cross-entropy.git@bad6f7b49c75fdec69471abb71b4cddd0f0c6438"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<ul>
|
||||
<li>If you are in dev environment</li>
|
||||
</ul>
|
||||
<div class="sourceCode" id="cb1"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="ex">python</span> scripts/cutcrossentropy_install.py <span class="kw">|</span> <span class="fu">sh</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<ul>
|
||||
<li>If you are installing from pip</li>
|
||||
</ul>
|
||||
<div class="sourceCode" id="cb2"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="ex">pip3</span> uninstall <span class="at">-y</span> cut-cross-entropy <span class="kw">&&</span> <span class="ex">pip3</span> install <span class="st">"cut-cross-entropy[transformers] @ git+https://github.com/apple/ml-cross-entropy.git@bad6f7b49c75fdec69471abb71b4cddd0f0c6438"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</section>
|
||||
<section id="usage" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="usage">Usage</h3>
|
||||
<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">plugins</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"> axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin</span></span>
|
||||
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="fu">cut_cross_entropy</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></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 yaml code-with-copy"><code class="sourceCode yaml"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin</span></span>
|
||||
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a><span class="fu">cut_cross_entropy</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</section>
|
||||
<section id="supported-models" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="supported-models">Supported Models</h3>
|
||||
@@ -551,17 +556,17 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
</section>
|
||||
<section id="citation" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="citation">Citation</h3>
|
||||
<div class="sourceCode" id="cb3"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="va">@article</span>{<span class="ot">wijmans2024cut</span>,</span>
|
||||
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span> = {Erik Wijmans and</span>
|
||||
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a> Brody Huval and</span>
|
||||
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a> Alexander Hertzberg and</span>
|
||||
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a> Vladlen Koltun and</span>
|
||||
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a> Philipp Kr<span class="ch">\"</span>ahenb<span class="ch">\"</span>uhl},</span>
|
||||
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span> = {Cut Your Losses in Large-Vocabulary Language Models},</span>
|
||||
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">journal</span> = {arXiv},</span>
|
||||
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span> = {2024},</span>
|
||||
<span id="cb3-10"><a href="#cb3-10" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span> = {https://arxiv.org/abs/2411.09009},</span>
|
||||
<span id="cb3-11"><a href="#cb3-11" aria-hidden="true" tabindex="-1"></a>}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb4"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="va">@article</span>{<span class="ot">wijmans2024cut</span>,</span>
|
||||
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span> = {Erik Wijmans and</span>
|
||||
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a> Brody Huval and</span>
|
||||
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a> Alexander Hertzberg and</span>
|
||||
<span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a> Vladlen Koltun and</span>
|
||||
<span id="cb4-6"><a href="#cb4-6" aria-hidden="true" tabindex="-1"></a> Philipp Kr<span class="ch">\"</span>ahenb<span class="ch">\"</span>uhl},</span>
|
||||
<span id="cb4-7"><a href="#cb4-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span> = {Cut Your Losses in Large-Vocabulary Language Models},</span>
|
||||
<span id="cb4-8"><a href="#cb4-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">journal</span> = {arXiv},</span>
|
||||
<span id="cb4-9"><a href="#cb4-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span> = {2024},</span>
|
||||
<span id="cb4-10"><a href="#cb4-10" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span> = {https://arxiv.org/abs/2411.09009},</span>
|
||||
<span id="cb4-11"><a href="#cb4-11" 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>Please see reference <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/cut_cross_entropy">here</a></p>
|
||||
</section>
|
||||
</section>
|
||||
@@ -570,20 +575,20 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<p>See https://github.com/ironjr/grokfast</p>
|
||||
<section id="usage-1" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="usage-1">Usage</h3>
|
||||
<div class="sourceCode" id="cb4"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.grokfast.GrokfastPlugin</span></span>
|
||||
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a><span class="fu">grokfast_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">2.0</span></span>
|
||||
<span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a><span class="fu">grokfast_lamb</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.98</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb5"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.grokfast.GrokfastPlugin</span></span>
|
||||
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a><span class="fu">grokfast_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">2.0</span></span>
|
||||
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a><span class="fu">grokfast_lamb</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.98</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</section>
|
||||
<section id="citation-1" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="citation-1">Citation</h3>
|
||||
<div class="sourceCode" id="cb5"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="va">@article</span>{<span class="ot">lee2024grokfast</span>,</span>
|
||||
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span>={{Grokfast}: Accelerated Grokking by Amplifying Slow Gradients},</span>
|
||||
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span>={Lee, Jaerin and Kang, Bong Gyun and Kim, Kihoon and Lee, Kyoung Mu},</span>
|
||||
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">journal</span>={arXiv preprint arXiv:2405.20233},</span>
|
||||
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span>={2024}</span>
|
||||
<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a>}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb6"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="va">@article</span>{<span class="ot">lee2024grokfast</span>,</span>
|
||||
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span>={{Grokfast}: Accelerated Grokking by Amplifying Slow Gradients},</span>
|
||||
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span>={Lee, Jaerin and Kang, Bong Gyun and Kim, Kihoon and Lee, Kyoung Mu},</span>
|
||||
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">journal</span>={arXiv preprint arXiv:2405.20233},</span>
|
||||
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span>={2024}</span>
|
||||
<span id="cb6-6"><a href="#cb6-6" 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>Please see reference <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/grokfast">here</a></p>
|
||||
</section>
|
||||
</section>
|
||||
@@ -591,21 +596,21 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<h2 class="anchored" data-anchor-id="knowledge-distillation-kd">Knowledge Distillation (KD)</h2>
