Buckets:

hf-doc-build
/

doc-dev

hf-doc-build/doc-dev / transformers /pr_33913 /ko /_app /immutable /nodes /13.08caa8ba.js

rtrm's picture

about 2 months ago

51.1 kB

	import{s as he,o as be,n as z}from"../chunks/scheduler.bdbef820.js";import{S as je,i as _e,g as f,s as p,r as d,A as Me,h as u,f as e,c as i,j as ge,u as g,x as j,k as $e,y as ve,a as n,v as $,d as y,t as h,w as b}from"../chunks/index.33f81d56.js";import{T as Ht}from"../chunks/Tip.34194030.js";import{C as q}from"../chunks/CodeBlock.362b34a4.js";import{F as ye,M as Hs}from"../chunks/Markdown.03194dea.js";import{H as Q,E as Te}from"../chunks/EditOnGithub.a9246e21.js";function Ze(w){let a,c='configuration 파일을 딕셔너리로 저장하거나 사용자 정의 configuration 속성과 기본 configuration 속성의 차이점만 저장할 수도 있습니다! 자세한 내용은 <a href="main_classes/configuration">configuration</a> 문서를 참조하세요.';return{c(){a=f("p"),a.innerHTML=c},l(l){a=u(l,"P",{"data-svelte-h":!0}),j(a)!=="svelte-p4ht4o"&&(a.innerHTML=c)},m(l,o){n(l,a,o)},p:z,d(l){l&&e(a)}}}function we(w){let a,c="사용자 지정 configuration 속성을 모델에 가져옵니다:",l,o,_,M,C="이제 사전 학습된 가중치 대신 임의의 값을 가진 모델이 생성됩니다. 이 모델을 훈련하기 전까지는 유용하게 사용할 수 없습니다. 훈련은 비용과 시간이 많이 소요되는 프로세스입니다. 일반적으로 훈련에 필요한 리소스의 일부만 사용하면서 더 나은 결과를 더 빨리 얻으려면 사전 훈련된 모델을 사용하는 것이 좋습니다.",k,v,J='사전 학습된 모델을 <a href="/docs/transformers/pr_33913/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained">from_pretrained()</a>로 생성합니다:',m,T,U,R,x="🤗 Transformers에서 제공한 모델의 사전 학습된 가중치를 사용하는 경우 기본 모델 configuration을 자동으로 불러옵니다. 그러나 원하는 경우 기본 모델 configuration 속성의 일부 또는 전부를 사용자 지정으로 바꿀 수 있습니다:",G,W,V;return o=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERpc3RpbEJlcnRNb2RlbCUwQSUwQW15X2NvbmZpZyUyMCUzRCUyMERpc3RpbEJlcnRDb25maWcuZnJvbV9wcmV0cmFpbmVkKCUyMi4lMkZ5b3VyX21vZGVsX3NhdmVfcGF0aCUyRmNvbmZpZy5qc29uJTIyKSUwQW1vZGVsJTIwJTNEJTIwRGlzdGlsQmVydE1vZGVsKG15X2NvbmZpZyk=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistilBertModel

	<span class="hljs-meta">>>> </span>my_config = DistilBertConfig.from_pretrained(<span class="hljs-string">"./your_model_save_path/config.json"</span>)
	<span class="hljs-meta">>>> </span>model = DistilBertModel(my_config)`,wrap:!1}}),T=new q({props:{code:"bW9kZWwlMjAlM0QlMjBEaXN0aWxCZXJ0TW9kZWwuZnJvbV9wcmV0cmFpbmVkKCUyMmRpc3RpbGJlcnQlMkZkaXN0aWxiZXJ0LWJhc2UtdW5jYXNlZCUyMik=",highlighted:'<span class="hljs-meta">>>> </span>model = DistilBertModel.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)',wrap:!1}}),W=new q({props:{code:"bW9kZWwlMjAlM0QlMjBEaXN0aWxCZXJ0TW9kZWwuZnJvbV9wcmV0cmFpbmVkKCUyMmRpc3RpbGJlcnQlMkZkaXN0aWxiZXJ0LWJhc2UtdW5jYXNlZCUyMiUyQyUyMGNvbmZpZyUzRG15X2NvbmZpZyk=",highlighted:'<span class="hljs-meta">>>> </span>model = DistilBertModel.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>, config=my_config)',wrap:!1}}),{c(){a=f("p"),a.textContent=c,l=p(),d(o.$$.fragment),_=p(),M=f("p"),M.textContent=C,k=p(),v=f("p"),v.innerHTML=J,m=p(),d(T.$$.fragment),U=p(),R=f("p"),R.textContent=x,G=p(),d(W.$$.fragment)},l(r){a=u(r,"P",{"data-svelte-h":!0}),j(a)!=="svelte-14tvdkn"&&(a.textContent=c),l=i(r),g(o.$$.fragment,r),_=i(r),M=u(r,"P",{"data-svelte-h":!0}),j(M)!=="svelte-1x90d88"&&(M.textContent=C),k=i(r),v=u(r,"P",{"data-svelte-h":!0}),j(v)!=="svelte-1ppxoc7"&&(v.innerHTML=J),m=i(r),g(T.$$.fragment,r),U=i(r),R=u(r,"P",{"data-svelte-h":!0}),j(R)!=="svelte-yuz877"&&(R.textContent=x),G=i(r),g(W.$$.fragment,r)},m(r,Z){n(r,a,Z),n(r,l,Z),$(o,r,Z),n(r,_,Z),n(r,M,Z),n(r,k,Z),n(r,v,Z),n(r,m,Z),$(T,r,Z),n(r,U,Z),n(r,R,Z),n(r,G,Z),$(W,r,Z),V=!0},p:z,i(r){V\|\|(y(o.$$.fragment,r),y(T.$$.fragment,r),y(W.$$.fragment,r),V=!0)},o(r){h(o.$$.fragment,r),h(T.$$.fragment,r),h(W.$$.fragment,r),V=!1},d(r){r&&(e(a),e(l),e(_),e(M),e(k),e(v),e(m),e(U),e(R),e(G)),b(o,r),b(T,r),b(W,r)}}}function qe(w){let a,c;return a=new Hs({props:{$$slots:{default:[we]},$$scope:{ctx:w}}}),{c(){d(a.$$.fragment)},l(l){g(a.$$.fragment,l)},m(l,o){$(a,l,o),c=!0},p(l,o){const _={};o&2&&(_.$$scope={dirty:o,ctx:l}),a.$set(_)},i(l){c\|\|(y(a.$$.fragment,l),c=!0)},o(l){h(a.$$.fragment,l),c=!1},d(l){b(a,l)}}}function Je(w){let a,c="사용자 지정 configuration 속성을 모델에 불러옵니다:",l,o,_,M,C="이제 사전 학습된 가중치 대신 임의의 값을 가진 모델이 생성됩니다. 이 모델을 훈련하기 전까지는 유용하게 사용할 수 없습니다. 훈련은 비용과 시간이 많이 소요되는 프로세스입니다. 일반적으로 훈련에 필요한 리소스의 일부만 사용하면서 더 나은 결과를 더 빨리 얻으려면 사전 훈련된 모델을 사용하는 것이 좋습니다.",k,v,J='사전 학습된 모델을 <a href="/docs/transformers/pr_33913/ko/main_classes/model#transformers.TFPreTrainedModel.from_pretrained">from_pretrained()</a>로 생성합니다:',m,T,U,R,x="🤗 Transformers에서 제공한 모델의 사전 학습된 가중치를 사용하는 경우 기본 모델 configuration을 자동으로 불러옵니다. 그러나 원하는 경우 기본 모델 configuration 속성의 일부 또는 전부를 사용자 지정으로 바꿀 수 있습니다:",G,W,V;return o=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFRGRGlzdGlsQmVydE1vZGVsJTBBJTBBbXlfY29uZmlnJTIwJTNEJTIwRGlzdGlsQmVydENvbmZpZy5mcm9tX3ByZXRyYWluZWQoJTIyLiUyRnlvdXJfbW9kZWxfc2F2ZV9wYXRoJTJGbXlfY29uZmlnLmpzb24lMjIpJTBBdGZfbW9kZWwlMjAlM0QlMjBURkRpc3RpbEJlcnRNb2RlbChteV9jb25maWcp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFDistilBertModel

