Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -619,7 +619,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<ul>
|
||||
<li>If you are installing from pip</li>
|
||||
</ul>
|
||||
<div class="code-copy-outer-scaffold"><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/axolotl-ai-cloud/ml-cross-entropy.git@242b245"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
<div class="code-copy-outer-scaffold"><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/axolotl-ai-cloud/ml-cross-entropy.git@318b7e2"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="usage" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="usage">Usage</h3>
|
||||
@@ -652,6 +652,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<li>granitemoehybrid</li>
|
||||
<li>hunyuan_v1_dense</li>
|
||||
<li>hunyuan_v1_moe</li>
|
||||
<li>internvl</li>
|
||||
<li>kimi_linear</li>
|
||||
<li>lfm2</li>
|
||||
<li>lfm2_moe</li>
|
||||
|
||||
@@ -528,6 +528,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<li><a href="#sec-qwen3-vl" id="toc-sec-qwen3-vl" class="nav-link" data-scroll-target="#sec-qwen3-vl">Qwen3-VL</a></li>
|
||||
<li><a href="#sec-smolvlm2" id="toc-sec-smolvlm2" class="nav-link" data-scroll-target="#sec-smolvlm2">SmolVLM2</a></li>
|
||||
<li><a href="#sec-lfm2-vl" id="toc-sec-lfm2-vl" class="nav-link" data-scroll-target="#sec-lfm2-vl">LFM2-VL</a></li>
|
||||
<li><a href="#sec-intern-vl" id="toc-sec-intern-vl" class="nav-link" data-scroll-target="#sec-intern-vl">Intern-VL</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#dataset-format" id="toc-dataset-format" class="nav-link" data-scroll-target="#dataset-format">Dataset Format</a>
|
||||
<ul class="collapse">
|
||||
@@ -578,6 +579,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<li><a href="#sec-qwen25-vl">Qwen2.5-VL</a></li>
|
||||
<li><a href="#sec-smolvlm2">SmolVLM2</a></li>
|
||||
<li><a href="#sec-lfm2-vl">LFM2-VL</a></li>
|
||||
<li><a href="#sec-intern-vl">Intern-VL</a></li>
|
||||
</ul>
|
||||
</section>
|
||||
<section id="usage" class="level2">
|
||||
@@ -815,6 +817,23 @@ Warning
|
||||
</div>
|
||||
<div class="code-copy-outer-scaffold"><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">base_model</span><span class="kw">:</span><span class="at"> LiquidAI/LFM2-VL-450M</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-intern-vl" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-intern-vl">Intern-VL</h3>
|
||||
<div class="callout callout-style-default callout-tip callout-titled">
|
||||
<div class="callout-header d-flex align-content-center">
|
||||
<div class="callout-icon-container">
|
||||
<i class="callout-icon"></i>
|
||||
</div>
|
||||
<div class="callout-title-container flex-fill">
|
||||
Tip
|
||||
</div>
|
||||
</div>
|
||||
<div class="callout-body-container callout-body">
|
||||
<p>Please make sure to install <code>timm</code> via <code>pip3 install timm==1.0.19</code></p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb16"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> OpenGVLab/InternVL3_5-8B</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="dataset-format" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="dataset-format">Dataset Format</h2>
|
||||
@@ -898,31 +917,31 @@ Warning
|
||||
<section id="example" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="example">Example</h3>
|
||||
<p>Here is an example of a multi-modal dataset:</p>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb16"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a><span class="ot">[</span></span>
|
||||
<span id="cb16-2"><a href="#cb16-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb16-3"><a href="#cb16-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"messages"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb16-4"><a href="#cb16-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb16-5"><a href="#cb16-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"system"</span><span class="fu">,</span></span>
|
||||
<span id="cb16-6"><a href="#cb16-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb16-7"><a href="#cb16-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"You are a helpful assistant."</span><span class="fu">}</span></span>
|
||||
<span id="cb16-8"><a href="#cb16-8" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb16-9"><a href="#cb16-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb16-10"><a href="#cb16-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb16-11"><a href="#cb16-11" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span></span>
