Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -797,6 +797,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<li><a href="#sec-mistral-small-4" id="toc-sec-mistral-small-4" class="nav-link" data-scroll-target="#sec-mistral-small-4">Mistral-Small-4</a></li>
|
||||
<li><a href="#sec-magistral-small-2509" id="toc-sec-magistral-small-2509" class="nav-link" data-scroll-target="#sec-magistral-small-2509">Magistral-Small-2509</a></li>
|
||||
<li><a href="#sec-voxtral" id="toc-sec-voxtral" class="nav-link" data-scroll-target="#sec-voxtral">Voxtral</a></li>
|
||||
<li><a href="#sec-gemma-4" id="toc-sec-gemma-4" class="nav-link" data-scroll-target="#sec-gemma-4">Gemma-4</a></li>
|
||||
<li><a href="#sec-gemma-3" id="toc-sec-gemma-3" class="nav-link" data-scroll-target="#sec-gemma-3">Gemma-3</a></li>
|
||||
<li><a href="#sec-gemma-3n" id="toc-sec-gemma-3n" class="nav-link" data-scroll-target="#sec-gemma-3n">Gemma-3n</a></li>
|
||||
<li><a href="#sec-qwen2-vl" id="toc-sec-qwen2-vl" class="nav-link" data-scroll-target="#sec-qwen2-vl">Qwen2-VL</a></li>
|
||||
@@ -844,6 +845,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<section id="supported-models" class="level2">
|
||||
<h2 class="anchored" data-anchor-id="supported-models">Supported Models</h2>
|
||||
<ul>
|
||||
<li><a href="#sec-gemma-4">Gemma-4</a> <em>(NEW)</em></li>
|
||||
<li><a href="#sec-mllama">Mllama</a></li>
|
||||
<li><a href="#sec-llama4">Llama4</a></li>
|
||||
<li><a href="#sec-pixtral">Pixtral</a></li>
|
||||
@@ -998,6 +1000,55 @@ Tip
|
||||
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a><span class="fu">processor_type</span><span class="kw">:</span><span class="at"> VoxtralProcessor</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-gemma-4" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-gemma-4">Gemma-4</h3>
|
||||
<p>All Gemma 4 variants (E2B, E4B, 26B-A4B, 31B) load as multimodal models even for text-only training.</p>
|
||||
<div class="code-copy-outer-scaffold"><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">base_model</span><span class="kw">:</span><span class="at"> google/gemma-4-E2B-it</span><span class="co"> # or E4B-it, 26B-A4B, 31B</span></span>
|
||||
<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> gemma4</span></span>
|
||||
<span id="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a><span class="fu">freeze_mm_modules</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span><span class="co"> # freeze vision/audio encoders for text-only or vision LoRA</span></span>
|
||||
<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb10-6"><a href="#cb10-6" aria-hidden="true" tabindex="-1"></a><span class="co"># For the 26B-A4B MoE model, enable ScatterMoE and expert LoRA:</span></span>
|
||||
<span id="cb10-7"><a href="#cb10-7" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span></span>
|
||||
<span id="cb10-8"><a href="#cb10-8" 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="cb10-9"><a href="#cb10-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> axolotl.integrations.kernels.KernelsPlugin</span></span>
|
||||
<span id="cb10-10"><a href="#cb10-10" aria-hidden="true" tabindex="-1"></a><span class="fu">use_kernels</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb10-11"><a href="#cb10-11" aria-hidden="true" tabindex="-1"></a><span class="fu">use_scattermoe</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||||
<span id="cb10-12"><a href="#cb10-12" aria-hidden="true" tabindex="-1"></a><span class="fu">experts_implementation</span><span class="kw">:</span><span class="at"> scattermoe</span></span>
|
||||
<span id="cb10-13"><a href="#cb10-13" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb10-14"><a href="#cb10-14" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_modules</span><span class="kw">:</span><span class="at"> </span><span class="st">'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj'</span></span>
|
||||
<span id="cb10-15"><a href="#cb10-15" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb10-16"><a href="#cb10-16" aria-hidden="true" tabindex="-1"></a><span class="co"># MoE expert LoRA (3D tensors, not nn.Linear) — only for 26B-A4B:</span></span>
|
||||
<span id="cb10-17"><a href="#cb10-17" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_parameters</span><span class="kw">:</span></span>
|
||||
<span id="cb10-18"><a href="#cb10-18" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> experts.gate_up_proj</span></span>
|
||||
<span id="cb10-19"><a href="#cb10-19" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> experts.down_proj</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
<div class="callout callout-style-default callout-warning 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">
|
||||
Warning
|
||||
</div>
|
||||
</div>
|
||||
<div class="callout-body-container callout-body">
|
||||
<p>Gemma 4 VLM training starts with high loss (~8-15). This is expected — see the <a href="../docs/training_stability.html">training stability guide</a> for details.</p>
|
||||
</div>
|
||||
</div>
|
||||
<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>For DDP training, axolotl auto-detects Gemma4 and sets <code>use_reentrant=False</code> and <code>ddp_find_unused_parameters=True</code>. However, when <code>activation_offloading: true</code>, <code>ddp_find_unused_parameters</code> is skipped (checkpoint wrappers conflict with it); use <code>freeze_mm_modules: true</code> instead to handle unused vision/audio params. For FSDP2, use <code>fsdp_transformer_layer_cls_to_wrap: Gemma4TextDecoderLayer</code>.</p>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="sec-gemma-3" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-gemma-3">Gemma-3</h3>
|
||||
<div class="callout callout-style-default callout-tip callout-titled">
|
||||
@@ -1014,9 +1065,9 @@ Tip
|
||||
</div>
|
||||
</div>
|
||||
<p>For multi-modal 4B/12B/27B models, use the following config:</p>
|
||||
<div class="code-copy-outer-scaffold"><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">base_model</span><span class="kw">:</span><span class="at"> google/gemma-3-4b-it</span></span>
|
||||
<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> gemma3</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="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">base_model</span><span class="kw">:</span><span class="at"> google/gemma-3-4b-it</span></span>
|
||||
<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> gemma3</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-gemma-3n" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-gemma-3n">Gemma-3n</h3>
|
||||
@@ -1046,42 +1097,42 @@ Tip
|
||||
