Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /pr_33913 /en /quantization /aqlm.html

rtrm

28 days ago

download

raw

12.3 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"AQLM","local":"aqlm","sections":[{"title":"PEFT","local":"peft","sections":[],"depth":2},{"title":"AQLM configurations","local":"aqlm-configurations","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/pr_33913/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/entry/start.b67f883f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/scheduler.25b97de1.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/singletons.62a184e0.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/index.e188933d.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/paths.51881b9e.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/entry/app.e436b1f2.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/index.d9030fc9.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/nodes/0.05e395f5.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/nodes/396.6186b4b8.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/Tip.baa67368.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/CodeBlock.e6cd0d95.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/EditOnGithub.91d95064.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"AQLM","local":"aqlm","sections":[{"title":"PEFT","local":"peft","sections":[],"depth":2},{"title":"AQLM configurations","local":"aqlm-configurations","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="aqlm" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#aqlm"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>AQLM</span></h1> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1rh1txr">Try AQLM on <a href="https://colab.research.google.com/drive/1-xZmBRXT5Fm3Ghn4Mwa2KRypORXb855X?usp=sharing" rel="nofollow">Google Colab</a>!</p></div> <p data-svelte-h="svelte-1qdvqc0">Additive Quantization of Language Models (<a href="https://arxiv.org/abs/2401.06118" rel="nofollow">AQLM</a>) is a Large Language Models compression method. It quantizes multiple weights together and takes advantage of interdependencies between them. AQLM represents groups of 8-16 weights as a sum of multiple vector codes.</p> <p data-svelte-h="svelte-1rdkef8">Inference support for AQLM is realised in the <code>aqlm</code> library. Make sure to install it to run the models (note aqlm works only with python>=3.10):</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->pip install aqlm[gpu,cpu]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-6sf1ac">The library provides efficient kernels for both GPU and CPU inference and training.</p> <p data-svelte-h="svelte-1urbdfd">The instructions on how to quantize models yourself, as well as all the relevant code can be found in the corresponding GitHub <a href="https://github.com/Vahe1994/AQLM" rel="nofollow">repository</a>. To run AQLM models simply load a model that has been quantized with AQLM:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, AutoModelForCausalLM

	quantized_model = AutoModelForCausalLM.from_pretrained(
	<span class="hljs-string">"ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf"</span>,
	torch_dtype=<span class="hljs-string">"auto"</span>,
	device_map=<span class="hljs-string">"auto"</span>
	)
	tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf"</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="peft" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#peft"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>PEFT</span></h2> <p data-svelte-h="svelte-1uurbap">Starting with version <code>aqlm 1.0.2</code>, AQLM supports Parameter-Efficient Fine-Tuning in a form of <a href="https://huggingface.co/docs/peft/package_reference/lora" rel="nofollow">LoRA</a> integrated into the <a href="https://huggingface.co/blog/peft" rel="nofollow">PEFT</a> library.</p> <h2 class="relative group"><a id="aqlm-configurations" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#aqlm-configurations"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>AQLM configurations</span></h2> <p data-svelte-h="svelte-1ouechy">AQLM quantization setups vary mainly on the number of codebooks used as well as codebook sizes in bits. The most popular setups, as well as inference kernels they support are:</p> <table data-svelte-h="svelte-mgp7ro"><thead><tr><th>Kernel</th> <th>Number of codebooks</th> <th>Codebook size, bits</th> <th>Notation</th> <th>Accuracy</th> <th>Speedup</th> <th>Fast GPU inference</th> <th>Fast CPU inference</th></tr></thead> <tbody><tr><td>Triton</td> <td>K</td> <td>N</td> <td>KxN</td> <td>-</td> <td>Up to ~0.7x</td> <td>✅</td> <td>❌</td></tr> <tr><td>CUDA</td> <td>1</td> <td>16</td> <td>1x16</td> <td>Best</td> <td>Up to ~1.3x</td> <td>✅</td> <td>❌</td></tr> <tr><td>CUDA</td> <td>2</td> <td>8</td> <td>2x8</td> <td>OK</td> <td>Up to ~3.0x</td> <td>✅</td> <td>❌</td></tr> <tr><td>Numba</td> <td>K</td> <td>8</td> <td>Kx8</td> <td>Good</td> <td>Up to ~4.0x</td> <td>❌</td> <td>✅</td></tr></tbody></table> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/en/quantization/aqlm.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_z647wz = {
	assets: "/docs/transformers/pr_33913/en",
	base: "/docs/transformers/pr_33913/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/pr_33913/en/_app/immutable/entry/start.b67f883f.js"),
	import("/docs/transformers/pr_33913/en/_app/immutable/entry/app.e436b1f2.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 396],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 12.3 kB
Xet hash:: 8add7ee6ef34956ead8293f262d200c976f454daaf4187c5a1e0251ce6de4d5b

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.