|
||||
<section id="usage-2" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="usage-2">Usage</h3>
|
||||
<div class="sourceCode" id="cb6"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="st">"axolotl.integrations.kd.KDPlugin"</span></span>
|
||||
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_trainer</span><span class="kw">:</span><span class="at"> </span><span class="ch">True</span></span>
|
||||
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_ce_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.1</span></span>
|
||||
<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.9</span></span>
|
||||
<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_temperature</span><span class="kw">:</span><span class="at"> </span><span class="fl">1.0</span></span>
|
||||
<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a><span class="fu">torch_compile</span><span class="kw">:</span><span class="at"> </span><span class="ch">True</span><span class="co"> # torch>=2.5.1, recommended to reduce vram</span></span>
|
||||
<span id="cb6-10"><a href="#cb6-10" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb6-12"><a href="#cb6-12" 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"> ...</span></span>
|
||||
<span id="cb6-13"><a href="#cb6-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> </span><span class="st">"axolotl.integrations.kd.chat_template"</span></span>
|
||||
<span id="cb6-14"><a href="#cb6-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> </span><span class="st">"messages_combined"</span></span>
|
||||
<span id="cb6-15"><a href="#cb6-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">logprobs_field</span><span class="kw">:</span><span class="at"> </span><span class="st">"llm_text_generation_vllm_logprobs"</span><span class="co"> # for kd only, field of logprobs</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb7"><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">plugins</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="st">"axolotl.integrations.kd.KDPlugin"</span></span>
|
||||
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_trainer</span><span class="kw">:</span><span class="at"> </span><span class="ch">True</span></span>
|
||||
<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_ce_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.1</span></span>
|
||||
<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.9</span></span>
|
||||
<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a><span class="fu">kd_temperature</span><span class="kw">:</span><span class="at"> </span><span class="fl">1.0</span></span>
|
||||
<span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a><span class="fu">torch_compile</span><span class="kw">:</span><span class="at"> </span><span class="ch">True</span><span class="co"> # torch>=2.5.1, recommended to reduce vram</span></span>
|
||||
<span id="cb7-10"><a href="#cb7-10" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb7-11"><a href="#cb7-11" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb7-12"><a href="#cb7-12" 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"> ...</span></span>
|
||||
<span id="cb7-13"><a href="#cb7-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> </span><span class="st">"axolotl.integrations.kd.chat_template"</span></span>
|
||||
<span id="cb7-14"><a href="#cb7-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">field_messages</span><span class="kw">:</span><span class="at"> </span><span class="st">"messages_combined"</span></span>
|
||||
<span id="cb7-15"><a href="#cb7-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">logprobs_field</span><span class="kw">:</span><span class="at"> </span><span class="st">"llm_text_generation_vllm_logprobs"</span><span class="co"> # for kd only, field of logprobs</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>An example dataset can be found at <a href="https://huggingface.co/datasets/axolotl-ai-co/evolkit-logprobs-pipeline-75k-v2-sample"><code>axolotl-ai-co/evolkit-logprobs-pipeline-75k-v2-sample</code></a></p>
|
||||
<p>Please see reference <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/kd">here</a></p>
|
||||
</section>
|
||||
@@ -621,13 +626,13 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<p>See https://github.com/linkedin/Liger-Kernel</p>
|
||||
<section id="usage-3" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="usage-3">Usage</h3>
|
||||
<div class="sourceCode" id="cb7"><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">plugins</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"> axolotl.integrations.liger.LigerPlugin</span></span>
|
||||
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_rope</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_rms_norm</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_glu_activation</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_layer_norm</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_fused_linear_cross_entropy</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb8"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.liger.LigerPlugin</span></span>
|
||||
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_rope</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_rms_norm</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_glu_activation</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb8-6"><a href="#cb8-6" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_layer_norm</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb8-7"><a href="#cb8-7" aria-hidden="true" tabindex="-1"></a><span class="fu">liger_fused_linear_cross_entropy</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</section>
|
||||
<section id="supported-models-1" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="supported-models-1">Supported Models</h3>
|
||||
@@ -653,16 +658,16 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
</section>
|
||||
<section id="citation-2" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="citation-2">Citation</h3>
|
||||
<div class="sourceCode" id="cb8"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="va">@article</span>{<span class="ot">hsu2024ligerkernelefficienttriton</span>,</span>
|
||||
<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span>={Liger Kernel: Efficient Triton Kernels for LLM Training},</span>
|
||||
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span>={Pin-Lun Hsu and Yun Dai and Vignesh Kothapalli and Qingquan Song and Shao Tang and Siyu Zhu and Steven Shimizu and Shivam Sahni and Haowen Ning and Yanning Chen},</span>
|
||||
<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span>={2024},</span>
|
||||
<span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">eprint</span>={2410.10989},</span>
|
||||
<span id="cb8-6"><a href="#cb8-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">archivePrefix</span>={arXiv},</span>
|
||||
<span id="cb8-7"><a href="#cb8-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">primaryClass</span>={cs.LG},</span>
|
||||
<span id="cb8-8"><a href="#cb8-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span>={https://arxiv.org/abs/2410.10989},</span>
|
||||
<span id="cb8-9"><a href="#cb8-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">journal</span>={arXiv preprint arXiv:2410.10989},</span>
|
||||
<span id="cb8-10"><a href="#cb8-10" aria-hidden="true" tabindex="-1"></a>}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb9"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="va">@article</span>{<span class="ot">hsu2024ligerkernelefficienttriton</span>,</span>
|
||||
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span>={Liger Kernel: Efficient Triton Kernels for LLM Training},</span>