	<span class="hljs-meta">>>> </span>my_config = DistilBertConfig.from_pretrained(<span class="hljs-string">"./your_model_save_path/my_config.json"</span>)
	<span class="hljs-meta">>>> </span>tf_model = TFDistilBertModel(my_config)`,wrap:!1}}),T=new q({props:{code:"dGZfbW9kZWwlMjAlM0QlMjBURkRpc3RpbEJlcnRNb2RlbC5mcm9tX3ByZXRyYWluZWQoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyKQ==",highlighted:'<span class="hljs-meta">>>> </span>tf_model = TFDistilBertModel.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)',wrap:!1}}),W=new q({props:{code:"dGZfbW9kZWwlMjAlM0QlMjBURkRpc3RpbEJlcnRNb2RlbC5mcm9tX3ByZXRyYWluZWQoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyJTJDJTIwY29uZmlnJTNEbXlfY29uZmlnKQ==",highlighted:'<span class="hljs-meta">>>> </span>tf_model = TFDistilBertModel.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>, config=my_config)',wrap:!1}}),{c(){a=f("p"),a.textContent=c,l=p(),d(o.$$.fragment),_=p(),M=f("p"),M.textContent=C,k=p(),v=f("p"),v.innerHTML=J,m=p(),d(T.$$.fragment),U=p(),R=f("p"),R.textContent=x,G=p(),d(W.$$.fragment)},l(r){a=u(r,"P",{"data-svelte-h":!0}),j(a)!=="svelte-1jf8wr"&&(a.textContent=c),l=i(r),g(o.$$.fragment,r),_=i(r),M=u(r,"P",{"data-svelte-h":!0}),j(M)!=="svelte-1x90d88"&&(M.textContent=C),k=i(r),v=u(r,"P",{"data-svelte-h":!0}),j(v)!=="svelte-6buo8p"&&(v.innerHTML=J),m=i(r),g(T.$$.fragment,r),U=i(r),R=u(r,"P",{"data-svelte-h":!0}),j(R)!=="svelte-yuz877"&&(R.textContent=x),G=i(r),g(W.$$.fragment,r)},m(r,Z){n(r,a,Z),n(r,l,Z),$(o,r,Z),n(r,_,Z),n(r,M,Z),n(r,k,Z),n(r,v,Z),n(r,m,Z),$(T,r,Z),n(r,U,Z),n(r,R,Z),n(r,G,Z),$(W,r,Z),V=!0},p:z,i(r){V\|\|(y(o.$$.fragment,r),y(T.$$.fragment,r),y(W.$$.fragment,r),V=!0)},o(r){h(o.$$.fragment,r),h(T.$$.fragment,r),h(W.$$.fragment,r),V=!1},d(r){r&&(e(a),e(l),e(_),e(M),e(k),e(v),e(m),e(U),e(R),e(G)),b(o,r),b(T,r),b(W,r)}}}function ke(w){let a,c;return a=new Hs({props:{$$slots:{default:[Je]},$$scope:{ctx:w}}}),{c(){d(a.$$.fragment)},l(l){g(a.$$.fragment,l)},m(l,o){$(a,l,o),c=!0},p(l,o){const _={};o&2&&(_.$$scope={dirty:o,ctx:l}),a.$set(_)},i(l){c\|\|(y(a.$$.fragment,l),c=!0)},o(l){h(a.$$.fragment,l),c=!1},d(l){b(a,l)}}}function Re(w){let a,c="예를 들어, <code>DistilBertForSequenceClassification</code>은 시퀀스 분류 헤드가 있는 기본 DistilBERT 모델입니다. 시퀀스 분류 헤드는 풀링된 출력 위에 있는 선형 레이어입니다.",l,o,_,M,C="다른 모델 헤드로 전환하여 이 체크포인트를 다른 작업에 쉽게 재사용할 수 있습니다. 질의응답 작업의 경우, <code>DistilBertForQuestionAnswering</code> 모델 헤드를 사용할 수 있습니다. 질의응답 헤드는 숨겨진 상태 출력 위에 선형 레이어가 있다는 점을 제외하면 시퀀스 분류 헤드와 유사합니다.",k,v,J;return o=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERpc3RpbEJlcnRGb3JTZXF1ZW5jZUNsYXNzaWZpY2F0aW9uJTBBJTBBbW9kZWwlMjAlM0QlMjBEaXN0aWxCZXJ0Rm9yU2VxdWVuY2VDbGFzc2lmaWNhdGlvbi5mcm9tX3ByZXRyYWluZWQoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistilBertForSequenceClassification

	<span class="hljs-meta">>>> </span>model = DistilBertForSequenceClassification.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),v=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERpc3RpbEJlcnRGb3JRdWVzdGlvbkFuc3dlcmluZyUwQSUwQW1vZGVsJTIwJTNEJTIwRGlzdGlsQmVydEZvclF1ZXN0aW9uQW5zd2VyaW5nLmZyb21fcHJldHJhaW5lZCglMjJkaXN0aWxiZXJ0JTJGZGlzdGlsYmVydC1iYXNlLXVuY2FzZWQlMjIp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistilBertForQuestionAnswering

	<span class="hljs-meta">>>> </span>model = DistilBertForQuestionAnswering.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),{c(){a=f("p"),a.innerHTML=c,l=p(),d(o.$$.fragment),_=p(),M=f("p"),M.innerHTML=C,k=p(),d(v.$$.fragment)},l(m){a=u(m,"P",{"data-svelte-h":!0}),j(a)!=="svelte-1d1i7tu"&&(a.innerHTML=c),l=i(m),g(o.$$.fragment,m),_=i(m),M=u(m,"P",{"data-svelte-h":!0}),j(M)!=="svelte-127ugzm"&&(M.innerHTML=C),k=i(m),g(v.$$.fragment,m)},m(m,T){n(m,a,T),n(m,l,T),$(o,m,T),n(m,_,T),n(m,M,T),n(m,k,T),$(v,m,T),J=!0},p:z,i(m){J\|\|(y(o.$$.fragment,m),y(v.$$.fragment,m),J=!0)},o(m){h(o.$$.fragment,m),h(v.$$.fragment,m),J=!1},d(m){m&&(e(a),e(l),e(_),e(M),e(k)),b(o,m),b(v,m)}}}function We(w){let a,c;return a=new Hs({props:{$$slots:{default:[Re]},$$scope:{ctx:w}}}),{c(){d(a.$$.fragment)},l(l){g(a.$$.fragment,l)},m(l,o){$(a,l,o),c=!0},p(l,o){const _={};o&2&&(_.$$scope={dirty:o,ctx:l}),a.$set(_)},i(l){c\|\|(y(a.$$.fragment,l),c=!0)},o(l){h(a.$$.fragment,l),c=!1},d(l){b(a,l)}}}function Ce(w){let a,c="예를 들어, <code>TFDistilBertForSequenceClassification</code>은 시퀀스 분류 헤드가 있는 기본 DistilBERT 모델입니다. 시퀀스 분류 헤드는 풀링된 출력 위에 있는 선형 레이어입니다.",l,o,_,M,C="다른 모델 헤드로 전환하여 이 체크포인트를 다른 작업에 쉽게 재사용할 수 있습니다. 질의응답 작업의 경우, <code>TFDistilBertForQuestionAnswering</code> 모델 헤드를 사용할 수 있습니다. 질의응답 헤드는 숨겨진 상태 출력 위에 선형 레이어가 있다는 점을 제외하면 시퀀스 분류 헤드와 유사합니다.",k,v,J;return o=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFRGRGlzdGlsQmVydEZvclNlcXVlbmNlQ2xhc3NpZmljYXRpb24lMEElMEF0Zl9tb2RlbCUyMCUzRCUyMFRGRGlzdGlsQmVydEZvclNlcXVlbmNlQ2xhc3NpZmljYXRpb24uZnJvbV9wcmV0cmFpbmVkKCUyMmRpc3RpbGJlcnQlMkZkaXN0aWxiZXJ0LWJhc2UtdW5jYXNlZCUyMik=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFDistilBertForSequenceClassification

	<span class="hljs-meta">>>> </span>tf_model = TFDistilBertForSequenceClassification.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),v=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFRGRGlzdGlsQmVydEZvclF1ZXN0aW9uQW5zd2VyaW5nJTBBJTBBdGZfbW9kZWwlMjAlM0QlMjBURkRpc3RpbEJlcnRGb3JRdWVzdGlvbkFuc3dlcmluZy5mcm9tX3ByZXRyYWluZWQoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFDistilBertForQuestionAnswering

	<span class="hljs-meta">>>> </span>tf_model = TFDistilBertForQuestionAnswering.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),{c(){a=f("p"),a.innerHTML=c,l=p(),d(o.$$.fragment),_=p(),M=f("p"),M.innerHTML=C,k=p(),d(v.$$.fragment)},l(m){a=u(m,"P",{"data-svelte-h":!0}),j(a)!=="svelte-io5rj8"&&(a.innerHTML=c),l=i(m),g(o.$$.fragment,m),_=i(m),M=u(m,"P",{"data-svelte-h":!0}),j(M)!=="svelte-87qals"&&(M.innerHTML=C),k=i(m),g(v.$$.fragment,m)},m(m,T){n(m,a,T),n(m,l,T),$(o,m,T),n(m,_,T),n(m,M,T),n(m,k,T),$(v,m,T),J=!0},p:z,i(m){J\|\|(y(o.$$.fragment,m),y(v.$$.fragment,m),J=!0)},o(m){h(o.$$.fragment,m),h(v.$$.fragment,m),J=!1},d(m){m&&(e(a),e(l),e(_),e(M),e(k)),b(o,m),b(v,m)}}}function Ue(w){let a,c;return a=new Hs({props:{$$slots:{default:[Ce]},$$scope:{ctx:w}}}),{c(){d(a.$$.fragment)},l(l){g(a.$$.fragment,l)},m(l,o){$(a,l,o),c=!0},p(l,o){const _={};o&2&&(_.$$scope={dirty:o,ctx:l}),a.$set(_)},i(l){c\|\|(y(a.$$.fragment,l),c=!0)},o(l){h(a.$$.fragment,l),c=!1},d(l){b(a,l)}}}function Ve(w){let a,c='모든 모델이 빠른 토크나이저를 지원하는 것은 아닙니다. 이 <a href="index#supported-frameworks">표</a>에서 모델의 빠른 토크나이저 지원 여부를 확인하세요.';return{c(){a=f("p"),a.innerHTML=c},l(l){a=u(l,"P",{"data-svelte-h":!0}),j(a)!=="svelte-w2xdht"&&(a.innerHTML=c)},m(l,o){n(l,a,o)},p:z,d(l){l&&e(a)}}}function xe(w){let a,c='<a href="/docs/transformers/pr_33913/ko/model_doc/auto#transformers.AutoTokenizer">AutoTokenizer</a>는 기본적으로 빠른 토크나이저를 가져오려고 합니다. 이 동작을 비활성화하려면 <code>from_pretrained</code>에서 <code>use_fast=False</code>를 설정하면 됩니다.';return{c(){a=f("p"),a.innerHTML=c},l(l){a=u(l,"P",{"data-svelte-h":!0}),j(a)!=="svelte-1a08cya"&&(a.innerHTML=c)},m(l,o){n(l,a,o)},p:z,d(l){l&&e(a)}}}function Ge(w){let a,c="사용자 지정을 원하지 않는 경우 <code>from_pretrained</code> 메소드를 사용하여 모델의 기본 이미지 프로세서 매개변수를 불러오면 됩니다.";return{c(){a=f("p"),a.innerHTML=c},l(l){a=u(l,"P",{"data-svelte-h":!0}),j(a)!=="svelte-f8vs2z"&&(a.innerHTML=c)},m(l,o){n(l,a,o)},p:z,d(l){l&&e(a)}}}function ze(w){let a,c="사용자 지정이 필요하지 않은 경우 <code>from_pretrained</code> 메소드를 사용하여 모델의 기본 특성 추출기 ㅁ개변수를 불러 오면 됩니다.";return{c(){a=f("p"),a.innerHTML=c},l(l){a=u(l,"P",{"data-svelte-h":!0}),j(a)!=="svelte-vnhffe"&&(a.innerHTML=c)},m(l,o){n(l,a,o)},p:z,d(l){l&&e(a)}}}function He(w){let a,c,l,o,_,M,C,k='<a href="model_doc/auto"><code>AutoClass</code></a>는 모델 아키텍처를 자동으로 추론하고 미리 학습된 configuration과 가중치를 다운로드합니다. 일반적으로 체크포인트에 구애받지 않는 코드를 생성하려면 <code>AutoClass</code>를 사용하는 것이 좋습니다. 하지만 특정 모델 파라미터를 보다 세밀하게 제어하고자 하는 사용자는 몇 가지 기본 클래스만으로 커스텀 🤗 Transformers 모델을 생성할 수 있습니다. 이는 🤗 Transformers 모델을 연구, 교육 또는 실험하는 데 관심이 있는 모든 사용자에게 특히 유용할 수 있습니다. 이 가이드에서는 ‘AutoClass’를 사용하지 않고 커스텀 모델을 만드는 방법에 대해 알아보겠습니다:',v,J,m="<li>모델 configuration을 가져오고 사용자 지정합니다.</li> <li>모델 아키텍처를 생성합니다.</li> <li>텍스트에 사용할 느리거나 빠른 토큰화기를 만듭니다.</li> <li>비전 작업을 위한 이미지 프로세서를 생성합니다.</li> <li>오디오 작업을 위한 특성 추출기를 생성합니다.</li> <li>멀티모달 작업용 프로세서를 생성합니다.</li>",T,U,R,x,G='<a href="main_classes/configuration">configuration</a>은 모델의 특정 속성을 나타냅니다. 각 모델 구성에는 서로 다른 속성이 있습니다. 예를 들어, 모든 NLP 모델에는 <code>hidden_size</code>, <code>num_attention_heads</code>, <code>num_hidden_layers</code> 및 <code>vocab_size</code> 속성이 공통으로 있습니다. 이러한 속성은 모델을 구성할 attention heads 또는 hidden layers의 수를 지정합니다.',W,V,r='<a href="model_doc/distilbert">DistilBERT</a> 속성을 검사하기 위해 <code>DistilBertConfig</code>에 접근하여 자세히 살펴봅니다:',Z,N,Ft,P,Fs="<code>DistilBertConfig</code>는 기본 <code>DistilBertModel</code>을 빌드하는 데 사용되는 모든 기본 속성을 표시합니다. 모든 속성은 커스터마이징이 가능하므로 실험을 위한 공간을 만들 수 있습니다. 예를 들어 기본 모델을 다음과 같이 커스터마이즈할 수 있습니다:",Xt,I,Xs="<li><code>activation</code> 파라미터로 다른 활성화 함수를 사용해 보세요.</li> <li><code>attention_dropout</code> 파라미터를 사용하여 어텐션 확률에 더 높은 드롭아웃 비율을 사용하세요.</li>",Bt,D,Et,S,Bs='사전 학습된 모델 속성은 <a href="/docs/transformers/pr_33913/ko/main_classes/configuration#transformers.PretrainedConfig.from_pretrained">from_pretrained()</a> 함수에서 수정할 수 있습니다:',Yt,A,Lt,K,Es='모델 구성이 만족스러우면 <a href="/docs/transformers/pr_33913/ko/main_classes/configuration#transformers.PretrainedConfig.save_pretrained">save_pretrained()</a>로 저장할 수 있습니다. 설정 파일은 지정된 작업 경로에 JSON 파일로 저장됩니다:',Qt,O,Nt,tt,Ys='configuration 파일을 재사용하려면 <a href="/docs/transformers/pr_33913/ko/main_classes/configuration#transformers.PretrainedConfig.from_pretrained">from_pretrained()</a>를 사용하여 가져오세요:',Pt,st,It,H,Dt,et,St,nt,Ls='다음 단계는 <a href="main_classes/models">모델(model)</a>을 만드는 것입니다. 느슨하게 아키텍처라고도 불리는 모델은 각 계층이 수행하는 동작과 발생하는 작업을 정의합니다. configuration의 <code>num_hidden_layers</code>와 같은 속성은 아키텍처를 정의하는 데 사용됩니다. 모든 모델은 기본 클래스 <a href="/docs/transformers/pr_33913/ko/main_classes/model#transformers.PreTrainedModel">PreTrainedModel</a>과 입력 임베딩 크기 조정 및 셀프 어텐션 헤드 가지 치기와 같은 몇 가지 일반적인 메소드를 공유합니다. 또한 모든 모델은 <a href="https://pytorch.org/docs/stable/generated/torch.nn.Module.html" rel="nofollow"><code>torch.nn.Module</code></a>, <a href="https://www.tensorflow.org/api_docs/python/tf/keras/Model" rel="nofollow"><code>tf.keras.Model</code></a> 또는 <a href="https://flax.readthedocs.io/en/latest/api_reference/flax.linen/module.html" rel="nofollow"><code>flax.linen.Module</code></a>의 서브클래스이기도 합니다. 즉, 모델은 각 프레임워크의 사용법과 호환됩니다.',At,F,Kt,at,Ot,lt,Qs="이 시점에서 <em>은닉 상태(hidden state)</em>를 출력하는 기본 DistilBERT 모델을 갖게 됩니다. 은닉 상태는 최종 출력을 생성하기 위해 모델 헤드에 입력으로 전달됩니다. 🤗 Transformers는 모델이 해당 작업을 지원하는 한 각 작업마다 다른 모델 헤드를 제공합니다(즉, 번역과 같은 시퀀스 간 작업에는 DistilBERT를 사용할 수 없음).",ts,X,ss,rt,es,pt,Ns='텍스트 데이터에 모델을 사용하기 전에 마지막으로 필요한 기본 클래스는 원시 텍스트를 텐서로 변환하는 <a href="main_classes/tokenizer">토크나이저</a>입니다. 🤗 Transformers에 사용할 수 있는 토크나이저는 두 가지 유형이 있습니다:',ns,it,Ps=`<li><code>PreTrainedTokenizer</code>: 파이썬으로 구현된 토크나이저입니다.</li> <li><code>PreTrainedTokenizerFast</code>: Rust 기반 <a href="https://huggingface.co/docs/tokenizers/python/latest/" rel="nofollow">🤗 Tokenizer</a> 라이브러리로 만들어진 토크나이저입니다. 이 토크나이저는 Rust로 구현되어 배치 토큰화에서 특히 빠릅니다. 빠른 토크나이저는 토큰을 원래 단어나 문자에 매핑하는 <em>오프셋 매핑</em>과 같은 추가 메소드도 제공합니다.
	두 토크나이저 모두 인코딩 및 디코딩, 새 토큰 추가, 특수 토큰 관리와 같은 일반적인 방법을 지원합니다.</li>`,as,B,ls,ot,Is="토크나이저를 직접 학습한 경우, <em>어휘(vocabulary)</em> 파일에서 토크나이저를 만들 수 있습니다:",rs,mt,ps,ct,Ds="사용자 지정 토크나이저의 어휘는 사전 학습된 모델의 토크나이저에서 생성된 어휘와 다를 수 있다는 점을 기억하는 것이 중요합니다. 사전 학습된 모델을 사용하는 경우 사전 학습된 모델의 어휘를 사용해야 하며, 그렇지 않으면 입력이 의미를 갖지 못합니다. <code>DistilBertTokenizer</code> 클래스를 사용하여 사전 학습된 모델의 어휘로 토크나이저를 생성합니다:",is,ft,os,ut,Ss="<code>DistilBertTokenizerFast</code> 클래스로 빠른 토크나이저를 생성합니다:",ms,dt,cs,E,fs,gt,us,$t,As='이미지 프로세서(image processor)는 비전 입력을 처리합니다. 기본 <a href="/docs/transformers/pr_33913/ko/internal/image_processing_utils#transformers.ImageProcessingMixin">ImageProcessingMixin</a> 클래스에서 상속합니다.',ds,yt,Ks='사용하려면 사용 중인 모델과 연결된 이미지 프로세서를 생성합니다. 예를 들어, 이미지 분류에 <a href="model_doc/vit">ViT</a>를 사용하는 경우 기본 <a href="/docs/transformers/pr_33913/ko/model_doc/vit#transformers.ViTImageProcessor">ViTImageProcessor</a>를 생성합니다:',gs,ht,$s,Y,ys,bt,Os='사용자 지정 이미지 프로세서를 생성하려면 <a href="/docs/transformers/pr_33913/ko/model_doc/vit#transformers.ViTImageProcessor">ViTImageProcessor</a> 파라미터를 수정합니다:',hs,jt,bs,_t,js,Mt,te='특성 추출기(feature extractor)는 오디오 입력을 처리합니다. 기본 <a href="/docs/transformers/pr_33913/ko/main_classes/feature_extractor#transformers.FeatureExtractionMixin">FeatureExtractionMixin</a> 클래스에서 상속되며, 오디오 입력을 처리하기 위해 <a href="/docs/transformers/pr_33913/ko/main_classes/feature_extractor#transformers.SequenceFeatureExtractor">SequenceFeatureExtractor</a> 클래스에서 상속할 수도 있습니다.',_s,vt,se='사용하려면 사용 중인 모델과 연결된 특성 추출기를 생성합니다. 예를 들어, 오디오 분류에 <a href="model_doc/wav2vec2">Wav2Vec2</a>를 사용하는 경우 기본 <code>Wav2Vec2FeatureExtractor</code>를 생성합니다:',Ms,Tt,vs,L,Ts,Zt,ee="사용자 지정 특성 추출기를 만들려면 <code>Wav2Vec2FeatureExtractor</code> 매개변수를 수정합니다:",Zs,wt,ws,qt,qs,Jt,ne="멀티모달 작업을 지원하는 모델의 경우, 🤗 Transformers는 특성 추출기 및 토크나이저와 같은 처리 클래스를 단일 객체로 편리하게 래핑하는 프로세서 클래스를 제공합니다. 예를 들어, 자동 음성 인식 작업(Automatic Speech Recognition task (ASR))에 <code>Wav2Vec2Processor</code>를 사용한다고 가정해 보겠습니다. 자동 음성 인식 작업은 오디오를 텍스트로 변환하므로 특성 추출기와 토크나이저가 필요합니다.",Js,kt,ae="오디오 입력을 처리할 특성 추출기를 만듭니다:",ks,Rt,Rs,Wt,le="텍스트 입력을 처리할 토크나이저를 만듭니다:",Ws,Ct,Cs,Ut,re="<code>Wav2Vec2Processor</code>에서 특성 추출기와 토크나이저를 결합합니다:",Us,Vt,Vs,xt,pe="configuration과 모델이라는 두 가지 기본 클래스와 추가 전처리 클래스(토크나이저, 이미지 프로세서, 특성 추출기 또는 프로세서)를 사용하면 🤗 Transformers에서 지원하는 모든 모델을 만들 수 있습니다. 이러한 각 기본 클래스는 구성이 가능하므로 원하는 특정 속성을 사용할 수 있습니다. 학습을 위해 모델을 쉽게 설정하거나 기존의 사전 학습된 모델을 수정하여 미세 조정할 수 있습니다.",xs,Gt,Gs,zt,zs;return _=new Q({props:{title:"맞춤형 아키텍처 만들기",local:"create-a-custom-architecture",headingTag:"h1"}}),U=new Q({props:{title:"Configuration",local:"configuration",headingTag:"h2"}}),N=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERpc3RpbEJlcnRDb25maWclMEElMEFjb25maWclMjAlM0QlMjBEaXN0aWxCZXJ0Q29uZmlnKCklMEFwcmludChjb25maWcp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistilBertConfig

