transformers/main/ko/quantization/quanto.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quanto&quot;,&quot;local&quot;:&quot;quanto&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/transformers/main/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/scheduler.9bc65507.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/singletons.9eec45c3.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.3b203c72.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/paths.566078f7.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.707bf1b6.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/0.1c99376b.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/55.bd0b6dd1.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/Tip.c2ecdbf4.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CodeBlock.54a9f38d.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/EditOnGithub.922df6ba.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quanto&quot;,&quot;local&quot;:&quot;quanto&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <h1 class="relative group"><a id="quanto" 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="#quanto"><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>Quanto</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-1f8fow8">이 <a href="https://colab.research.google.com/drive/16CXfVmtdQvciSh9BopZUDYcmXCDpvgrT?usp=sharing" rel="nofollow">노트북</a>으로 Quanto와 transformers를 사용해 보세요!</p></div> <p data-svelte-h="svelte-u79ms7"><a href="https://github.com/huggingface/optimum-quanto" rel="nofollow">🤗 Quanto</a> 라이브러리는 다목적 파이토치 양자화 툴킷입니다. 이 라이브러리에서 사용되는 양자화 방법은 선형 양자화입니다. Quanto는 다음과 같은 여러 가지 기능을 제공합니다:</p> <ul data-svelte-h="svelte-1ghlhdh"><li>가중치 양자화 (<code>float8</code>,<code>int8</code>,<code>int4</code>,<code>int2</code>)</li> <li>활성화 양자화 (<code>float8</code>,<code>int8</code>)</li> <li>모달리티에 구애받지 않음 (e.g CV,LLM)</li> <li>장치에 구애받지 않음 (e.g CUDA,MPS,CPU)</li> <li><code>torch.compile</code> 호환성</li> <li>특정 장치에 대한 사용자 정의 커널의 쉬운 추가</li> <li>QAT(양자화를 고려한 학습) 지원</li></ul> <p data-svelte-h="svelte-1dydg7a">시작하기 전에 다음 라이브러리가 설치되어 있는지 확인하세요:</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 quanto accelerate transformers<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-11pt1fa">이제 <code>from_pretrained()</code> 메소드에 <code>QuantoConfig</code> 객체를 전달하여 모델을 양자화할 수 있습니다. 이 방식은 <code>torch.nn.Linear</code> 레이어를 포함하는 모든 모달리티의 모든 모델에서 잘 작동합니다.</p> <p data-svelte-h="svelte-imwxel">허깅페이스의 transformers 라이브러리는 개발자 편의를 위해 quanto의 인터페이스를 일부 통합하여 지원하고 있으며, 이 방식으로는 가중치 양자화만 지원합니다. 활성화 양자화, 캘리브레이션, QAT 같은 더 복잡한 기능을 수행하기 위해서는 <a href="https://github.com/huggingface/optimum-quanto" rel="nofollow">quanto</a> 라이브러리의 해당 함수를 직접 호출해야 합니다.</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> AutoModelForCausalLM, AutoTokenizer, QuantoConfig

model_id = <span class="hljs-string">&quot;facebook/opt-125m&quot;</span>
tokenizer = AutoTokenizer.from_pretrained(model_id)
quantization_config = QuantoConfig(weights=<span class="hljs-string">&quot;int8&quot;</span>)
quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map=<span class="hljs-string">&quot;cuda:0&quot;</span>, quantization_config=quantization_config)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-8mo7mh">참고로, transformers에서는 아직 직렬화가 지원되지 않지만 곧 지원될 예정입니다!
모델을 저장하고 싶으면 quanto 라이브러리를 대신 사용할 수 있습니다.</p> <p data-svelte-h="svelte-1i8tmwt">Quanto 라이브러리는 양자화를 위해 선형 양자화 알고리즘을 사용합니다. 비록 기본적인 양자화 기술이지만, 좋은 결과를 얻는데 아주 큰 도움이 됩니다! 바로 아래에 있는 벤치마크(llama-2-7b의 펄플렉서티 지표)를 확인해 보세요. 더 많은 벤치마크는 <a href="https://github.com/huggingface/quanto/tree/main/bench/generation" rel="nofollow">여기</a> 에서 찾을 수 있습니다.</p> <div class="flex gap-4" data-svelte-h="svelte-196rp13"><div><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/quantization/NousResearch-Llama-2-7b-hf_Perplexity.png" alt="llama-2-7b-quanto-perplexity"></div></div> <p data-svelte-h="svelte-1dccdow">이 라이브러리는 대부분의 PTQ 최적화 알고리즘과 호환될 만큼 충분히 유연합니다. 앞으로의 계획은 가장 인기 있는 알고리즘(AWQ, Smoothquant)을 최대한 매끄럽게 통합하는 것입니다.</p> <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/ko/quantization/quanto.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1hrx8 = {
						assets: "/docs/transformers/main/ko",
						base: "/docs/transformers/main/ko",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js"),
						import("/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 55],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>