|
||||
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span>={Pin-Lun Hsu and Yun Dai and Vignesh Kothapalli and Qingquan Song and Shao Tang and Siyu Zhu and Steven Shimizu and Shivam Sahni and Haowen Ning and Yanning Chen},</span>
|
||||
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span>={2024},</span>
|
||||
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">eprint</span>={2410.10989},</span>
|
||||
<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">archivePrefix</span>={arXiv},</span>
|
||||
<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">primaryClass</span>={cs.LG},</span>
|
||||
<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span>={https://arxiv.org/abs/2410.10989},</span>
|
||||
<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">journal</span>={arXiv preprint arXiv:2410.10989},</span>
|
||||
<span id="cb9-10"><a href="#cb9-10" 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>Please see reference <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/liger">here</a></p>
|
||||
</section>
|
||||
</section>
|
||||
@@ -672,29 +677,29 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<p>See https://github.com/EleutherAI/lm-evaluation-harness</p>
|
||||
<section id="usage-4" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="usage-4">Usage</h3>
|
||||
<div class="sourceCode" id="cb9"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.lm_eval.LMEvalPlugin</span></span>
|
||||
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a><span class="fu">lm_eval_tasks</span><span class="kw">:</span></span>
|
||||
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> gsm8k</span></span>
|
||||
<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> hellaswag</span></span>
|
||||
<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> arc_easy</span></span>
|
||||
<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a><span class="fu">lm_eval_batch_size</span><span class="kw">:</span><span class="co"> # Batch size for evaluation</span></span>
|
||||
<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="co"> # Directory to save evaluation results</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb10"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.lm_eval.LMEvalPlugin</span></span>
|
||||
<span id="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a><span class="fu">lm_eval_tasks</span><span class="kw">:</span></span>
|
||||
<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> gsm8k</span></span>
|
||||
<span id="cb10-6"><a href="#cb10-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> hellaswag</span></span>
|
||||
<span id="cb10-7"><a href="#cb10-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> arc_easy</span></span>
|
||||
<span id="cb10-8"><a href="#cb10-8" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb10-9"><a href="#cb10-9" aria-hidden="true" tabindex="-1"></a><span class="fu">lm_eval_batch_size</span><span class="kw">:</span><span class="co"> # Batch size for evaluation</span></span>
|
||||
<span id="cb10-10"><a href="#cb10-10" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="co"> # Directory to save evaluation results</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</section>
|
||||
<section id="citation-3" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="citation-3">Citation</h3>
|
||||
<div class="sourceCode" id="cb10"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="va">@misc</span>{<span class="ot">eval</span>-<span class="ot">harness</span>,</span>
|
||||
<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span> = {Gao, Leo and Tow, Jonathan and Abbasi, Baber and Biderman, Stella and Black, Sid and DiPofi, Anthony and Foster, Charles and Golding, Laurence and Hsu, Jeffrey and Le Noac'h, Alain and Li, Haonan and McDonell, Kyle and Muennighoff, Niklas and Ociepa, Chris and Phang, Jason and Reynolds, Laria and Schoelkopf, Hailey and Skowron, Aviya and Sutawika, Lintang and Tang, Eric and Thite, Anish and Wang, Ben and Wang, Kevin and Zou, Andy},</span>
|
||||
<span id="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span> = {A framework for few-shot language model evaluation},</span>
|
||||
<span id="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">month</span> = 07,</span>
|
||||
<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span> = 2024,</span>
|
||||
<span id="cb10-6"><a href="#cb10-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">publisher</span> = {Zenodo},</span>
|
||||
<span id="cb10-7"><a href="#cb10-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">version</span> = {v0.4.3},</span>
|
||||
<span id="cb10-8"><a href="#cb10-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">doi</span> = {10.5281/zenodo.12608602},</span>
|
||||
<span id="cb10-9"><a href="#cb10-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span> = {https://zenodo.org/records/12608602}</span>
|
||||
<span id="cb10-10"><a href="#cb10-10" aria-hidden="true" tabindex="-1"></a>}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb11"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="va">@misc</span>{<span class="ot">eval</span>-<span class="ot">harness</span>,</span>
|
||||
<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span> = {Gao, Leo and Tow, Jonathan and Abbasi, Baber and Biderman, Stella and Black, Sid and DiPofi, Anthony and Foster, Charles and Golding, Laurence and Hsu, Jeffrey and Le Noac'h, Alain and Li, Haonan and McDonell, Kyle and Muennighoff, Niklas and Ociepa, Chris and Phang, Jason and Reynolds, Laria and Schoelkopf, Hailey and Skowron, Aviya and Sutawika, Lintang and Tang, Eric and Thite, Anish and Wang, Ben and Wang, Kevin and Zou, Andy},</span>
|
||||
<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span> = {A framework for few-shot language model evaluation},</span>
|
||||
<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">month</span> = 07,</span>
|
||||
<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span> = 2024,</span>
|
||||
<span id="cb11-6"><a href="#cb11-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">publisher</span> = {Zenodo},</span>
|
||||
<span id="cb11-7"><a href="#cb11-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">version</span> = {v0.4.3},</span>
|
||||
<span id="cb11-8"><a href="#cb11-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">doi</span> = {10.5281/zenodo.12608602},</span>
|
||||
<span id="cb11-9"><a href="#cb11-9" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span> = {https://zenodo.org/records/12608602}</span>
|
||||
<span id="cb11-10"><a href="#cb11-10" 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>Please see reference <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/lm_eval">here</a></p>
|
||||
</section>
|
||||
</section>
|
||||
@@ -710,23 +715,23 @@ By identifying the top n% of layers with the highest SNR, you can optimize train
|
||||
</section>
|
||||
<section id="usage-5" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="usage-5">Usage</h3>
|
||||
<div class="sourceCode" id="cb11"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.spectrum.SpectrumPlugin</span></span>
|
||||
<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a><span class="fu">spectrum_top_fraction</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.5</span></span>
|
||||
<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a><span class="fu">spectrum_model_name</span><span class="kw">:</span><span class="at"> meta-llama/Meta-Llama-3.1-8B</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb12"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.spectrum.SpectrumPlugin</span></span>
|
||||