	<span class="hljs-meta">>>> </span>config = DistilBertConfig()
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(config)
	DistilBertConfig {
	<span class="hljs-string">"activation"</span>: <span class="hljs-string">"gelu"</span>,
	<span class="hljs-string">"attention_dropout"</span>: <span class="hljs-number">0.1</span>,
	<span class="hljs-string">"dim"</span>: <span class="hljs-number">768</span>,
	<span class="hljs-string">"dropout"</span>: <span class="hljs-number">0.1</span>,
	<span class="hljs-string">"hidden_dim"</span>: <span class="hljs-number">3072</span>,
	<span class="hljs-string">"initializer_range"</span>: <span class="hljs-number">0.02</span>,
	<span class="hljs-string">"max_position_embeddings"</span>: <span class="hljs-number">512</span>,
	<span class="hljs-string">"model_type"</span>: <span class="hljs-string">"distilbert"</span>,
	<span class="hljs-string">"n_heads"</span>: <span class="hljs-number">12</span>,
	<span class="hljs-string">"n_layers"</span>: <span class="hljs-number">6</span>,
	<span class="hljs-string">"pad_token_id"</span>: <span class="hljs-number">0</span>,
	<span class="hljs-string">"qa_dropout"</span>: <span class="hljs-number">0.1</span>,
	<span class="hljs-string">"seq_classif_dropout"</span>: <span class="hljs-number">0.2</span>,
	<span class="hljs-string">"sinusoidal_pos_embds"</span>: false,
	<span class="hljs-string">"transformers_version"</span>: <span class="hljs-string">"4.16.2"</span>,
	<span class="hljs-string">"vocab_size"</span>: <span class="hljs-number">30522</span>
	}`,wrap:!1}}),D=new q({props:{code:"bXlfY29uZmlnJTIwJTNEJTIwRGlzdGlsQmVydENvbmZpZyhhY3RpdmF0aW9uJTNEJTIycmVsdSUyMiUyQyUyMGF0dGVudGlvbl9kcm9wb3V0JTNEMC40KSUwQXByaW50KG15X2NvbmZpZyk=",highlighted:`<span class="hljs-meta">>>> </span>my_config = DistilBertConfig(activation=<span class="hljs-string">"relu"</span>, attention_dropout=<span class="hljs-number">0.4</span>)
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(my_config)
	DistilBertConfig {
	<span class="hljs-string">"activation"</span>: <span class="hljs-string">"relu"</span>,
	<span class="hljs-string">"attention_dropout"</span>: <span class="hljs-number">0.4</span>,
	<span class="hljs-string">"dim"</span>: <span class="hljs-number">768</span>,
	<span class="hljs-string">"dropout"</span>: <span class="hljs-number">0.1</span>,
	<span class="hljs-string">"hidden_dim"</span>: <span class="hljs-number">3072</span>,
	<span class="hljs-string">"initializer_range"</span>: <span class="hljs-number">0.02</span>,
	<span class="hljs-string">"max_position_embeddings"</span>: <span class="hljs-number">512</span>,
	<span class="hljs-string">"model_type"</span>: <span class="hljs-string">"distilbert"</span>,
	<span class="hljs-string">"n_heads"</span>: <span class="hljs-number">12</span>,
	<span class="hljs-string">"n_layers"</span>: <span class="hljs-number">6</span>,
	<span class="hljs-string">"pad_token_id"</span>: <span class="hljs-number">0</span>,
	<span class="hljs-string">"qa_dropout"</span>: <span class="hljs-number">0.1</span>,
	<span class="hljs-string">"seq_classif_dropout"</span>: <span class="hljs-number">0.2</span>,
	<span class="hljs-string">"sinusoidal_pos_embds"</span>: false,
	<span class="hljs-string">"transformers_version"</span>: <span class="hljs-string">"4.16.2"</span>,
	<span class="hljs-string">"vocab_size"</span>: <span class="hljs-number">30522</span>
	}`,wrap:!1}}),A=new q({props:{code:"bXlfY29uZmlnJTIwJTNEJTIwRGlzdGlsQmVydENvbmZpZy5mcm9tX3ByZXRyYWluZWQoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyJTJDJTIwYWN0aXZhdGlvbiUzRCUyMnJlbHUlMjIlMkMlMjBhdHRlbnRpb25fZHJvcG91dCUzRDAuNCk=",highlighted:'<span class="hljs-meta">>>> </span>my_config = DistilBertConfig.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>, activation=<span class="hljs-string">"relu"</span>, attention_dropout=<span class="hljs-number">0.4</span>)',wrap:!1}}),O=new q({props:{code:"bXlfY29uZmlnLnNhdmVfcHJldHJhaW5lZChzYXZlX2RpcmVjdG9yeSUzRCUyMi4lMkZ5b3VyX21vZGVsX3NhdmVfcGF0aCUyMik=",highlighted:'<span class="hljs-meta">>>> </span>my_config.save_pretrained(save_directory=<span class="hljs-string">"./your_model_save_path"</span>)',wrap:!1}}),st=new q({props:{code:"bXlfY29uZmlnJTIwJTNEJTIwRGlzdGlsQmVydENvbmZpZy5mcm9tX3ByZXRyYWluZWQoJTIyLiUyRnlvdXJfbW9kZWxfc2F2ZV9wYXRoJTJGY29uZmlnLmpzb24lMjIp",highlighted:'<span class="hljs-meta">>>> </span>my_config = DistilBertConfig.from_pretrained(<span class="hljs-string">"./your_model_save_path/config.json"</span>)',wrap:!1}}),H=new Ht({props:{$$slots:{default:[Ze]},$$scope:{ctx:w}}}),et=new Q({props:{title:"모델",local:"model",headingTag:"h2"}}),F=new ye({props:{pytorch:!0,tensorflow:!0,jax:!1,$$slots:{tensorflow:[ke],pytorch:[qe]},$$scope:{ctx:w}}}),at=new Q({props:{title:"모델 헤드",local:"model-heads",headingTag:"h3"}}),X=new ye({props:{pytorch:!0,tensorflow:!0,jax:!1,$$slots:{tensorflow:[Ue],pytorch:[We]},$$scope:{ctx:w}}}),rt=new Q({props:{title:"토크나이저",local:"tokenizer",headingTag:"h2"}}),B=new Ht({props:{warning:!0,$$slots:{default:[Ve]},$$scope:{ctx:w}}}),mt=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERpc3RpbEJlcnRUb2tlbml6ZXIlMEElMEFteV90b2tlbml6ZXIlMjAlM0QlMjBEaXN0aWxCZXJ0VG9rZW5pemVyKHZvY2FiX2ZpbGUlM0QlMjJteV92b2NhYl9maWxlLnR4dCUyMiUyQyUyMGRvX2xvd2VyX2Nhc2UlM0RGYWxzZSUyQyUyMHBhZGRpbmdfc2lkZSUzRCUyMmxlZnQlMjIp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistilBertTokenizer

	<span class="hljs-meta">>>> </span>my_tokenizer = DistilBertTokenizer(vocab_file=<span class="hljs-string">"my_vocab_file.txt"</span>, do_lower_case=<span class="hljs-literal">False</span>, padding_side=<span class="hljs-string">"left"</span>)`,wrap:!1}}),ft=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERpc3RpbEJlcnRUb2tlbml6ZXIlMEElMEFzbG93X3Rva2VuaXplciUyMCUzRCUyMERpc3RpbEJlcnRUb2tlbml6ZXIuZnJvbV9wcmV0cmFpbmVkKCUyMmRpc3RpbGJlcnQlMkZkaXN0aWxiZXJ0LWJhc2UtdW5jYXNlZCUyMik=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistilBertTokenizer

	<span class="hljs-meta">>>> </span>slow_tokenizer = DistilBertTokenizer.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),dt=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERpc3RpbEJlcnRUb2tlbml6ZXJGYXN0JTBBJTBBZmFzdF90b2tlbml6ZXIlMjAlM0QlMjBEaXN0aWxCZXJ0VG9rZW5pemVyRmFzdC5mcm9tX3ByZXRyYWluZWQoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DistilBertTokenizerFast

	<span class="hljs-meta">>>> </span>fast_tokenizer = DistilBertTokenizerFast.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),E=new Ht({props:{$$slots:{default:[xe]},$$scope:{ctx:w}}}),gt=new Q({props:{title:"이미지 프로세서",local:"image-processor",headingTag:"h2"}}),ht=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFZpVEltYWdlUHJvY2Vzc29yJTBBJTBBdml0X2V4dHJhY3RvciUyMCUzRCUyMFZpVEltYWdlUHJvY2Vzc29yKCklMEFwcmludCh2aXRfZXh0cmFjdG9yKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> ViTImageProcessor

