Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / smol-course /pr_296 /ko /README.html

HuggingFaceDocBuilder

about 2 months ago

download

raw

27.8 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"소형 언어 모델 과정","local":"소형-언어-모델-과정","sections":[{"title":"과정 개요","local":"과정-개요","sections":[],"depth":2},{"title":"왜 소형 언어 모델을 사용하나요?","local":"왜-소형-언어-모델을-사용하나요","sections":[],"depth":2},{"title":"사전 준비 사항","local":"사전-준비-사항","sections":[],"depth":2},{"title":"설치","local":"설치","sections":[{"title":"uv 사용","local":"uv-사용","sections":[],"depth":3},{"title":"pip 사용","local":"pip-사용","sections":[],"depth":3},{"title":"Google Colab","local":"google-colab","sections":[],"depth":3}],"depth":2},{"title":"참여","local":"참여","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/smol-course/pr_296/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/entry/start.4b8aa76a.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/scheduler.f38f3a0e.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/singletons.9dc2cfa6.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/paths.19dfb0c8.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/entry/app.f0d4b751.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/preload-helper.9248d1a9.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/index.a03143fc.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/nodes/0.ef9bb04f.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/nodes/2.18390ab3.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.a813f85d.js">
	<link rel="modulepreload" href="/docs/smol-course/pr_296/ko/_app/immutable/chunks/CodeBlock.0c6d6ef1.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"소형 언어 모델 과정","local":"소형-언어-모델-과정","sections":[{"title":"과정 개요","local":"과정-개요","sections":[],"depth":2},{"title":"왜 소형 언어 모델을 사용하나요?","local":"왜-소형-언어-모델을-사용하나요","sections":[],"depth":2},{"title":"사전 준비 사항","local":"사전-준비-사항","sections":[],"depth":2},{"title":"설치","local":"설치","sections":[{"title":"uv 사용","local":"uv-사용","sections":[],"depth":3},{"title":"pip 사용","local":"pip-사용","sections":[],"depth":3},{"title":"Google Colab","local":"google-colab","sections":[],"depth":3}],"depth":2},{"title":"참여","local":"참여","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <p data-svelte-h="svelte-1f2aupr"><img src="../banner.png" alt="smolcourse image"></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="소형-언어-모델-과정" 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="#소형-언어-모델-과정"><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>소형 언어 모델 과정</span></h1> <p data-svelte-h="svelte-1mnd6go">이 과정에서는 특정 사용 사례에 맞게 언어 모델을 정렬하는 법을 다룹니다. 모든 자료는 대부분의 로컬 컴퓨터에서 실행되므로 간편하게 언어 모델 정렬을 시작해볼 수 있습니다. 이 과정을 위해 필요한 최소한의 GPU 요구 사항이나 유료 서비스가 없습니다. <a href="https://github.com/huggingface/smollm/tree/main" rel="nofollow">SmolLM2</a> 시리즈 모델을 기반으로 하는 과정이지만, 여기서 배운 기술을 더 큰 모델이나 다른 작은 언어 모델로 옮길 수 있습니다.</p> <a href="http://hf.co/join/discord" data-svelte-h="svelte-yck9g"><img src="https://img.shields.io/badge/Discord-7289DA?&logo=discord&logoColor=white"></a> <div style="background: linear-gradient(to right, #e0f7fa, #e1bee7, orange); padding: 20px; border-radius: 5px; margin-bottom: 20px; color: purple;" data-svelte-h="svelte-153mswq"><h2>지금 바로 참여하세요!