<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb12-4"><a href="#cb12-4" aria-hidden="true" tabindex="-1"></a><span class="fu">spectrum_top_fraction</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.5</span></span>
|
||||
<span id="cb12-5"><a href="#cb12-5" aria-hidden="true" tabindex="-1"></a><span class="fu">spectrum_model_name</span><span class="kw">:</span><span class="at"> meta-llama/Meta-Llama-3.1-8B</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</section>
|
||||
<section id="citation-4" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="citation-4">Citation</h3>
|
||||
<div class="sourceCode" id="cb12"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="va">@misc</span>{<span class="ot">hartford2024spectrumtargetedtrainingsignal</span>,</span>
|
||||
<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span>={Spectrum: Targeted Training on Signal to Noise Ratio},</span>
|
||||
<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span>={Eric Hartford and Lucas Atkins and Fernando Fernandes Neto and David Golchinfar},</span>
|
||||
<span id="cb12-4"><a href="#cb12-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span>={2024},</span>
|
||||
<span id="cb12-5"><a href="#cb12-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">eprint</span>={2406.06623},</span>
|
||||
<span id="cb12-6"><a href="#cb12-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">archivePrefix</span>={arXiv},</span>
|
||||
<span id="cb12-7"><a href="#cb12-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">primaryClass</span>={cs.LG},</span>
|
||||
<span id="cb12-8"><a href="#cb12-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span>={https://arxiv.org/abs/2406.06623},</span>
|
||||
<span id="cb12-9"><a href="#cb12-9" aria-hidden="true" tabindex="-1"></a>}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb13"><pre class="sourceCode bib code-with-copy"><code class="sourceCode bibtex"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="va">@misc</span>{<span class="ot">hartford2024spectrumtargetedtrainingsignal</span>,</span>
|
||||
<span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a> <span class="dt">title</span>={Spectrum: Targeted Training on Signal to Noise Ratio},</span>
|
||||
<span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">author</span>={Eric Hartford and Lucas Atkins and Fernando Fernandes Neto and David Golchinfar},</span>
|
||||
<span id="cb13-4"><a href="#cb13-4" aria-hidden="true" tabindex="-1"></a> <span class="dt">year</span>={2024},</span>
|
||||
<span id="cb13-5"><a href="#cb13-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">eprint</span>={2406.06623},</span>
|
||||
<span id="cb13-6"><a href="#cb13-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">archivePrefix</span>={arXiv},</span>
|
||||
<span id="cb13-7"><a href="#cb13-7" aria-hidden="true" tabindex="-1"></a> <span class="dt">primaryClass</span>={cs.LG},</span>
|
||||
<span id="cb13-8"><a href="#cb13-8" aria-hidden="true" tabindex="-1"></a> <span class="dt">url</span>={https://arxiv.org/abs/2406.06623},</span>
|
||||
<span id="cb13-9"><a href="#cb13-9" 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>Please see reference <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/spectrum">here</a></p>
|
||||
</section>
|
||||
</section>
|
||||
@@ -770,10 +775,10 @@ Warning
|
||||
</div>
|
||||
<div class="callout-body-container callout-body">
|
||||
<p>If you could not load your integration, please ensure you are pip installing in editable mode.</p>
|
||||
<div class="sourceCode" id="cb13"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="ex">pip</span> install <span class="at">-e</span> .</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb14"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a><span class="ex">pip</span> install <span class="at">-e</span> .</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>and correctly spelled the integration name in the config file.</p>
|
||||
<div class="sourceCode" id="cb14"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb14-2"><a href="#cb14-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.your_integration_name.YourIntegrationPlugin</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<div class="sourceCode" id="cb15"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb15-2"><a href="#cb15-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.your_integration_name.YourIntegrationPlugin</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="callout callout-style-default callout-note callout-titled">
|
||||
|
||||
@@ -475,6 +475,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<p align="center">
|
||||
<img src="https://img.shields.io/github/license/axolotl-ai-cloud/axolotl.svg?color=blue" alt="GitHub License">
|
||||
<img src="https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/tests.yml/badge.svg" alt="tests">
|
||||
<a href="https://codecov.io/gh/axolotl-ai-cloud/axolotl"><img src="https://codecov.io/gh/axolotl-ai-cloud/axolotl/branch/main/graph/badge.svg" alt="codecov"></a>
|
||||
<a href="https://github.com/axolotl-ai-cloud/axolotl/releases"><img src="https://img.shields.io/github/release/axolotl-ai-cloud/axolotl.svg" alt="Releases"></a>
|
||||
<br>
|
||||
<a href="https://github.com/axolotl-ai-cloud/axolotl/graphs/contributors"><img src="https://img.shields.io/github/contributors-anon/axolotl-ai-cloud/axolotl?color=yellow&style=flat-square" alt="contributors" style="height: 20px;"></a>
|
||||
|
||||
@@ -3033,7 +3033,7 @@
|
||||
"href": "docs/custom_integrations.html#cut-cross-entropy",
|
||||
"title": "Custom Integrations",
|
||||
"section": "Cut Cross Entropy",
|
||||
"text": "Cut Cross Entropy\nCut Cross Entropy (CCE) reduces VRAM usage through optimization on the cross-entropy operation during loss calculation.\nSee https://github.com/apple/ml-cross-entropy\n\nRequirements\n\nPyTorch 2.4.0 or higher\n\n\n\nInstallation\nRun the following command to install cut_cross_entropy[transformers] if you don’t have it already.\npython scripts/cutcrossentropy_install.py | sh\n\npip3 uninstall -y cut-cross-entropy && pip3 install \"cut-cross-entropy[transformers] @ git+https://github.com/apple/ml-cross-entropy.git@bad6f7b49c75fdec69471abb71b4cddd0f0c6438\"\n\n\nUsage\nplugins:\n - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin\n\ncut_cross_entropy: true\n\n\nSupported Models\n\nllama\nllama4_text\nllama4\nmllama\nphi3\ngemma\ngemma2\ngemma3\ngemma3_text\nmistral\nmistral3\nqwen2\ncohere\ncohere2\n\n\n\nCitation\n@article{wijmans2024cut,\n author = {Erik Wijmans and\n Brody Huval and\n Alexander Hertzberg and\n Vladlen Koltun and\n Philipp Kr\\\"ahenb\\\"uhl},\n title = {Cut Your Losses in Large-Vocabulary Language Models},\n journal = {arXiv},\n year = {2024},\n url = {https://arxiv.org/abs/2411.09009},\n}\nPlease see reference here",
|
||||
"text": "Cut Cross Entropy\nCut Cross Entropy (CCE) reduces VRAM usage through optimization on the cross-entropy operation during loss calculation.\nSee https://github.com/apple/ml-cross-entropy\n\nRequirements\n\nPyTorch 2.4.0 or higher\n\n\n\nInstallation\nRun the following command to install cut_cross_entropy[transformers] if you don’t have it already.\n\nIf you are in dev environment\n\npython scripts/cutcrossentropy_install.py | sh\n\nIf you are installing from pip\n\npip3 uninstall -y cut-cross-entropy && pip3 install \"cut-cross-entropy[transformers] @ git+https://github.com/apple/ml-cross-entropy.git@bad6f7b49c75fdec69471abb71b4cddd0f0c6438\"\n\n\nUsage\nplugins:\n - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin\n\ncut_cross_entropy: true\n\n\nSupported Models\n\nllama\nllama4_text\nllama4\nmllama\nphi3\ngemma\ngemma2\ngemma3\ngemma3_text\nmistral\nmistral3\nqwen2\ncohere\ncohere2\n\n\n\nCitation\n@article{wijmans2024cut,\n author = {Erik Wijmans and\n Brody Huval and\n Alexander Hertzberg and\n Vladlen Koltun and\n Philipp Kr\\\"ahenb\\\"uhl},\n title = {Cut Your Losses in Large-Vocabulary Language Models},\n journal = {arXiv},\n year = {2024},\n url = {https://arxiv.org/abs/2411.09009},\n}\nPlease see reference here",