	<span class="hljs-meta">>>> </span>vit_extractor = ViTImageProcessor()
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(vit_extractor)
	ViTImageProcessor {
	<span class="hljs-string">"do_normalize"</span>: true,
	<span class="hljs-string">"do_resize"</span>: true,
	<span class="hljs-string">"feature_extractor_type"</span>: <span class="hljs-string">"ViTImageProcessor"</span>,
	<span class="hljs-string">"image_mean"</span>: [
	<span class="hljs-number">0.5</span>,
	<span class="hljs-number">0.5</span>,
	<span class="hljs-number">0.5</span>
	],
	<span class="hljs-string">"image_std"</span>: [
	<span class="hljs-number">0.5</span>,
	<span class="hljs-number">0.5</span>,
	<span class="hljs-number">0.5</span>
	],
	<span class="hljs-string">"resample"</span>: <span class="hljs-number">2</span>,
	<span class="hljs-string">"size"</span>: <span class="hljs-number">224</span>
	}`,wrap:!1}}),Y=new Ht({props:{$$slots:{default:[Ge]},$$scope:{ctx:w}}}),jt=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFZpVEltYWdlUHJvY2Vzc29yJTBBJTBBbXlfdml0X2V4dHJhY3RvciUyMCUzRCUyMFZpVEltYWdlUHJvY2Vzc29yKHJlc2FtcGxlJTNEJTIyUElMLkltYWdlLkJPWCUyMiUyQyUyMGRvX25vcm1hbGl6ZSUzREZhbHNlJTJDJTIwaW1hZ2VfbWVhbiUzRCU1QjAuMyUyQyUyMDAuMyUyQyUyMDAuMyU1RCklMEFwcmludChteV92aXRfZXh0cmFjdG9yKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> ViTImageProcessor

	<span class="hljs-meta">>>> </span>my_vit_extractor = ViTImageProcessor(resample=<span class="hljs-string">"PIL.Image.BOX"</span>, do_normalize=<span class="hljs-literal">False</span>, image_mean=[<span class="hljs-number">0.3</span>, <span class="hljs-number">0.3</span>, <span class="hljs-number">0.3</span>])
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(my_vit_extractor)
	ViTImageProcessor {
	<span class="hljs-string">"do_normalize"</span>: false,
	<span class="hljs-string">"do_resize"</span>: true,
	<span class="hljs-string">"feature_extractor_type"</span>: <span class="hljs-string">"ViTImageProcessor"</span>,
	<span class="hljs-string">"image_mean"</span>: [
	<span class="hljs-number">0.3</span>,
	<span class="hljs-number">0.3</span>,
	<span class="hljs-number">0.3</span>
	],
	<span class="hljs-string">"image_std"</span>: [
	<span class="hljs-number">0.5</span>,
	<span class="hljs-number">0.5</span>,
	<span class="hljs-number">0.5</span>
	],
	<span class="hljs-string">"resample"</span>: <span class="hljs-string">"PIL.Image.BOX"</span>,
	<span class="hljs-string">"size"</span>: <span class="hljs-number">224</span>
	}`,wrap:!1}}),_t=new Q({props:{title:"특성 추출기",local:"feature-extractor",headingTag:"h2"}}),Tt=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFdhdjJWZWMyRmVhdHVyZUV4dHJhY3RvciUwQSUwQXcydjJfZXh0cmFjdG9yJTIwJTNEJTIwV2F2MlZlYzJGZWF0dXJlRXh0cmFjdG9yKCklMEFwcmludCh3MnYyX2V4dHJhY3Rvcik=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> Wav2Vec2FeatureExtractor

	<span class="hljs-meta">>>> </span>w2v2_extractor = Wav2Vec2FeatureExtractor()
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(w2v2_extractor)
	Wav2Vec2FeatureExtractor {
	<span class="hljs-string">"do_normalize"</span>: true,
	<span class="hljs-string">"feature_extractor_type"</span>: <span class="hljs-string">"Wav2Vec2FeatureExtractor"</span>,
	<span class="hljs-string">"feature_size"</span>: <span class="hljs-number">1</span>,
	<span class="hljs-string">"padding_side"</span>: <span class="hljs-string">"right"</span>,
	<span class="hljs-string">"padding_value"</span>: <span class="hljs-number">0.0</span>,
	<span class="hljs-string">"return_attention_mask"</span>: false,
	<span class="hljs-string">"sampling_rate"</span>: <span class="hljs-number">16000</span>
	}`,wrap:!1}}),L=new Ht({props:{$$slots:{default:[ze]},$$scope:{ctx:w}}}),wt=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFdhdjJWZWMyRmVhdHVyZUV4dHJhY3RvciUwQSUwQXcydjJfZXh0cmFjdG9yJTIwJTNEJTIwV2F2MlZlYzJGZWF0dXJlRXh0cmFjdG9yKHNhbXBsaW5nX3JhdGUlM0Q4MDAwJTJDJTIwZG9fbm9ybWFsaXplJTNERmFsc2UpJTBBcHJpbnQodzJ2Ml9leHRyYWN0b3Ip",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> Wav2Vec2FeatureExtractor

	<span class="hljs-meta">>>> </span>w2v2_extractor = Wav2Vec2FeatureExtractor(sampling_rate=<span class="hljs-number">8000</span>, do_normalize=<span class="hljs-literal">False</span>)
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(w2v2_extractor)
	Wav2Vec2FeatureExtractor {
	<span class="hljs-string">"do_normalize"</span>: false,
	<span class="hljs-string">"feature_extractor_type"</span>: <span class="hljs-string">"Wav2Vec2FeatureExtractor"</span>,
	<span class="hljs-string">"feature_size"</span>: <span class="hljs-number">1</span>,
	<span class="hljs-string">"padding_side"</span>: <span class="hljs-string">"right"</span>,
	<span class="hljs-string">"padding_value"</span>: <span class="hljs-number">0.0</span>,
	<span class="hljs-string">"return_attention_mask"</span>: false,
	<span class="hljs-string">"sampling_rate"</span>: <span class="hljs-number">8000</span>
	}`,wrap:!1}}),qt=new Q({props:{title:"프로세서",local:"processor",headingTag:"h2"}}),Rt=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFdhdjJWZWMyRmVhdHVyZUV4dHJhY3RvciUwQSUwQWZlYXR1cmVfZXh0cmFjdG9yJTIwJTNEJTIwV2F2MlZlYzJGZWF0dXJlRXh0cmFjdG9yKHBhZGRpbmdfdmFsdWUlM0QxLjAlMkMlMjBkb19ub3JtYWxpemUlM0RUcnVlKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> Wav2Vec2FeatureExtractor

	<span class="hljs-meta">>>> </span>feature_extractor = Wav2Vec2FeatureExtractor(padding_value=<span class="hljs-number">1.0</span>, do_normalize=<span class="hljs-literal">True</span>)`,wrap:!1}}),Ct=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFdhdjJWZWMyQ1RDVG9rZW5pemVyJTBBJTBBdG9rZW5pemVyJTIwJTNEJTIwV2F2MlZlYzJDVENUb2tlbml6ZXIodm9jYWJfZmlsZSUzRCUyMm15X3ZvY2FiX2ZpbGUudHh0JTIyKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> Wav2Vec2CTCTokenizer

	<span class="hljs-meta">>>> </span>tokenizer = Wav2Vec2CTCTokenizer(vocab_file=<span class="hljs-string">"my_vocab_file.txt"</span>)`,wrap:!1}}),Vt=new q({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFdhdjJWZWMyUHJvY2Vzc29yJTBBJTBBcHJvY2Vzc29yJTIwJTNEJTIwV2F2MlZlYzJQcm9jZXNzb3IoZmVhdHVyZV9leHRyYWN0b3IlM0RmZWF0dXJlX2V4dHJhY3RvciUyQyUyMHRva2VuaXplciUzRHRva2VuaXplcik=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> Wav2Vec2Processor