</h2> <p>이 과정은 열려 있으며 다른 사용자와의 상호 검토를 진행할 수 있습니다. 이 과정에 참여하려면 <strong>pull request(PR)</strong>를 열고 검토 받을 수 있도록 결과물을 제출하세요. 다음 단계를 따르면 됩니다:</p> <ol><li><a href="https://github.com/huggingface/smol-course/fork">여기</a>에서 레포지토리를 fork하세요.</li> <li>자료를 읽고, 바꿔 보고, 실습해보고, 나만의 예제를 추가해보세요.</li> <li>december-2024 브랜치에 PR을 보내세요.</li> <li>검토가 끝나면 december-2024 브랜치에 병합됩니다.</li></ol> <p>이 과정은 학습에 도움이 될 뿐만 아니라 지속적으로 발전하는 커뮤니티 기반 코스를 형성하는 데에도 기여할 것입니다.</p></div> <p data-svelte-h="svelte-1vnmtxl"><a href="https://github.com/huggingface/smol-course/discussions/2#discussion-7602932" rel="nofollow">discussion thread</a>에서 과정에 대해 토론할 수도 있습니다.</p> <h2 class="relative group"><a id="과정-개요" 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="#과정-개요"><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>과정 개요</span></h2> <p data-svelte-h="svelte-9gwtfk">이 과정은 소형 언어 모델의 초기 학습부터 결과물 배포까지 실습할 수 있는 실용적인 내용을 제공합니다.</p> <table data-svelte-h="svelte-1y2gtvz"><thead><tr><th>모듈</th> <th>설명</th> <th>상태</th> <th>공개일</th></tr></thead> <tbody><tr><td><a href="./1_instruction_tuning">Instruction Tuning</a></td> <td>지도 학습 기반 미세 조정, 대화 템플릿 작성, 기본적인 지시를 따르게 하는 방법 학습</td> <td>✅ 학습 가능</td> <td>2024. 12. 3</td></tr> <tr><td><a href="./2_preference_alignment">Preference Alignment</a></td> <td>모델을 인간 선호도에 맞게 정렬하기 위한 DPO와 ORPO 기법 학습</td> <td>✅ 학습 가능</td> <td>2024. 12. 6</td></tr> <tr><td><a href="./3_parameter_efficient_finetuning">Parameter-efficient Fine-tuning</a></td> <td>LoRA, 프롬프트 튜닝을 포함한 효율적인 적응 방법 학습</td> <td>✅ 학습 가능</td> <td>2024. 12. 9</td></tr> <tr><td><a href="./4_evaluation">Evaluation</a></td> <td>자동 벤치마크 사용법 및 사용자 정의 도메인 평가 수행 방법 학습</td> <td>✅ 학습 가능</td> <td>2024. 12. 13</td></tr> <tr><td><a href="./5_vision_language_models">Vision-language Models</a></td> <td>비전-언어 태스크를 위한 멀티모달 모델 적용 방법 학습</td> <td><a href="https://github.com/huggingface/smol-course/issues/49" rel="nofollow">🚧 준비중</a></td> <td>2024. 12. 16</td></tr> <tr><td><a href="./6_synthetic_datasets">Synthetic Datasets</a></td> <td>모델 학습을 위한 합성 데이터셋 생성 및 검증</td> <td><a href="https://github.com/huggingface/smol-course/issues/83" rel="nofollow">🚧 준비중</a></td> <td>2024. 12. 20</td></tr> <tr><td><a href="./7_inference">Inference</a></td> <td>모델의 효율적인 추론 방법 학습</td> <td>📝 작성 예정</td> <td>2024. 12. 23</td></tr></tbody></table> <h2 class="relative group"><a id="왜-소형-언어-모델을-사용하나요" 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="#왜-소형-언어-모델을-사용하나요"><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>왜 소형 언어 모델을 사용하나요?</span></h2> <p data-svelte-h="svelte-50ekhi">대형 언어 모델은 뛰어난 능력을 보여주지만, 상당한 연산 자원을 필요로 하며 특정 기능에 초점을 맞춘 애플리케이션에 대해서는 대형 언어 모델이 과한 경우도 있습니다. 소형 언어 모델은 도메인 특화 애플리케이션에 있어서 몇 가지 이점을 제공합니다:</p> <ul data-svelte-h="svelte-11k38g4"><li><strong>효율성</strong>: 대형 언어 모델보다 훨씬 적은 연산 자원으로 학습 및 배포 가능</li> <li><strong>맞춤화</strong>: 특정 도메인에 대한 미세 조정 및 적응 용이</li> <li><strong>제어</strong>: 모델 동작 과정을 잘 이해할 수 있고 모델의 동작을 쉽게 제어 가능</li> <li><strong>비용</strong>: 학습과 추론 과정에서 필요한 비용 감소</li> <li><strong>프라이버시</strong>: 데이터를 외부 API로 보내지 않고 로컬에서 실행 가능</li> <li><strong>친환경</strong>: 탄소 발자국을 줄이는 효율적인 자원 사용</li> <li><strong>쉬운 학술 연구 및 개발</strong>: 최신 LLM을 활용해 물리적 제약 없이 학술 연구를 쉽게 시작할 수 있도록 지원</li></ul> <h2 class="relative group"><a id="사전-준비-사항" 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="#사전-준비-사항"><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>사전 준비 사항</span></h2> <p data-svelte-h="svelte-vqi5vv">시작하기 전에 아래 사항이 준비되어 있는지 확인하세요:</p> <ul data-svelte-h="svelte-1d0xu42"><li>머신러닝과 자연어처리에 대한 기본적인 이해가 필요합니다.