|
||||
"crumbs": [
|
||||
"Advanced Features",
|
||||
"Custom Integrations"
|
||||
|
||||
340
sitemap.xml
340
sitemap.xml
@@ -2,682 +2,682 @@
|
||||
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.899Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.860Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/template_free.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/tokenized.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/nccl.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/amd_hpc.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/config.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multi-gpu.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/installation.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.858Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/torchao.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/reward_modelling.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/input_output.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.858Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multimodal.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.177Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.307Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.732Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.889Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.753Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.906Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.399Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.588Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.672Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.834Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.451Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.634Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.liger.args.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.089Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.221Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.training.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.942Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.081Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/datasets.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.848Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.076Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.geglu.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.605Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.773Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.654Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.818Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.sweeps.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.214Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.419Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.freeze.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.832Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.980Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.673Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.835Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.main.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.101Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.312Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.trl.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.299Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.497Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.453Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.636Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.052Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.267Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.068Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.281Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.472Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.653Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.mamba.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.148Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.278Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.base.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.073Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.206Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.bench.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.824Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.972Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.swiglu.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.616Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.783Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.shared.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.054Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.268Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.077Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.209Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.datasets.chat.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.059Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.273Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.174Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.303Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.078Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.210Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.343Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.537Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.345Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.539Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.471Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.652Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.992Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.129Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.trl.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.973Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.111Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_tokenizers.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.908Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.132Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.data.sft.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.916Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.057Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schedulers.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.878Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.022Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.chat_templates.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.805Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.954Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.models.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.786Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.937Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.448Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.631Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.distributed.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.900Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.043Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.utils.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.719Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.877Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.utils.