	<span class="hljs-meta">>>> </span>processor = Wav2Vec2Processor(feature_extractor=feature_extractor, tokenizer=tokenizer)`,wrap:!1}}),Gt=new Te({props:{source:"https://github.com/huggingface/transformers/blob/main/docs/source/ko/create_a_model.md"}}),{c(){a=f("meta"),c=p(),l=f("p"),o=p(),d(_.$$.fragment),M=p(),C=f("p"),C.innerHTML=k,v=p(),J=f("ul"),J.innerHTML=m,T=p(),d(U.$$.fragment),R=p(),x=f("p"),x.innerHTML=G,W=p(),V=f("p"),V.innerHTML=r,Z=p(),d(N.$$.fragment),Ft=p(),P=f("p"),P.innerHTML=Fs,Xt=p(),I=f("ul"),I.innerHTML=Xs,Bt=p(),d(D.$$.fragment),Et=p(),S=f("p"),S.innerHTML=Bs,Yt=p(),d(A.$$.fragment),Lt=p(),K=f("p"),K.innerHTML=Es,Qt=p(),d(O.$$.fragment),Nt=p(),tt=f("p"),tt.innerHTML=Ys,Pt=p(),d(st.$$.fragment),It=p(),d(H.$$.fragment),Dt=p(),d(et.$$.fragment),St=p(),nt=f("p"),nt.innerHTML=Ls,At=p(),d(F.$$.fragment),Kt=p(),d(at.$$.fragment),Ot=p(),lt=f("p"),lt.innerHTML=Qs,ts=p(),d(X.$$.fragment),ss=p(),d(rt.$$.fragment),es=p(),pt=f("p"),pt.innerHTML=Ns,ns=p(),it=f("ul"),it.innerHTML=Ps,as=p(),d(B.$$.fragment),ls=p(),ot=f("p"),ot.innerHTML=Is,rs=p(),d(mt.$$.fragment),ps=p(),ct=f("p"),ct.innerHTML=Ds,is=p(),d(ft.$$.fragment),os=p(),ut=f("p"),ut.innerHTML=Ss,ms=p(),d(dt.$$.fragment),cs=p(),d(E.$$.fragment),fs=p(),d(gt.$$.fragment),us=p(),$t=f("p"),$t.innerHTML=As,ds=p(),yt=f("p"),yt.innerHTML=Ks,gs=p(),d(ht.$$.fragment),$s=p(),d(Y.$$.fragment),ys=p(),bt=f("p"),bt.innerHTML=Os,hs=p(),d(jt.$$.fragment),bs=p(),d(_t.$$.fragment),js=p(),Mt=f("p"),Mt.innerHTML=te,_s=p(),vt=f("p"),vt.innerHTML=se,Ms=p(),d(Tt.$$.fragment),vs=p(),d(L.$$.fragment),Ts=p(),Zt=f("p"),Zt.innerHTML=ee,Zs=p(),d(wt.$$.fragment),ws=p(),d(qt.$$.fragment),qs=p(),Jt=f("p"),Jt.innerHTML=ne,Js=p(),kt=f("p"),kt.textContent=ae,ks=p(),d(Rt.$$.fragment),Rs=p(),Wt=f("p"),Wt.textContent=le,Ws=p(),d(Ct.$$.fragment),Cs=p(),Ut=f("p"),Ut.innerHTML=re,Us=p(),d(Vt.$$.fragment),Vs=p(),xt=f("p"),xt.textContent=pe,xs=p(),d(Gt.$$.fragment),Gs=p(),zt=f("p"),this.h()},l(t){const s=Me("svelte-u9bgzb",document.head);a=u(s,"META",{name:!0,content:!0}),s.forEach(e),c=i(t),l=u(t,"P",{}),ge(l).forEach(e),o=i(t),g(_.$$.fragment,t),M=i(t),C=u(t,"P",{"data-svelte-h":!0}),j(C)!=="svelte-19ve0b1"&&(C.innerHTML=k),v=i(t),J=u(t,"UL",{"data-svelte-h":!0}),j(J)!=="svelte-1ebb2km"&&(J.innerHTML=m),T=i(t),g(U.$$.fragment,t),R=i(t),x=u(t,"P",{"data-svelte-h":!0}),j(x)!=="svelte-1u7e78i"&&(x.innerHTML=G),W=i(t),V=u(t,"P",{"data-svelte-h":!0}),j(V)!=="svelte-1ujadwn"&&(V.innerHTML=r),Z=i(t),g(N.$$.fragment,t),Ft=i(t),P=u(t,"P",{"data-svelte-h":!0}),j(P)!=="svelte-ipet8t"&&(P.innerHTML=Fs),Xt=i(t),I=u(t,"UL",{"data-svelte-h":!0}),j(I)!=="svelte-oc0ep3"&&(I.innerHTML=Xs),Bt=i(t),g(D.$$.fragment,t),Et=i(t),S=u(t,"P",{"data-svelte-h":!0}),j(S)!=="svelte-1m7d7zc"&&(S.innerHTML=Bs),Yt=i(t),g(A.$$.fragment,t),Lt=i(t),K=u(t,"P",{"data-svelte-h":!0}),j(K)!=="svelte-3v59w9"&&(K.innerHTML=Es),Qt=i(t),g(O.$$.fragment,t),Nt=i(t),tt=u(t,"P",{"data-svelte-h":!0}),j(tt)!=="svelte-tzonpy"&&(tt.innerHTML=Ys),Pt=i(t),g(st.$$.fragment,t),It=i(t),g(H.$$.fragment,t),Dt=i(t),g(et.$$.fragment,t),St=i(t),nt=u(t,"P",{"data-svelte-h":!0}),j(nt)!=="svelte-1jdh3j7"&&(nt.innerHTML=Ls),At=i(t),g(F.$$.fragment,t),Kt=i(t),g(at.$$.fragment,t),Ot=i(t),lt=u(t,"P",{"data-svelte-h":!0}),j(lt)!=="svelte-x49xse"&&(lt.innerHTML=Qs),ts=i(t),g(X.$$.fragment,t),ss=i(t),g(rt.$$.fragment,t),es=i(t),pt=u(t,"P",{"data-svelte-h":!0}),j(pt)!=="svelte-tr0od4"&&(pt.innerHTML=Ns),ns=i(t),it=u(t,"UL",{"data-svelte-h":!0}),j(it)!=="svelte-1s73745"&&(it.innerHTML=Ps),as=i(t),g(B.$$.fragment,t),ls=i(t),ot=u(t,"P",{"data-svelte-h":!0}),j(ot)!=="svelte-1ydtv7o"&&(ot.innerHTML=Is),rs=i(t),g(mt.$$.fragment,t),ps=i(t),ct=u(t,"P",{"data-svelte-h":!0}),j(ct)!=="svelte-hd5xug"&&(ct.innerHTML=Ds),is=i(t),g(ft.$$.fragment,t),os=i(t),ut=u(t,"P",{"data-svelte-h":!0}),j(ut)!=="svelte-1vv93q7"&&(ut.innerHTML=Ss),ms=i(t),g(dt.$$.fragment,t),cs=i(t),g(E.$$.fragment,t),fs=i(t),g(gt.$$.fragment,t),us=i(t),$t=u(t,"P",{"data-svelte-h":!0}),j($t)!=="svelte-19907x1"&&($t.innerHTML=As),ds=i(t),yt=u(t,"P",{"data-svelte-h":!0}),j(yt)!=="svelte-cybtfj"&&(yt.innerHTML=Ks),gs=i(t),g(ht.$$.fragment,t),$s=i(t),g(Y.$$.fragment,t),ys=i(t),bt=u(t,"P",{"data-svelte-h":!0}),j(bt)!=="svelte-1tl7m22"&&(bt.innerHTML=Os),hs=i(t),g(jt.$$.fragment,t),bs=i(t),g(_t.$$.fragment,t),js=i(t),Mt=u(t,"P",{"data-svelte-h":!0}),j(Mt)!=="svelte-6vjfx9"&&(Mt.innerHTML=te),_s=i(t),vt=u(t,"P",{"data-svelte-h":!0}),j(vt)!=="svelte-mindlu"&&(vt.innerHTML=se),Ms=i(t),g(Tt.$$.fragment,t),vs=i(t),g(L.$$.fragment,t),Ts=i(t),Zt=u(t,"P",{"data-svelte-h":!0}),j(Zt)!=="svelte-1hh3a05"&&(Zt.innerHTML=ee),Zs=i(t),g(wt.$$.fragment,t),ws=i(t),g(qt.$$.fragment,t),qs=i(t),Jt=u(t,"P",{"data-svelte-h":!0}),j(Jt)!=="svelte-m80yeb"&&(Jt.innerHTML=ne),Js=i(t),kt=u(t,"P",{"data-svelte-h":!0}),j(kt)!=="svelte-rxz7k7"&&(kt.textContent=ae),ks=i(t),g(Rt.$$.fragment,t),Rs=i(t),Wt=u(t,"P",{"data-svelte-h":!0}),j(Wt)!