|
||||
<span id="cb16-12"><a href="#cb16-12" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb16-13"><a href="#cb16-13" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"image"</span><span class="fu">,</span> <span class="dt">"url"</span><span class="fu">:</span> <span class="st">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"</span><span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb16-14"><a href="#cb16-14" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"Describe this image in detail."</span><span class="fu">}</span></span>
|
||||
<span id="cb16-15"><a href="#cb16-15" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb16-16"><a href="#cb16-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb16-17"><a href="#cb16-17" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb16-18"><a href="#cb16-18" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span></span>
|
||||
<span id="cb16-19"><a href="#cb16-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb16-20"><a href="#cb16-20" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"The image is a bee."</span><span class="fu">}</span></span>
|
||||
<span id="cb16-21"><a href="#cb16-21" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb16-22"><a href="#cb16-22" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb16-23"><a href="#cb16-23" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb16-24"><a href="#cb16-24" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb16-25"><a href="#cb16-25" aria-hidden="true" tabindex="-1"></a><span class="ot">]</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb17"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb17-1"><a href="#cb17-1" aria-hidden="true" tabindex="-1"></a><span class="ot">[</span></span>
|
||||
<span id="cb17-2"><a href="#cb17-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb17-3"><a href="#cb17-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"messages"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb17-4"><a href="#cb17-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb17-5"><a href="#cb17-5" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"system"</span><span class="fu">,</span></span>
|
||||
<span id="cb17-6"><a href="#cb17-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb17-7"><a href="#cb17-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"You are a helpful assistant."</span><span class="fu">}</span></span>
|
||||
<span id="cb17-8"><a href="#cb17-8" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb17-9"><a href="#cb17-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb17-10"><a href="#cb17-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb17-11"><a href="#cb17-11" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"user"</span><span class="fu">,</span></span>
|
||||
<span id="cb17-12"><a href="#cb17-12" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb17-13"><a href="#cb17-13" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"image"</span><span class="fu">,</span> <span class="dt">"url"</span><span class="fu">:</span> <span class="st">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"</span><span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb17-14"><a href="#cb17-14" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"Describe this image in detail."</span><span class="fu">}</span></span>
|
||||
<span id="cb17-15"><a href="#cb17-15" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb17-16"><a href="#cb17-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb17-17"><a href="#cb17-17" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb17-18"><a href="#cb17-18" aria-hidden="true" tabindex="-1"></a> <span class="dt">"role"</span><span class="fu">:</span> <span class="st">"assistant"</span><span class="fu">,</span></span>
|
||||
<span id="cb17-19"><a href="#cb17-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb17-20"><a href="#cb17-20" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span><span class="dt">"type"</span><span class="fu">:</span> <span class="st">"text"</span><span class="fu">,</span> <span class="dt">"text"</span><span class="fu">:</span> <span class="st">"The image is a bee."</span><span class="fu">}</span></span>
|
||||