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.006Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.142Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.683Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.844Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/common.datasets.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.116Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.247Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/logging_config.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.914Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.137Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.quantize.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.624Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.790Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.722Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.880Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.model.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.936Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.075Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.728Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.886Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.754Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.907Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.tokenization.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.794Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.944Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.086Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.218Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.961Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.099Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.core.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.119Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.250Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.721Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.879Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.912Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.054Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.394Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.583Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/index.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.760Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:31.998Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.265Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.466Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.437Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.621Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.train.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.110Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.321Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainer_builder.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.930Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.153Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.168Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.298Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/getting-started.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.856Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset_loading.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.856Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/batch_vs_grad.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/faq.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.856Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/debugging.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.856Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/lr_groups.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/TODO.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.893Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.854Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.916Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.875Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/index.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.912Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.871Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.916Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.875Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/FAQS.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.892Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.854Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multi-node.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/sequence_parallelism.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multipack.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/inference.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.858Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/lora_optims.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.lora_embeddings.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.814Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.963Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.utils.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.626Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.792Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.328Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.523Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/convert.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.862Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.090Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/common.const.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.099Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.230Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.cloud.base.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.258Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.459Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.relora.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.681Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.842Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.lora.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.810Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.960Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.merge_lora.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.187Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.393Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.499Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.678Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.199Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.405Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.096Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.227Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.117Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.248Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/common.architectures.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.097Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.229Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.trainer.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.850Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.997Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.181Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.311Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.vllm_serve.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.254Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.456Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.979Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.117Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.gradient_checkpointing.unsloth.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.919Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.060Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.base.