Built site for gh-pages

.nojekyll

@@ -1 +1 @@
-ec7962f3
+590c8a6b

docs/models/qwen3-next.html

@@ -784,31 +784,16 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
 <section id="getting-started" class="level2">
 <h2 class="anchored" data-anchor-id="getting-started">Getting started</h2>
 <ol type="1">
-<li><p>Install Axolotl following the <a href="https://docs.axolotl.ai/docs/installation.html">installation guide</a>. You need to install from main as Qwen3-Next is only on nightly or use our latest <a href="https://docs.axolotl.ai/docs/docker.html">Docker images</a>.</p>
-<p>Here is an example of how to install from main for pip:</p></li>
+<li><p>Install Axolotl following the <a href="https://docs.axolotl.ai/docs/installation.html">installation guide</a>.</p></li>
+<li><p>Install <a href="https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy">Cut Cross Entropy</a> to reduce training VRAM usage.</p></li>
+<li><p>Install FLA for improved performance</p></li>
 </ol>
-<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb1"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Ensure you have Pytorch installed (Pytorch 2.6.0 min)</span></span>
-<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">git</span> clone https://github.com/axolotl-ai-cloud/axolotl.git</span>
-<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="bu">cd</span> axolotl</span>
-<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="ex">pip3</span> install packaging==26.0 setuptools==75.8.0 wheel ninja</span>
-<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="ex">pip3</span> install <span class="at">--no-build-isolation</span> <span class="at">-e</span> <span class="st">'.[flash-attn]'</span></span>
-<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a><span class="co"># Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy</span></span>
-<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a><span class="ex">python</span> scripts/cutcrossentropy_install.py <span class="kw">|</span> <span class="fu">sh</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
-<ol start="2" type="1">
-<li>Install Qwen3-Next transformers commit</li>
-</ol>
-<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> transformers <span class="kw">&amp;&amp;</span> <span class="ex">pip3</span> install <span class="st">"git+https://github.com/huggingface/transformers.git@b9282355bea846b54ed850a066901496b19da654"</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
-<ol start="3" type="1">
-<li>Install FLA for improved performance</li>
-</ol>
-<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb3"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="ex">pip3</span> uninstall <span class="at">-y</span> causal-conv1d <span class="kw">&amp;&amp;</span> <span class="ex">pip3</span> install flash-linear-attention==0.3.2</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="cb1"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="ex">pip3</span> uninstall <span class="at">-y</span> causal-conv1d <span class="kw">&amp;&amp;</span> <span class="ex">pip3</span> install flash-linear-attention==0.4.1</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
 <ol start="4" type="1">
 <li>Run the finetuning example:</li>
 </ol>
-<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb4"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train examples/qwen3-next/qwen3-next-80b-a3b-qlora.yaml</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
-<p>This config uses about 45.62 GiB VRAM.</p>
+<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">axolotl</span> train examples/qwen3-next/qwen3-next-80b-a3b-qlora.yaml</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
+<p>This config uses about ~47 GiB (no target experts) and ~71GiB (target experts) VRAM.</p>
 <p>Let us know how it goes. Happy finetuning! 🚀</p>
 <section id="tips" class="level3">
 <h3 class="anchored" data-anchor-id="tips">TIPS</h3>

search.json

@@ -5572,7 +5572,7 @@
     "href": "docs/models/qwen3-next.html#getting-started",
     "title": "Qwen 3 Next",
     "section": "Getting started",
-    "text": "Getting started\n\nInstall Axolotl following the installation guide. You need to install from main as Qwen3-Next is only on nightly or use our latest Docker images.\nHere is an example of how to install from main for pip:\n\n# Ensure you have Pytorch installed (Pytorch 2.6.0 min)\ngit clone https://github.com/axolotl-ai-cloud/axolotl.git\ncd axolotl\n\npip3 install packaging==26.0 setuptools==75.8.0 wheel ninja\npip3 install --no-build-isolation -e '.[flash-attn]'\n\n# Install CCE https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy\npython scripts/cutcrossentropy_install.py | sh\n\nInstall Qwen3-Next transformers commit\n\npip3 uninstall -y transformers && pip3 install \"git+https://github.com/huggingface/transformers.git@b9282355bea846b54ed850a066901496b19da654\"\n\nInstall FLA for improved performance\n\npip3 uninstall -y causal-conv1d && pip3 install flash-linear-attention==0.3.2\n\nRun the finetuning example:\n\naxolotl train examples/qwen3-next/qwen3-next-80b-a3b-qlora.yaml\nThis config uses about 45.62 GiB VRAM.\nLet us know how it goes. Happy finetuning! 🚀\n\nTIPS\n\nFor inference, you can experiment with temperature: 0.7, top_p: 0.8, top_k: 20, and min_p: 0.\nYou can run a full finetuning by removing the adapter: qlora and load_in_4bit: true from the config. See Multi-GPU section below.\nRead more on how to load your own dataset at docs.\nThe dataset format follows the OpenAI Messages format as seen here.",
+    "text": "Getting started\n\nInstall Axolotl following the installation guide.\nInstall Cut Cross Entropy to reduce training VRAM usage.\nInstall FLA for improved performance\n\npip3 uninstall -y causal-conv1d && pip3 install flash-linear-attention==0.4.1\n\nRun the finetuning example:\n\naxolotl train examples/qwen3-next/qwen3-next-80b-a3b-qlora.yaml\nThis config uses about ~47 GiB (no target experts) and ~71GiB (target experts) VRAM.\nLet us know how it goes. Happy finetuning! 🚀\n\nTIPS\n\nFor inference, you can experiment with temperature: 0.7, top_p: 0.8, top_k: 20, and min_p: 0.\nYou can run a full finetuning by removing the adapter: qlora and load_in_4bit: true from the config. See Multi-GPU section below.\nRead more on how to load your own dataset at docs.\nThe dataset format follows the OpenAI Messages format as seen here.",
     "crumbs": [
       "Getting Started",
       "Model Guides",