Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -770,6 +770,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<li><a href="#sec-qwen2-vl" id="toc-sec-qwen2-vl" class="nav-link" data-scroll-target="#sec-qwen2-vl">Qwen2-VL</a></li>
|
||||
<li><a href="#sec-qwen25-vl" id="toc-sec-qwen25-vl" class="nav-link" data-scroll-target="#sec-qwen25-vl">Qwen2.5-VL</a></li>
|
||||
<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-qwen3-5" id="toc-sec-qwen3-5" class="nav-link" data-scroll-target="#sec-qwen3-5">Qwen3.5</a></li>
|
||||
<li><a href="#sec-glm-4-6v" id="toc-sec-glm-4-6v" class="nav-link" data-scroll-target="#sec-glm-4-6v">GLM-4.6V</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>
|
||||
@@ -823,6 +824,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<li><a href="#sec-gemma-3n">Gemma-3n</a></li>
|
||||
<li><a href="#sec-qwen2-vl">Qwen2-VL</a></li>
|
||||
<li><a href="#sec-qwen25-vl">Qwen2.5-VL</a></li>
|
||||
<li><a href="#sec-qwen3-5">Qwen3.5</a></li>
|
||||
<li><a href="#sec-glm-4-6v">GLM-4.6V</a></li>
|
||||
<li><a href="#sec-smolvlm2">SmolVLM2</a></li>
|
||||
<li><a href="#sec-lfm2-vl">LFM2-VL</a></li>
|
||||
@@ -1034,14 +1036,20 @@ Tip
|
||||
<span id="cb14-2"><a href="#cb14-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb14-3"><a href="#cb14-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> qwen2_vl</span><span class="co"> # same as qwen2-vl</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-qwen3-5" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-qwen3-5">Qwen3.5</h3>
|
||||
<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"> Qwen/Qwen3.5-9B</span></span>
|
||||
<span id="cb15-2"><a href="#cb15-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb15-3"><a href="#cb15-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> qwen3_5</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-glm-4-6v" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-glm-4-6v">GLM-4.6V</h3>
|
||||
<p>Both GLM-4.6V (106B MoE) and GLM-4.6V-Flash (9B) are supported.</p>
|
||||
<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="co"># GLM-4.6V (106B MoE version)</span></span>
|
||||
<span id="cb15-2"><a href="#cb15-2" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> zai-org/GLM-4.6V</span></span>
|
||||
<span id="cb15-3"><a href="#cb15-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb15-4"><a href="#cb15-4" aria-hidden="true" tabindex="-1"></a><span class="co"># OR GLM-4.6V-Flash (9B version)</span></span>
|
||||
<span id="cb15-5"><a href="#cb15-5" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> zai-org/GLM-4.6V-Flash</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="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="co"># GLM-4.6V (106B MoE version)</span></span>
|
||||
<span id="cb16-2"><a href="#cb16-2" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> zai-org/GLM-4.6V</span></span>
|
||||
<span id="cb16-3"><a href="#cb16-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb16-4"><a href="#cb16-4" aria-hidden="true" tabindex="-1"></a><span class="co"># OR GLM-4.6V-Flash (9B version)</span></span>
|
||||
<span id="cb16-5"><a href="#cb16-5" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> zai-org/GLM-4.6V-Flash</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-smolvlm2" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-smolvlm2">SmolVLM2</h3>
|
||||
@@ -1058,7 +1066,7 @@ Tip
|
||||
<p>Please make sure to install <code>num2words</code> via <code>pip3 install num2words==0.5.14</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"> HuggingFaceTB/SmolVLM2-500M-Video-Instruct</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 yaml code-with-copy"><code class="sourceCode yaml"><span id="cb17-1"><a href="#cb17-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> HuggingFaceTB/SmolVLM2-500M-Video-Instruct</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-lfm2-vl" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-lfm2-vl">LFM2-VL</h3>
|
||||
@@ -1075,7 +1083,7 @@ Warning
|
||||
<p>Please uninstall <code>causal-conv1d</code> via <code>pip3 uninstall -y causal-conv1d</code></p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb17"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb17-1"><a href="#cb17-1" 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>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb18"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb18-1"><a href="#cb18-1" 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>
|
||||
@@ -1092,7 +1100,7 @@ Tip
|
||||
<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="cb18"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb18-1"><a href="#cb18-1" 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>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb19"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb19-1"><a href="#cb19-1" 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">
|
||||
@@ -1177,31 +1185,31 @@ 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="cb19"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb19-1"><a href="#cb19-1" aria-hidden="true" tabindex="-1"></a><span class="ot">[</span></span>
|
||||
