Buckets:
| import{s as Q,n as I,o as K}from"../chunks/scheduler.37c15a92.js";import{S as V,i as W,g as r,s as n,r as B,A as X,h as i,f as a,c as o,j as J,u as z,x as b,k as O,y as Z,a as l,v as A,d as j,t as S,w as U}from"../chunks/index.7cb9c9b8.js";import{Y as tt}from"../chunks/Youtube.8666c400.js";import{C as et}from"../chunks/CourseFloatingBanner.df82c153.js";import{H as at,E as lt}from"../chunks/getInferenceSnippets.a2135f3c.js";function nt(k){let s,x,d,w,m,C,f,E,p,T,u,N="エンコーダーモデルとは、Transformerモデルのエンコーダーのみを使用したモデルを指します。 処理の各段階で、attention層は最初の文の全ての単語にアクセスすることができます。 これらのモデルは “bi-directional”(双方向)のattentionを持つものとして特徴付けられ、<em>オートエンコーダーモデル</em>と呼ばれます。",P,c,Y="これらのモデルの事前学習は、何らかの方法で(例えば文中の単語をランダムにマスクするなどで)文を壊し、この文の再構築をタスクとして解くことを中心に展開されます。",L,h,D="エンコーダーモデルは、文の分類 ・ 固有表現認識(より一般的には単語の分類) ・ 抽出的質問応答など、文全体の理解を必要とするタスクに最も適しています。",M,$,F="エンコーダーモデルでは以下のものが代表的です:",R,_,G='<li><a href="https://huggingface.co/transformers/model_doc/albert.html" rel="nofollow">ALBERT</a></li> <li><a href="https://huggingface.co/transformers/model_doc/bert.html" rel="nofollow">BERT</a></li> <li><a href="https://huggingface.co/transformers/model_doc/distilbert.html" rel="nofollow">DistilBERT</a></li> <li><a href="https://huggingface.co/transformers/model_doc/electra.html" rel="nofollow">ELECTRA</a></li> <li><a href="https://huggingface.co/transformers/model_doc/roberta.html" rel="nofollow">RoBERTa</a></li>',y,g,H,v,q;return m=new at({props:{title:"エンコーダーモデル",local:"エンコーダーモデル",headingTag:"h1"}}),f=new et({props:{chapter:1,classNames:"absolute z-10 right-0 top-0"}}),p=new tt({props:{id:"MUqNwgPjJvQ"}}),g=new lt({props:{source:"https://github.com/huggingface/course/blob/main/chapters/ja/chapter1/5.mdx"}}),{c(){s=r("meta"),x=n(),d=r("p"),w=n(),B(m.$$.fragment),C=n(),B(f.$$.fragment),E=n(),B(p.$$.fragment),T=n(),u=r("p"),u.innerHTML=N,P=n(),c=r("p"),c.textContent=Y,L=n(),h=r("p"),h.textContent=D,M=n(),$=r("p"),$.textContent=F,R=n(),_=r("ul"),_.innerHTML=G,y=n(),B(g.$$.fragment),H=n(),v=r("p"),this.h()},l(t){const e=X("svelte-u9bgzb",document.head);s=i(e,"META",{name:!0,content:!0}),e.forEach(a),x=o(t),d=i(t,"P",{}),J(d).forEach(a),w=o(t),z(m.$$.fragment,t),C=o(t),z(f.$$.fragment,t),E=o(t),z(p.$$.fragment,t),T=o(t),u=i(t,"P",{"data-svelte-h":!0}),b(u)!=="svelte-8po7a1"&&(u.innerHTML=N),P=o(t),c=i(t,"P",{"data-svelte-h":!0}),b(c)!=="svelte-q93tvn"&&(c.textContent=Y),L=o(t),h=i(t,"P",{"data-svelte-h":!0}),b(h)!=="svelte-y4qvu8"&&(h.textContent=D),M=o(t),$=i(t,"P",{"data-svelte-h":!0}),b($)!=="svelte-62qi47"&&($.textContent=F),R=o(t),_=i(t,"UL",{"data-svelte-h":!0}),b(_)!=="svelte-18kzzol"&&(_.innerHTML=G),y=o(t),z(g.$$.fragment,t),H=o(t),v=i(t,"P",{}),J(v).forEach(a),this.h()},h(){O(s,"name","hf:doc:metadata"),O(s,"content",ot)},m(t,e){Z(document.head,s),l(t,x,e),l(t,d,e),l(t,w,e),A(m,t,e),l(t,C,e),A(f,t,e),l(t,E,e),A(p,t,e),l(t,T,e),l(t,u,e),l(t,P,e),l(t,c,e),l(t,L,e),l(t,h,e),l(t,M,e),l(t,$,e),l(t,R,e),l(t,_,e),l(t,y,e),A(g,t,e),l(t,H,e),l(t,v,e),q=!0},p:I,i(t){q||(j(m.$$.fragment,t),j(f.$$.fragment,t),j(p.$$.fragment,t),j(g.$$.fragment,t),q=!0)},o(t){S(m.$$.fragment,t),S(f.$$.fragment,t),S(p.$$.fragment,t),S(g.$$.fragment,t),q=!1},d(t){t&&(a(x),a(d),a(w),a(C),a(E),a(T),a(u),a(P),a(c),a(L),a(h),a(M),a($),a(R),a(_),a(y),a(H),a(v)),a(s),U(m,t),U(f,t),U(p,t),U(g,t)}}}const ot='{"title":"エンコーダーモデル","local":"エンコーダーモデル","sections":[],"depth":1}';function st(k){return K(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ut extends V{constructor(s){super(),W(this,s,st,nt,Q,{})}}export{ut as component}; | |
Xet Storage Details
- Size:
- 4.2 kB
- Xet hash:
- 118633c247b79891e0832c84ae9d1f118a6e403035d064c8aa584afcbddaa65f
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.