<span id="cb17-21"><a href="#cb17-21" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb17-22"><a href="#cb17-22" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb17-23"><a href="#cb17-23" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb17-24"><a href="#cb17-24" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb17-25"><a href="#cb17-25" aria-hidden="true" tabindex="-1"></a><span class="ot">]</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="faq" class="level2">
|
||||
|
||||
@@ -567,7 +567,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="op">%%</span>capture</span>
|
||||
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="co"># This step can take ~5-10 minutes to install dependencies</span></span>
|
||||
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install <span class="op">--</span>no<span class="op">-</span>build<span class="op">-</span>isolation axolotl[flash<span class="op">-</span>attn]<span class="op">>=</span><span class="fl">0.9.1</span></span>
|
||||
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install <span class="st">"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@242b245"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install <span class="st">"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@318b7e2"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</div>
|
||||
<section id="demo-talk-like-a-pirate" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="demo-talk-like-a-pirate">Demo: Talk Like a Pirate</h2>
|
||||
|
||||
@@ -564,7 +564,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<section id="latest-updates" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="latest-updates">🎉 Latest Updates</h2>
|
||||
<ul>
|
||||
<li>2025/12: Axolotl now includes support for <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/kimi-linear">Kimi-Linear</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/examples/olmo3">Olmo3</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/trinity">Trinity</a>, and <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/examples/ministral3">Ministral3</a>.</li>
|
||||
<li>2025/12: Axolotl now includes support for <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/kimi-linear">Kimi-Linear</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/plano">Plano-Orchestrator</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/mimo">MiMo</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/internvl3_5">InternVL 3.5</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/examples/olmo3">Olmo3</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/trinity">Trinity</a>, and <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/examples/ministral3">Ministral3</a>.</li>
|
||||
<li>2025/10: New model support has been added in Axolotl for: <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/examples/qwen3-next">Qwen3 Next</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/qwen2_5-vl">Qwen2.5-vl, Qwen3-vl</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/qwen3">Qwen3, Qwen3MoE</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/granite4">Granite 4</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/hunyuan">HunYuan</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/magistral#vision">Magistral 2509</a>, <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/apertus">Apertus</a>, and <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/seed-oss">Seed-OSS</a>.</li>
|
||||
<li>2025/09: Axolotl now has text diffusion training. Read more <a href="https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/diffusion">here</a>.</li>
|
||||
<li>2025/08: QAT has been updated to include NVFP4 support. See <a href="https://github.com/axolotl-ai-cloud/axolotl/pull/3107">PR</a>.</li>
|
||||
|
||||
10
search.json
10
search.json
@@ -1910,7 +1910,7 @@
|
||||
"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.\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/axolotl-ai-cloud/ml-cross-entropy.git@242b245\"\n\n\nUsage\nplugins:\n - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin\n\n\nSupported Models\n\napertus\narcee\ncohere\ncohere2\ndeepseek_v3\ngemma\ngemma2\ngemma3\ngemma3_text\ngemma3n\ngemma3n_text\nglm\nglm4\nglm4_moe\nglm4v\nglm4v_moe\ngpt_oss\ngranite\ngranitemoe\ngranitemoeshared\ngranitemoehybrid\nhunyuan_v1_dense\nhunyuan_v1_moe\nkimi_linear\nlfm2\nlfm2_moe\nlfm2_vl\nllama\nllama4\nllama4_text\nllava\nministral\nministral3\nmistral\nmistral3\nmixtral\nmllama\nolmo\nolmo2\nolmo3\nphi\nphi3\nphi4_multimodal\nqwen2\nqwen2_vl\nqwen2_moe\nqwen2_5_vl\nqwen3\nqwen3_moe\nqwen3_vl\nqwen3_vl_moe\nqwen3_next\nsmollm3\nseed_oss\nvoxtral\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/axolotl-ai-cloud/ml-cross-entropy.git@318b7e2\"\n\n\nUsage\nplugins:\n - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin\n\n\nSupported Models\n\napertus\narcee\ncohere\ncohere2\ndeepseek_v3\ngemma\ngemma2\ngemma3\ngemma3_text\ngemma3n\ngemma3n_text\nglm\nglm4\nglm4_moe\nglm4v\nglm4v_moe\ngpt_oss\ngranite\ngranitemoe\ngranitemoeshared\ngranitemoehybrid\nhunyuan_v1_dense\nhunyuan_v1_moe\ninternvl\nkimi_linear\nlfm2\nlfm2_moe\nlfm2_vl\nllama\nllama4\nllama4_text\nllava\nministral\nministral3\nmistral\nmistral3\nmixtral\nmllama\nolmo\nolmo2\nolmo3\nphi\nphi3\nphi4_multimodal\nqwen2\nqwen2_vl\nqwen2_moe\nqwen2_5_vl\nqwen3\nqwen3_moe\nqwen3_vl\nqwen3_vl_moe\nqwen3_next\nsmollm3\nseed_oss\nvoxtral\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"
|
||||
@@ -2030,7 +2030,7 @@
|
||||
"href": "index.html#latest-updates",
|
||||
"title": "Axolotl",
|
||||
"section": "🎉 Latest Updates",
|
||||
"text": "🎉 Latest Updates\n\n2025/12: Axolotl now includes support for Kimi-Linear, Olmo3, Trinity, and Ministral3.\n2025/10: New model support has been added in Axolotl for: Qwen3 Next, Qwen2.5-vl, Qwen3-vl, Qwen3, Qwen3MoE, Granite 4, HunYuan, Magistral 2509, Apertus, and Seed-OSS.\n2025/09: Axolotl now has text diffusion training. Read more here.\n2025/08: QAT has been updated to include NVFP4 support. See PR.\n2025/07:\n\nND Parallelism support has been added into Axolotl. Compose Context Parallelism (CP), Tensor Parallelism (TP), and Fully Sharded Data Parallelism (FSDP) within a single node and across multiple nodes. Check out the blog post for more info.\nAxolotl adds more models: GPT-OSS, Gemma 3n, Liquid Foundation Model 2 (LFM2), and Arcee Foundation Models (AFM).\nFP8 finetuning with fp8 gather op is now possible in Axolotl via torchao. Get started here!\nVoxtral, Magistral 1.1, and Devstral with mistral-common tokenizer support has been integrated in Axolotl!\nTiledMLP support for single-GPU to multi-GPU training with DDP, DeepSpeed and FSDP support has been added to support Arctic Long Sequence Training. (ALST). See examples for using ALST with Axolotl!\n\n2025/05: Quantization Aware Training (QAT) support has been added to Axolotl. Explore the docs to learn more!\n\n\n\nExpand older updates\n\n\n2025/03: Axolotl has implemented Sequence Parallelism (SP) support. Read the blog and docs to learn how to scale your context length when fine-tuning.\n2025/06: Magistral with mistral-common tokenizer support has been added to Axolotl. See examples to start training your own Magistral models with Axolotl!\n2025/04: Llama 4 support has been added in Axolotl. See examples to start training your own Llama 4 models with Axolotl’s linearized version!\n2025/03: (Beta) Fine-tuning Multimodal models is now supported in Axolotl. Check out the docs to fine-tune your own!\n2025/02: Axolotl has added LoRA optimizations to reduce memory usage and improve training speed for LoRA and QLoRA in single GPU and multi-GPU training (DDP and DeepSpeed). Jump into the docs to give it a try.\n2025/02: Axolotl has added GRPO support. Dive into our blog and GRPO example and have some fun!\n2025/01: Axolotl has added Reward Modelling / Process Reward Modelling fine-tuning support. See docs.",
|
||||
"text": "🎉 Latest Updates\n\n2025/12: Axolotl now includes support for Kimi-Linear, Plano-Orchestrator, MiMo, InternVL 3.5, Olmo3, Trinity, and Ministral3.\n2025/10: New model support has been added in Axolotl for: Qwen3 Next, Qwen2.5-vl, Qwen3-vl, Qwen3, Qwen3MoE, Granite 4, HunYuan, Magistral 2509, Apertus, and Seed-OSS.\n2025/09: Axolotl now has text diffusion training. Read more here.\n2025/08: QAT has been updated to include NVFP4 support. See PR.\n2025/07:\n\nND Parallelism support has been added into Axolotl. Compose Context Parallelism (CP), Tensor Parallelism (TP), and Fully Sharded Data Parallelism (FSDP) within a single node and across multiple nodes. Check out the blog post for more info.\nAxolotl adds more models: GPT-OSS, Gemma 3n, Liquid Foundation Model 2 (LFM2), and Arcee Foundation Models (AFM).\nFP8 finetuning with fp8 gather op is now possible in Axolotl via torchao. Get started here!\nVoxtral, Magistral 1.1, and Devstral with mistral-common tokenizer support has been integrated in Axolotl!\nTiledMLP support for single-GPU to multi-GPU training with DDP, DeepSpeed and FSDP support has been added to support Arctic Long Sequence Training. (ALST). See examples for using ALST with Axolotl!\n\n2025/05: Quantization Aware Training (QAT) support has been added to Axolotl. Explore the docs to learn more!