Buckets:
| import{s as K,n as V,o as W}from"../chunks/scheduler.505acc25.js";import{S as X,i as Z,e as r,s,c as b,h as ee,a as i,d as a,b as n,f as Q,g as C,j as w,k as I,l as te,m as o,n as E,t as T,o as M,p as P}from"../chunks/index.1238bded.js";import{C as ae,H as oe,E as se}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.18853757.js";import{Y as ne}from"../chunks/Youtube.2fb63721.js";import{C as le}from"../chunks/CourseFloatingBanner.2e302d0f.js";function re(N){let l,L,x,y,m,R,f,q,d,z,c,H,p,Y="Os modelos de encoder (codificadores) usam apenas o encoder de um modelo Transformer. Em cada estágio, as camadas de atenção podem acessar todas as palavras da frase inicial. Esses modelos geralmente são caracterizados como tendo atenção “bidirecional” e são frequentemente chamados de <em>modelos de codificação automática</em>.",B,u,D="O pré-treinamento desses modelos geralmente gira em torno de corromper de alguma forma uma determinada frase (por exemplo, mascarando palavras aleatórias nela) e encarregando o modelo de encontrar ou reconstruir a frase inicial.",O,$,F="Os modelos de codificador são mais adequados para tarefas que exigem uma compreensão da sentença completa, como classificação de sentença, reconhecimento de entidade nomeada (e, mais geralmente, classificação de palavras) e resposta extrativa de perguntas.",j,g,G="Os representantes desta família de modelos incluem:",S,h,J='<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>',A,_,U,v,k;return m=new ae({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),f=new oe({props:{title:"Modelos codificadores",local:"modelos-codificadores",headingTag:"h1"}}),d=new le({props:{chapter:1,classNames:"absolute z-10 right-0 top-0"}}),c=new ne({props:{id:"MUqNwgPjJvQ"}}),_=new se({props:{source:"https://github.com/huggingface/course/blob/main/chapters/pt/chapter1/5.mdx"}}),{c(){l=r("meta"),L=s(),x=r("p"),y=s(),b(m.$$.fragment),R=s(),b(f.$$.fragment),q=s(),b(d.$$.fragment),z=s(),b(c.$$.fragment),H=s(),p=r("p"),p.innerHTML=Y,B=s(),u=r("p"),u.textContent=D,O=s(),$=r("p"),$.textContent=F,j=s(),g=r("p"),g.textContent=G,S=s(),h=r("ul"),h.innerHTML=J,A=s(),b(_.$$.fragment),U=s(),v=r("p"),this.h()},l(e){const t=ee("svelte-u9bgzb",document.head);l=i(t,"META",{name:!0,content:!0}),t.forEach(a),L=n(e),x=i(e,"P",{}),Q(x).forEach(a),y=n(e),C(m.$$.fragment,e),R=n(e),C(f.$$.fragment,e),q=n(e),C(d.$$.fragment,e),z=n(e),C(c.$$.fragment,e),H=n(e),p=i(e,"P",{"data-svelte-h":!0}),w(p)!=="svelte-qj02cj"&&(p.innerHTML=Y),B=n(e),u=i(e,"P",{"data-svelte-h":!0}),w(u)!=="svelte-9pg3ea"&&(u.textContent=D),O=n(e),$=i(e,"P",{"data-svelte-h":!0}),w($)!=="svelte-9o6rgt"&&($.textContent=F),j=n(e),g=i(e,"P",{"data-svelte-h":!0}),w(g)!=="svelte-1x0lt16"&&(g.textContent=G),S=n(e),h=i(e,"UL",{"data-svelte-h":!0}),w(h)!=="svelte-18kzzol"&&(h.innerHTML=J),A=n(e),C(_.$$.fragment,e),U=n(e),v=i(e,"P",{}),Q(v).forEach(a),this.h()},h(){I(l,"name","hf:doc:metadata"),I(l,"content",ie)},m(e,t){te(document.head,l),o(e,L,t),o(e,x,t),o(e,y,t),E(m,e,t),o(e,R,t),E(f,e,t),o(e,q,t),E(d,e,t),o(e,z,t),E(c,e,t),o(e,H,t),o(e,p,t),o(e,B,t),o(e,u,t),o(e,O,t),o(e,$,t),o(e,j,t),o(e,g,t),o(e,S,t),o(e,h,t),o(e,A,t),E(_,e,t),o(e,U,t),o(e,v,t),k=!0},p:V,i(e){k||(T(m.$$.fragment,e),T(f.$$.fragment,e),T(d.$$.fragment,e),T(c.$$.fragment,e),T(_.$$.fragment,e),k=!0)},o(e){M(m.$$.fragment,e),M(f.$$.fragment,e),M(d.$$.fragment,e),M(c.$$.fragment,e),M(_.$$.fragment,e),k=!1},d(e){e&&(a(L),a(x),a(y),a(R),a(q),a(z),a(H),a(p),a(B),a(u),a(O),a($),a(j),a(g),a(S),a(h),a(A),a(U),a(v)),a(l),P(m,e),P(f,e),P(d,e),P(c,e),P(_,e)}}}const ie='{"title":"Modelos codificadores","local":"modelos-codificadores","sections":[],"depth":1}';function me(N){return W(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class $e extends X{constructor(l){super(),Z(this,l,me,re,K,{})}}export{$e as component}; | |
Xet Storage Details
- Size:
- 4.39 kB
- Xet hash:
- 30ef47bd666ed2c380a8bf7168e0be30490e5eea0abe7523e49a666f6e7c70e4
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.