<p>Please make sure to install <code>timm</code> via <code>pip3 install timm==1.0.17</code></p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="code-copy-outer-scaffold"><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">base_model</span><span class="kw">:</span><span class="at"> google/gemma-3n-E2B-it</span></span>
|
||||
<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> gemma3n</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="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">base_model</span><span class="kw">:</span><span class="at"> google/gemma-3n-E2B-it</span></span>
|
||||
<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> gemma3n</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
</section>
|
||||
<section id="sec-qwen2-vl" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-qwen2-vl">Qwen2-VL</h3>
|
||||
<div class="code-copy-outer-scaffold"><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">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen2-VL-7B-Instruct</span></span>
|
||||
<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> qwen2_vl</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="cb13"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen2-VL-7B-Instruct</span></span>
|
||||
<span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> 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-qwen25-vl" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-qwen25-vl">Qwen2.5-VL</h3>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb13"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen2.5-VL-7B-Instruct</span></span>
|
||||
<span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb13-3"><a href="#cb13-3" 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-vl" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-qwen3-vl">Qwen3-VL</h3>
|
||||
<div class="code-copy-outer-scaffold"><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">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen3-VL-4B-Instruct</span></span>
|
||||
<div class="code-copy-outer-scaffold"><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">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen2.5-VL-7B-Instruct</span></span>
|
||||
<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-vl" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="sec-qwen3-vl">Qwen3-VL</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-VL-4B-Instruct</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"> 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>
|
||||
<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"> Qwen/Qwen3.5-9B</span></span>
|
||||
<span id="cb16-2"><a href="#cb16-2" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb16-3"><a href="#cb16-3" 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="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>
|
||||
<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="co"># GLM-4.6V (106B MoE version)</span></span>
|
||||
<span id="cb17-2"><a href="#cb17-2" 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="cb17-3"><a href="#cb17-3" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb17-4"><a href="#cb17-4" aria-hidden="true" tabindex="-1"></a><span class="co"># OR GLM-4.6V-Flash (9B version)</span></span>
|
||||
<span id="cb17-5"><a href="#cb17-5" 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>
|
||||
@@ -1098,7 +1149,7 @@ 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="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>
|
||||
<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"> 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>
|
||||
@@ -1115,7 +1166,7 @@ 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="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>
|
||||
<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"> 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>
|
||||
@@ -1132,7 +1183,7 @@ 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="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>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb20"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb20-1"><a href="#cb20-1" 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">
|
||||
@@ -1217,31 +1268,31 @@ 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="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>
|
||||
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb21"><pre class="sourceCode json code-with-copy"><code class="sourceCode json"><span id="cb21-1"><a href="#cb21-1" aria-hidden="true" tabindex="-1"></a><span class="ot">[</span></span>
|
||||
<span id="cb21-2"><a href="#cb21-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb21-3"><a href="#cb21-3" aria-hidden="true" tabindex="-1"></a> <span class="dt">"messages"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb21-4"><a href="#cb21-4" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb21-5"><a href="#cb21-5" 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="cb21-6"><a href="#cb21-6" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb21-7"><a href="#cb21-7" 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="cb21-8"><a href="#cb21-8" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb21-9"><a href="#cb21-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb21-10"><a href="#cb21-10" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb21-11"><a href="#cb21-11" 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="cb21-12"><a href="#cb21-12" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb21-13"><a href="#cb21-13" 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="cb21-14"><a href="#cb21-14" 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="cb21-15"><a href="#cb21-15" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb21-16"><a href="#cb21-16" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span><span class="ot">,</span></span>
|
||||
<span id="cb21-17"><a href="#cb21-17" aria-hidden="true" tabindex="-1"></a> <span class="fu">{</span></span>
|
||||
<span id="cb21-18"><a href="#cb21-18" 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="cb21-19"><a href="#cb21-19" aria-hidden="true" tabindex="-1"></a> <span class="dt">"content"</span><span class="fu">:</span> <span class="ot">[</span></span>
|
||||
<span id="cb21-20"><a href="#cb21-20" 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="cb21-21"><a href="#cb21-21" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb21-22"><a href="#cb21-22" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb21-23"><a href="#cb21-23" aria-hidden="true" tabindex="-1"></a> <span class="ot">]</span></span>
|
||||
<span id="cb21-24"><a href="#cb21-24" aria-hidden="true" tabindex="-1"></a> <span class="fu">}</span></span>
|
||||
<span id="cb21-25"><a href="#cb21-25" 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">
|
||||
|
||||
Reference in New Issue
Block a user