\n\n\n\nExpand older updates\n\n\n2025/03: Axolotl has implemented Sequence Parallelism (SP) support. Read the blog and docs to learn how to scale your context length when fine-tuning.\n2025/06: Magistral with mistral-common tokenizer support has been added to Axolotl. See examples to start training your own Magistral models with Axolotl!\n2025/04: Llama 4 support has been added in Axolotl. See examples to start training your own Llama 4 models with Axolotl’s linearized version!\n2025/03: (Beta) Fine-tuning Multimodal models is now supported in Axolotl. Check out the docs to fine-tune your own!\n2025/02: Axolotl has added LoRA optimizations to reduce memory usage and improve training speed for LoRA and QLoRA in single GPU and multi-GPU training (DDP and DeepSpeed). Jump into the docs to give it a try.\n2025/02: Axolotl has added GRPO support. Dive into our blog and GRPO example and have some fun!\n2025/01: Axolotl has added Reward Modelling / Process Reward Modelling fine-tuning support. See docs.",
|
||||
"crumbs": [
|
||||
"Home"
|
||||
]
|
||||
@@ -3455,7 +3455,7 @@
|
||||
"href": "docs/multimodal.html",
|
||||
"title": "MultiModal / Vision Language Models (BETA)",
|
||||
"section": "",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL\nIntern-VL",
|
||||
"crumbs": [
|
||||
"How To Guides",
|
||||
"MultiModal / Vision Language Models (BETA)"
|
||||
@@ -3466,7 +3466,7 @@
|
||||
"href": "docs/multimodal.html#supported-models",
|
||||
"title": "MultiModal / Vision Language Models (BETA)",
|
||||
"section": "",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nSmolVLM2\nLFM2-VL\nIntern-VL",
|
||||
"crumbs": [
|
||||
"How To Guides",
|
||||
"MultiModal / Vision Language Models (BETA)"
|
||||
@@ -3477,7 +3477,7 @@
|
||||
"href": "docs/multimodal.html#usage",
|
||||
"title": "MultiModal / Vision Language Models (BETA)",
|
||||
"section": "Usage",
|
||||
"text": "Usage\nMultimodal support is limited and doesn’t have full feature parity.\nHere are the hyperparams you’ll need to use to finetune a multimodal model.\nprocessor_type: AutoProcessor\n\nskip_prepare_dataset: true\nremove_unused_columns: false # leave columns in place as they are needed to handle image embeddings during training\nsample_packing: false # not yet supported with multimodal\n\nchat_template: # see in next section if specified\n\n# example dataset\ndatasets:\n - path: HuggingFaceH4/llava-instruct-mix-vsft\n type: chat_template\n split: train[:1%]\n\n# (optional) if doing lora, only finetune the Language model,\n# leave the vision model and vision tower frozen\n# load_in_8bit: true\nadapter: lora\nlora_target_modules: 'model.language_model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'\n\n# (optional) if you want to resize images to a set size\nimage_size: 512\nimage_resize_algorithm: bilinear\nPlease see examples folder for full configs.\n\n\n\n\n\n\nTip\n\n\n\nSome of our chat_templates have been extended to support broader dataset types. This should not break any existing configs.\n\n\n\n\n\n\n\n\nNote\n\n\n\nAs of now, we do not truncate nor drop samples based on sequence_len as each arch has different ways to process non-text tokens. We are looking for help on this.\n\n\n\nMllama\nbase_model: meta-llama/Llama-3.2-11B-Vision-Instruct\n\nchat_template: llama3_2_vision\n\n\nLlama4\nbase_model: meta-llama/Llama-4-Scout-17B-16E-Instruct\n\nchat_template: llama4\n\n\nPixtral\nbase_model: mistralai/Pixtral-12B-2409\n\nchat_template: pixtral\n\n\nLlava-1.5\nbase_model: llava-hf/llava-1.5-7b-hf\n\nchat_template: llava\n\n\nMistral-Small-3.1\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'\n\n\nbase_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503\n\n\nMagistral-Small-2509\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'\n\n\nbase_model: mistralai/Magistral-Small-2509\n\n\nVoxtral\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install audio lib via pip3 install librosa==0.11.0 'mistral_common[audio]==1.8.3'\n\n\nbase_model: mistralai/Voxtral-Mini-3B-2507\n\nprocessor_type: VoxtralProcessor\n\n\nGemma-3\n\n\n\n\n\n\nTip\n\n\n\nThe Gemma3-1B model is a text-only model, so please train as regular text model.\n\n\nFor multi-modal 4B/12B/27B models, use the following config:\nbase_model: google/gemma-3-4b-it\n\nchat_template: gemma3\n\n\nGemma-3n\n\n\n\n\n\n\nWarning\n\n\n\nThe model’s initial loss and grad norm will be very high. We suspect this to be due to the Conv in the vision layers.