=="svelte-1pis3oo"&&(Wt.textContent=le),Ws=i(t),g(Ct.$$.fragment,t),Cs=i(t),Ut=u(t,"P",{"data-svelte-h":!0}),j(Ut)!=="svelte-1ou4ndv"&&(Ut.innerHTML=re),Us=i(t),g(Vt.$$.fragment,t),Vs=i(t),xt=u(t,"P",{"data-svelte-h":!0}),j(xt)!=="svelte-wnze"&&(xt.textContent=pe),xs=i(t),g(Gt.$$.fragment,t),Gs=i(t),zt=u(t,"P",{}),ge(zt).forEach(e),this.h()},h(){$e(a,"name","hf:doc:metadata"),$e(a,"content",Fe)},m(t,s){ve(document.head,a),n(t,c,s),n(t,l,s),n(t,o,s),$(_,t,s),n(t,M,s),n(t,C,s),n(t,v,s),n(t,J,s),n(t,T,s),$(U,t,s),n(t,R,s),n(t,x,s),n(t,W,s),n(t,V,s),n(t,Z,s),$(N,t,s),n(t,Ft,s),n(t,P,s),n(t,Xt,s),n(t,I,s),n(t,Bt,s),$(D,t,s),n(t,Et,s),n(t,S,s),n(t,Yt,s),$(A,t,s),n(t,Lt,s),n(t,K,s),n(t,Qt,s),$(O,t,s),n(t,Nt,s),n(t,tt,s),n(t,Pt,s),$(st,t,s),n(t,It,s),$(H,t,s),n(t,Dt,s),$(et,t,s),n(t,St,s),n(t,nt,s),n(t,At,s),$(F,t,s),n(t,Kt,s),$(at,t,s),n(t,Ot,s),n(t,lt,s),n(t,ts,s),$(X,t,s),n(t,ss,s),$(rt,t,s),n(t,es,s),n(t,pt,s),n(t,ns,s),n(t,it,s),n(t,as,s),$(B,t,s),n(t,ls,s),n(t,ot,s),n(t,rs,s),$(mt,t,s),n(t,ps,s),n(t,ct,s),n(t,is,s),$(ft,t,s),n(t,os,s),n(t,ut,s),n(t,ms,s),$(dt,t,s),n(t,cs,s),$(E,t,s),n(t,fs,s),$(gt,t,s),n(t,us,s),n(t,$t,s),n(t,ds,s),n(t,yt,s),n(t,gs,s),$(ht,t,s),n(t,$s,s),$(Y,t,s),n(t,ys,s),n(t,bt,s),n(t,hs,s),$(jt,t,s),n(t,bs,s),$(_t,t,s),n(t,js,s),n(t,Mt,s),n(t,_s,s),n(t,vt,s),n(t,Ms,s),$(Tt,t,s),n(t,vs,s),$(L,t,s),n(t,Ts,s),n(t,Zt,s),n(t,Zs,s),$(wt,t,s),n(t,ws,s),$(qt,t,s),n(t,qs,s),n(t,Jt,s),n(t,Js,s),n(t,kt,s),n(t,ks,s),$(Rt,t,s),n(t,Rs,s),n(t,Wt,s),n(t,Ws,s),$(Ct,t,s),n(t,Cs,s),n(t,Ut,s),n(t,Us,s),$(Vt,t,s),n(t,Vs,s),n(t,xt,s),n(t,xs,s),$(Gt,t,s),n(t,Gs,s),n(t,zt,s),zs=!0},p(t,[s]){const ie={};s&2&&(ie.$$scope={dirty:s,ctx:t}),H.$set(ie);const oe={};s&2&&(oe.$$scope={dirty:s,ctx:t}),F.$set(oe);const me={};s&2&&(me.$$scope={dirty:s,ctx:t}),X.$set(me);const ce={};s&2&&(ce.$$scope={dirty:s,ctx:t}),B.$set(ce);const fe={};s&2&&(fe.$$scope={dirty:s,ctx:t}),E.$set(fe);const ue={};s&2&&(ue.$$scope={dirty:s,ctx:t}),Y.$set(ue);const de={};s&2&&(de.$$scope={dirty:s,ctx:t}),L.$set(de)},i(t){zs\|\|(y(_.$$.fragment,t),y(U.$$.fragment,t),y(N.$$.fragment,t),y(D.$$.fragment,t),y(A.$$.fragment,t),y(O.$$.fragment,t),y(st.$$.fragment,t),y(H.$$.fragment,t),y(et.$$.fragment,t),y(F.$$.fragment,t),y(at.$$.fragment,t),y(X.$$.fragment,t),y(rt.$$.fragment,t),y(B.$$.fragment,t),y(mt.$$.fragment,t),y(ft.$$.fragment,t),y(dt.$$.fragment,t),y(E.$$.fragment,t),y(gt.$$.fragment,t),y(ht.$$.fragment,t),y(Y.$$.fragment,t),y(jt.$$.fragment,t),y(_t.$$.fragment,t),y(Tt.$$.fragment,t),y(L.$$.fragment,t),y(wt.$$.fragment,t),y(qt.$$.fragment,t),y(Rt.$$.fragment,t),y(Ct.$$.fragment,t),y(Vt.$$.fragment,t),y(Gt.$$.fragment,t),zs=!0)},o(t){h(_.$$.fragment,t),h(U.$$.fragment,t),h(N.$$.fragment,t),h(D.$$.fragment,t),h(A.$$.fragment,t),h(O.$$.fragment,t),h(st.$$.fragment,t),h(H.$$.fragment,t),h(et.$$.fragment,t),h(F.$$.fragment,t),h(at.$$.fragment,t),h(X.$$.fragment,t),h(rt.$$.fragment,t),h(B.$$.fragment,t),h(mt.$$.fragment,t),h(ft.$$.fragment,t),h(dt.$$.fragment,t),h(E.$$.fragment,t),h(gt.$$.fragment,t),h(ht.$$.fragment,t),h(Y.$$.fragment,t),h(jt.$$.fragment,t),h(_t.$$.fragment,t),h(Tt.$$.fragment,t),h(L.$$.fragment,t),h(wt.$$.fragment,t),h(qt.$$.fragment,t),h(Rt.$$.fragment,t),h(Ct.$$.fragment,t),h(Vt.$$.fragment,t),h(Gt.$$.fragment,t),zs=!1},d(t){t&&(e(c),e(l),e(o),e(M),e(C),e(v),e(J),e(T),e(R),e(x),e(W),e(V),e(Z),e(Ft),e(P),e(Xt),e(I),e(Bt),e(Et),e(S),e(Yt),e(Lt),e(K),e(Qt),e(Nt),e(tt),e(Pt),e(It),e(Dt),e(St),e(nt),e(At),e(Kt),e(Ot),e(lt),e(ts),e(ss),e(es),e(pt),e(ns),e(it),e(as),e(ls),e(ot),e(rs),e(ps),e(ct),e(is),e(os),e(ut),e(ms),e(cs),e(fs),e(us),e($t),e(ds),e(yt),e(gs),e($s),e(ys),e(bt),e(hs),e(bs),e(js),e(Mt),e(_s),e(vt),e(Ms),e(vs),e(Ts),e(Zt),e(Zs),e(ws),e(qs),e(Jt),e(Js),e(kt),e(ks),e(Rs),e(Wt),e(Ws),e(Cs),e(Ut),e(Us),e(Vs),e(xt),e(xs),e(Gs),e(zt)),e(a),b(_,t),b(U,t),b(N,t),b(D,t),b(A,t),b(O,t),b(st,t),b(H,t),b(et,t),b(F,t),b(at,t),b(X,t),b(rt,t),b(B,t),b(mt,t),b(ft,t),b(dt,t),b(E,t),b(gt,t),b(ht,t),b(Y,t),b(jt,t),b(_t,t),b(Tt,t),b(L,t),b(wt,t),b(qt,t),b(Rt,t),b(Ct,t),b(Vt,t),b(Gt,t)}}}const Fe='{"title":"맞춤형 아키텍처 만들기","local":"create-a-custom-architecture","sections":[{"title":"Configuration","local":"configuration","sections":[],"depth":2},{"title":"모델","local":"model","sections":[{"title":"모델 헤드","local":"model-heads","sections":[],"depth":3}],"depth":2},{"title":"토크나이저","local":"tokenizer","sections":[],"depth":2},{"title":"이미지 프로세서","local":"image-processor","sections":[],"depth":2},{"title":"특성 추출기","local":"feature-extractor","sections":[],"depth":2},{"title":"프로세서","local":"processor","sections":[],"depth":2}],"depth":1}';function Xe(w){return be(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Pe extends je{constructor(a){super(),_e(this,a,Xe,He,he,{})}}export{Pe as component};

Xet Storage Details

Size:: 51.1 kB
Xet hash:: bdc291d0465ef09749a275a258507e2d6c88b08958c719e8e367ce9e0dee6f16

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