transformers/main/ko/quantization/gptq.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;GPTQ&quot;,&quot;local&quot;:&quot;gptq&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.408ae46b.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/scheduler.53228c21.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/singletons.6689a30e.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.e93d0901.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/paths.8adef0e5.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/app.c554ba11.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/preload-helper.cb103237.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.3db2ce32.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/0.ea7f8d3c.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/148.d630f79e.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/Tip.d62b0755.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CopyLLMTxtMenu.1327b590.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.49b88d99.js">
		<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CodeBlock.ada04ea6.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;GPTQ&quot;,&quot;local&quot;:&quot;gptq&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="gptq" 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="#gptq"><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>GPTQ</span></h1> <blockquote class="tip"><p data-svelte-h="svelte-1da9pno">PEFT를 활용한 GPTQ 양자화를 사용해보시려면 이 <a href="https://colab.research.google.com/drive/1_TIrmuKOFhuRRiTWN94iLKUFu6ZX4ceb" rel="nofollow">노트북</a>을 참고하시고, 자세한 내용은 이 <a href="https://huggingface.co/blog/gptq-integration" rel="nofollow">블로그 게시물</a>에서 확인하세요!</p></blockquote> <p data-svelte-h="svelte-1rymx5r"><a href="https://github.com/ModelCloud/GPTQModel" rel="nofollow">GPT-QModel</a> 라이브러리는 GPTQ 알고리즘을 구현합니다. 이는 훈련 후 양자화 기법으로, 가중치 행렬의 각 행을 독립적으로 양자화하여 오차를 최소화하는 가중치 버전을 찾습니다. 이 가중치는 int4로 양자화되지만, 추론 중에는 실시간으로 fp16으로 복원됩니다. 이는 int4 가중치가 GPU의 전역 메모리 대신 결합된 커널에서 역양자화되기 때문에 메모리 사용량을 4배 절약할 수 있으며, 더 낮은 비트 너비를 사용함으로써 통신 시간이 줄어들어 추론 속도가 빨라질 것으로 기대할 수 있습니다.</p> <p data-svelte-h="svelte-1lpb91s">시작하기 전에 다음 라이브러리들이 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="language-bash "><!-- HTML_TAG_START -->pip install gptqmodel --no-build-isolation
pip install --upgrade accelerate optimum transformers<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-h8r0xk">모델을 양자화하려면(현재 텍스트 모델만 지원됨) <a href="/docs/transformers/main/ko/main_classes/quantization#transformers.GPTQConfig">GPTQConfig</a> 클래스를 생성하고 양자화할 비트 수, 양자화를 위한 가중치 교정 데이터셋, 그리고 데이터셋을 준비하기 위한 토크나이저를 설정해야 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="language-py "><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer, GPTQConfig

model_id = <span class="hljs-string">&quot;facebook/opt-125m&quot;</span>
tokenizer = AutoTokenizer.from_pretrained(model_id)
gptq_config = GPTQConfig(bits=<span class="hljs-number">4</span>, dataset=<span class="hljs-string">&quot;c4&quot;</span>, tokenizer=tokenizer)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-16sjond">자신의 데이터셋을 문자열 리스트 형태로 전달할 수도 있지만, GPTQ 논문에서 사용한 동일한 데이터셋을 사용하는 것을 강력히 권장합니다.</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="language-py "><!-- HTML_TAG_START -->dataset = [<span class="hljs-string">&quot;gptqmodel is an easy-to-use model quantization library with user-friendly apis, based on the GPTQ algorithm.&quot;</span>]