\n\n\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install timm via pip3 install timm==1.0.17\n\n\nbase_model: google/gemma-3n-E2B-it\n\nchat_template: gemma3n\n\n\nQwen2-VL\nbase_model: Qwen/Qwen2-VL-7B-Instruct\n\nchat_template: qwen2_vl\n\n\nQwen2.5-VL\nbase_model: Qwen/Qwen2.5-VL-7B-Instruct\n\nchat_template: qwen2_vl # same as qwen2-vl\n\n\nQwen3-VL\nbase_model: Qwen/Qwen3-VL-4B-Instruct\n\nchat_template: qwen2_vl # same as qwen2-vl\n\n\nSmolVLM2\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install num2words via pip3 install num2words==0.5.14\n\n\nbase_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct\n\n\nLFM2-VL\n\n\n\n\n\n\nWarning\n\n\n\nPlease uninstall causal-conv1d via pip3 uninstall -y causal-conv1d\n\n\nbase_model: LiquidAI/LFM2-VL-450M",
|
||||
"text": "Usage\nMultimodal support is limited and doesn’t have full feature parity.\nHere are the hyperparams you’ll need to use to finetune a multimodal model.\nprocessor_type: AutoProcessor\n\nskip_prepare_dataset: true\nremove_unused_columns: false # leave columns in place as they are needed to handle image embeddings during training\nsample_packing: false # not yet supported with multimodal\n\nchat_template: # see in next section if specified\n\n# example dataset\ndatasets:\n - path: HuggingFaceH4/llava-instruct-mix-vsft\n type: chat_template\n split: train[:1%]\n\n# (optional) if doing lora, only finetune the Language model,\n# leave the vision model and vision tower frozen\n# load_in_8bit: true\nadapter: lora\nlora_target_modules: 'model.language_model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'\n\n# (optional) if you want to resize images to a set size\nimage_size: 512\nimage_resize_algorithm: bilinear\nPlease see examples folder for full configs.\n\n\n\n\n\n\nTip\n\n\n\nSome of our chat_templates have been extended to support broader dataset types. This should not break any existing configs.\n\n\n\n\n\n\n\n\nNote\n\n\n\nAs of now, we do not truncate nor drop samples based on sequence_len as each arch has different ways to process non-text tokens. We are looking for help on this.\n\n\n\nMllama\nbase_model: meta-llama/Llama-3.2-11B-Vision-Instruct\n\nchat_template: llama3_2_vision\n\n\nLlama4\nbase_model: meta-llama/Llama-4-Scout-17B-16E-Instruct\n\nchat_template: llama4\n\n\nPixtral\nbase_model: mistralai/Pixtral-12B-2409\n\nchat_template: pixtral\n\n\nLlava-1.5\nbase_model: llava-hf/llava-1.5-7b-hf\n\nchat_template: llava\n\n\nMistral-Small-3.1\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'\n\n\nbase_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503\n\n\nMagistral-Small-2509\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install vision lib via pip install 'mistral-common[opencv]==1.8.5'\n\n\nbase_model: mistralai/Magistral-Small-2509\n\n\nVoxtral\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install audio lib via pip3 install librosa==0.11.0 'mistral_common[audio]==1.8.3'\n\n\nbase_model: mistralai/Voxtral-Mini-3B-2507\n\nprocessor_type: VoxtralProcessor\n\n\nGemma-3\n\n\n\n\n\n\nTip\n\n\n\nThe Gemma3-1B model is a text-only model, so please train as regular text model.\n\n\nFor multi-modal 4B/12B/27B models, use the following config:\nbase_model: google/gemma-3-4b-it\n\nchat_template: gemma3\n\n\nGemma-3n\n\n\n\n\n\n\nWarning\n\n\n\nThe model’s initial loss and grad norm will be very high. We suspect this to be due to the Conv in the vision layers.\n\n\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install timm via pip3 install timm==1.0.17\n\n\nbase_model: google/gemma-3n-E2B-it\n\nchat_template: gemma3n\n\n\nQwen2-VL\nbase_model: Qwen/Qwen2-VL-7B-Instruct\n\nchat_template: qwen2_vl\n\n\nQwen2.5-VL\nbase_model: Qwen/Qwen2.5-VL-7B-Instruct\n\nchat_template: qwen2_vl # same as qwen2-vl\n\n\nQwen3-VL\nbase_model: Qwen/Qwen3-VL-4B-Instruct\n\nchat_template: qwen2_vl # same as qwen2-vl\n\n\nSmolVLM2\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install num2words via pip3 install num2words==0.5.14\n\n\nbase_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct\n\n\nLFM2-VL\n\n\n\n\n\n\nWarning\n\n\n\nPlease uninstall causal-conv1d via pip3 uninstall -y causal-conv1d\n\n\nbase_model: LiquidAI/LFM2-VL-450M\n\n\nIntern-VL\n\n\n\n\n\n\nTip\n\n\n\nPlease make sure to install timm via pip3 install timm==1.0.19\n\n\nbase_model: OpenGVLab/InternVL3_5-8B",
|
||||
"crumbs": [
|
||||
"How To Guides",
|
||||
"MultiModal / Vision Language Models (BETA)"
|
||||
|
||||
400
sitemap.xml
400
sitemap.xml
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user