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.280Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.480Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.741Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.898Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.162Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.292Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.172Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.302Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.093Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.224Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.data.pretraining.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.914Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.055Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/evaluate.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.839Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.069Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.dict.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.904Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.046Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.utils.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.249Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.451Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.419Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.605Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.training_args.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.025Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.241Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.inference.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.178Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.384Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.lora.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.593Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.762Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.evaluate.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.119Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.329Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.batching.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.144Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.274Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.388Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.577Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.449Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.633Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.407Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.594Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.495Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.674Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.358Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.550Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.820Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.969Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.config.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.163Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.370Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.enums.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.999Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.136Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.preprocess.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.208Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.413Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.messages.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.049Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.264Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.426Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.611Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.peft.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.970Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.107Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/train.html</loc>
|
||||
<lastmod>2025-04-16T21:49:35.828Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.059Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.424Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.609Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.412Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.598Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html</loc>
|
||||
<lastmod>2025-04-16T21:49:37.153Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.283Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.462Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.644Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.attention.mllama.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.751Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.904Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.checks.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.144Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.352Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.739Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.896Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.656Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.819Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.306Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.504Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.367Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.558Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.args.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.137Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.346Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.381Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.571Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.config.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.928Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:33.068Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.310Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.507Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.050Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.265Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.711Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.869Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.base.html</loc>
|
||||
<lastmod>2025-04-16T21:49:36.312Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:32.509Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/rlhf.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/cli.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/unsloth.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.899Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/fsdp_qlora.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.856Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset_preprocessing.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.856Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/custom_integrations.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/mac.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/docker.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.895Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.856Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/ray-integration.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.898Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/index.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/conversation.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/pretraining.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html</loc>
|
||||
<lastmod>2025-04-16T21:48:50.894Z</lastmod>
|
||||
<lastmod>2025-04-16T22:03:03.855Z</lastmod>
|
||||
</url>
|
||||
</urlset>
|
||||
|
||||
Reference in New Issue
Block a user