gptq_config = GPTQConfig(bits=<span class="hljs-number">4</span>, dataset=dataset, tokenizer=tokenizer)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ohnq2z">양자화할 모델을 로드하고 <code>gptq_config</code>을 <a href="/docs/transformers/main/ko/model_doc/auto#transformers.AutoModel.from_pretrained">from_pretrained()</a> 메소드에 전달하세요. 모델을 메모리에 맞추기 위해 <code>device_map=&quot;auto&quot;</code>를 설정하여 모델을 자동으로 CPU로 오프로드하고, 양자화를 위해 모델 모듈이 CPU와 GPU 간에 이동할 수 있도록 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="language-py "><!-- HTML_TAG_START -->quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map=<span class="hljs-string">&quot;auto&quot;</span>, quantization_config=gptq_config)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-lj3tj5">데이터셋이 너무 커서 메모리가 부족한 경우를 대비한 디스크 오프로드는 현재 지원하지 않고 있습니다. 이럴 때는 <code>max_memory</code> 매개변수를 사용하여 디바이스(GPU 및 CPU)에서 사용할 메모리 양을 할당해 보세요:</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="language-py "><!-- HTML_TAG_START -->quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map=<span class="hljs-string">&quot;auto&quot;</span>, max_memory={<span class="hljs-number">0</span>: <span class="hljs-string">&quot;30GiB&quot;</span>, <span class="hljs-number">1</span>: <span class="hljs-string">&quot;46GiB&quot;</span>, <span class="hljs-string">&quot;cpu&quot;</span>: <span class="hljs-string">&quot;30GiB&quot;</span>}, quantization_config=gptq_config)<!-- HTML_TAG_END --></pre></div> <blockquote class="warning"><p data-svelte-h="svelte-1yg57hz">하드웨어와 모델 매개변수량에 따라 모델을 처음부터 양자화하는 데 드는 시간이 서로 다를 수 있습니다. 예를 들어, 무료 등급의 Google Colab GPU로 비교적 가벼운 <a href="https://huggingface.co/facebook/opt-350m" rel="nofollow">facebook/opt-350m</a> 모델을 양자화하는 데 약 5분이 걸리지만, NVIDIA A100으로 175B에 달하는 매개변수를 가진 모델을 양자화하는 데는 약 4시간에 달하는 시간이 걸릴 수 있습니다. 모델을 양자화하기 전에, Hub에서 해당 모델의 GPTQ 양자화 버전이 이미 존재하는지 확인하는 것이 좋습니다.</p></blockquote> <p data-svelte-h="svelte-z2aoq7">모델이 양자화되면, 모델과 토크나이저를 Hub에 푸시하여 쉽게 공유하고 접근할 수 있습니다. <a href="/docs/transformers/main/ko/main_classes/quantization#transformers.GPTQConfig">GPTQConfig</a>를 저장하기 위해 <a href="/docs/transformers/main/ko/main_classes/model#transformers.utils.PushToHubMixin.push_to_hub">push_to_hub()</a> 메소드를 사용하세요:</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="language-py "><!-- HTML_TAG_START -->quantized_model.push_to_hub(<span class="hljs-string">&quot;opt-125m-gptq&quot;</span>)
tokenizer.push_to_hub(<span class="hljs-string">&quot;opt-125m-gptq&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1s17101">양자화된 모델을 로컬에 저장하려면 <a href="/docs/transformers/main/ko/main_classes/model#transformers.PreTrainedModel.save_pretrained">save_pretrained()</a> 메소드를 사용할 수 있습니다. 모델이 <code>device_map</code> 매개변수로 양자화되었을 경우, 저장하기 전에 전체 모델을 GPU나 CPU로 이동해야 합니다. 예를 들어, 모델을 CPU에 저장하려면 다음과 같이 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="language-py "><!-- HTML_TAG_START -->quantized_model.save_pretrained(<span class="hljs-string">&quot;opt-125m-gptq&quot;</span>)
tokenizer.save_pretrained(<span class="hljs-string">&quot;opt-125m-gptq&quot;</span>)

<span class="hljs-comment"># device_map이 설정된 상태에서 양자화된 경우</span>
quantized_model.to(<span class="hljs-string">&quot;cpu&quot;</span>)
quantized_model.save_pretrained(<span class="hljs-string">&quot;opt-125m-gptq&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-dxybn9">양자화된 모델을 다시 로드하려면 <a href="/docs/transformers/main/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained">from_pretrained()</a> 메소드를 사용하고, <code>device_map=&quot;auto&quot;</code>를 설정하여 모든 사용 가능한 GPU에 모델을 자동으로 분산시켜 더 많은 메모리를 사용하지 않으면서 모델을 더 빠르게 로드할 수 있습니다.</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="language-py "><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(<span class="hljs-string">&quot;{your_username}/opt-125m-gptq&quot;</span>, device_map=<span class="hljs-string">&quot;auto&quot;</span>)<!-- HTML_TAG_END --></pre></div> <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/gptq.md" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1nybis1 = {
						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.408ae46b.js"),
						import("/docs/transformers/main/ko/_app/immutable/entry/app.c554ba11.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 148],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>