</li> <li>Python, PyTorch 및 <code>transformers</code> 라이브러리에 익숙해야 합니다.</li> <li>사전 학습된 언어 모델과 레이블이 있는 액세스할 수 있어야 합니다.</li></ul> <h2 class="relative group"><a id="설치" 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="#설치"><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>설치</span></h2> <p data-svelte-h="svelte-gz9ns0">이 과정은 패키지 형태로 관리되기 때문에 패키지 매니저를 이용해 의존성 설치를 쉽게 진행할 수 있습니다. 이를 위해 <a href="https://github.com/astral-sh/uv" rel="nofollow">uv</a> 사용을 권장하지만 <code>pip</code>나 <code>pdm</code>을 사용할 수도 있습니다.</p> <h3 class="relative group"><a id="uv-사용" 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="#uv-사용"><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>uv 사용</span></h3> <p data-svelte-h="svelte-g48lld"><code>uv</code>를 설치한 후, 아래 명령어로 소형 언어 모델 과정을 설치할 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=""><!-- HTML_TAG_START -->uv venv --python 3.11.0
	uv <span class="hljs-built_in">sync</span><!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="pip-사용" 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="#pip-사용"><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>pip 사용</span></h3> <p data-svelte-h="svelte-1f2eghc">모든 예제는 동일한 <strong>python 3.11</strong> 환경에서 실행되기 때문에 아래처럼 환경을 생성하고 의존성을 설치해야 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-comment"># python -m venv .venv</span>
	<span class="hljs-comment"># source .venv/bin/activate</span>
	pip install -r requirements.txt<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="google-colab" 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="#google-colab"><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>Google Colab</span></h3> <p data-svelte-h="svelte-1khymrk"><strong>Google Colab</strong>에서는 사용하는 하드웨어에 따라 유연하게 의존성을 설치해야 합니다. 아래와 같이 진행하세요:</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 transformers trl datasets huggingface_hub<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="참여" 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="#참여"><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>참여</span></h2> <p data-svelte-h="svelte-9andge">많은 사람이 고가의 장비 없이 LLM을 미세 조정하는 법을 배울 수 있도록 이 자료를 공유해 봅시다!</p> <p data-svelte-h="svelte-n6b46e"><a href="https://star-history.com/#huggingface/smol-course&Date" rel="nofollow"><img src="https://api.star-history.com/svg?repos=huggingface/smol-course&type=Date" alt="Star History Chart"></a></p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/smol-course/blob/main/units/ko/README.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_11xhwgo = {
	assets: "/docs/smol-course/pr_296/ko",
	base: "/docs/smol-course/pr_296/ko",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/smol-course/pr_296/ko/_app/immutable/entry/start.4b8aa76a.js"),
	import("/docs/smol-course/pr_296/ko/_app/immutable/entry/app.f0d4b751.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 2],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 27.8 kB
Xet hash:: 6df9922ed5bd1bdf21bae43f3785b2443d88b2b117fd0c9ba623236c588a4961

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