<span id="cb19-2"><a href="#cb19-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb19-3"><a href="#cb19-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"messages"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb19-4"><a href="#cb19-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb19-5"><a href="#cb19-5" 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="cb19-6"><a href="#cb19-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb19-7"><a href="#cb19-7" 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="cb19-8"><a href="#cb19-8" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb19-9"><a href="#cb19-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb19-10"><a href="#cb19-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb19-11"><a href="#cb19-11" 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="cb19-12"><a href="#cb19-12" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb19-13"><a href="#cb19-13" 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="cb19-14"><a href="#cb19-14" 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="cb19-15"><a href="#cb19-15" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb19-16"><a href="#cb19-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb19-17"><a href="#cb19-17" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb19-18"><a href="#cb19-18" 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="cb19-19"><a href="#cb19-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb19-20"><a href="#cb19-20" 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="cb19-21"><a href="#cb19-21" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb19-22"><a href="#cb19-22" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb19-23"><a href="#cb19-23" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb19-24"><a href="#cb19-24" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb19-25"><a href="#cb19-25" 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="cb20"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb20-1"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a><span class="ot">[</span></span>
|
||||
<span id="cb20-2"><a href="#cb20-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb20-3"><a href="#cb20-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"messages"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb20-4"><a href="#cb20-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb20-5"><a href="#cb20-5" 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="cb20-6"><a href="#cb20-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb20-7"><a href="#cb20-7" 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="cb20-8"><a href="#cb20-8" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb20-9"><a href="#cb20-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb20-10"><a href="#cb20-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb20-11"><a href="#cb20-11" 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="cb20-12"><a href="#cb20-12" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb20-13"><a href="#cb20-13" 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="cb20-14"><a href="#cb20-14" 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="cb20-15"><a href="#cb20-15" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb20-16"><a href="#cb20-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb20-17"><a href="#cb20-17" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb20-18"><a href="#cb20-18" 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="cb20-19"><a href="#cb20-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb20-20"><a href="#cb20-20" 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="cb20-21"><a href="#cb20-21" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb20-22"><a href="#cb20-22" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb20-23"><a href="#cb20-23" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb20-24"><a href="#cb20-24" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb20-25"><a href="#cb20-25" 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">
|
||||
|
||||
@@ -975,7 +975,7 @@
|
||||
"href": "docs/multimodal.html",
|
||||
"title": "MultiModal / Vision Language Models (BETA)",
|
||||
"section": "",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMistral-Small-4\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nGLM-4.6V\nSmolVLM2\nLFM2-VL\nIntern-VL",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMistral-Small-4\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nQwen3.5\nGLM-4.6V\nSmolVLM2\nLFM2-VL\nIntern-VL",
|
||||
"crumbs": [
|
||||
"How To Guides",
|
||||
"MultiModal / Vision Language Models (BETA)"
|
||||
@@ -986,7 +986,7 @@
|
||||
"href": "docs/multimodal.html#supported-models",
|
||||
"title": "MultiModal / Vision Language Models (BETA)",
|
||||
"section": "",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMistral-Small-4\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nGLM-4.6V\nSmolVLM2\nLFM2-VL\nIntern-VL",
|
||||
"text": "Mllama\nLlama4\nPixtral\nLlava-1.5\nMistral-Small-3.1\nMistral-Small-4\nMagistral-Small-2509\nVoxtral\nGemma-3\nGemma-3n\nQwen2-VL\nQwen2.5-VL\nQwen3.5\nGLM-4.6V\nSmolVLM2\nLFM2-VL\nIntern-VL",
|
||||
"crumbs": [
|
||||
"How To Guides",
|
||||
"MultiModal / Vision Language Models (BETA)"
|
||||
@@ -997,7 +997,7 @@
|
||||
"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\nMistral-Small-4\nbase_model: mistralai/Mistral-Small-4-119B-2603\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\nGLM-4.6V\nBoth GLM-4.6V (106B MoE) and GLM-4.6V-Flash (9B) are supported.\n# GLM-4.6V (106B MoE version)\nbase_model: zai-org/GLM-4.6V\n\n# OR GLM-4.6V-Flash (9B version)\nbase_model: zai-org/GLM-4.6V-Flash\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",
|
||||
"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\nMistral-Small-4\nbase_model: mistralai/Mistral-Small-4-119B-2603\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\nQwen3.5\nbase_model: Qwen/Qwen3.5-9B\n\nchat_template: qwen3_5\n\n\nGLM-4.6V\nBoth GLM-4.6V (106B MoE) and GLM-4.6V-Flash (9B) are supported.\n# GLM-4.6V (106B MoE version)\nbase_model: zai-org/GLM-4.6V\n\n# OR GLM-4.6V-Flash (9B version)\nbase_model: zai-org/GLM-4.6V-Flash\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)"
|
||||
|
||||
476
sitemap.xml
476
sitemap.xml
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user