Buckets:

rtrm's picture
download
raw
4.43 kB
import{s as K,n as V,o as W}from"../chunks/scheduler.505acc25.js";import{S as X,i as Z,e as i,s as o,c as C,h as ee,a as r,d as a,b as l,f as Q,g as v,j as w,k as I,l as te,m as n,n as E,t as y,o as L,p as T}from"../chunks/index.ccc5f2c1.js";import{C as ae,E as ne}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.69ef0a42.js";import{Y as oe}from"../chunks/Youtube.ed0cfdd7.js";import{C as le}from"../chunks/CourseFloatingBanner.edb13094.js";import{H as se}from"../chunks/Heading.666af0ac.js";function ie(Y){let s,M,b,P,m,z,c,R,f,H,d,q,p,D="Los modelos de codificadores usan únicamente el codificador del Transformer. En cada etapa, las capas de atención pueden acceder a todas las palabras de la oración inicial. Estos modelos se caracterizan generalmente por tener atención “bidireccional” y se suelen llamar modelos <em>auto-encoding</em>.",B,u,F="El preentrenamiento de estos modelos generalmente gira en torno a corromper de alguna manera una oración dada (por ejemplo, ocultando aleatoriamente palabras en ella) y pidiéndole al modelo que encuentre o reconstruya la oración inicial.",S,$,G="Los modelos de codificadores son más adecuados para tareas que requieren un entendimiento de la oración completa, como la clasificación de oraciones, reconocimiento de entidades nombradas (y más generalmente clasificación de palabras) y respuesta extractiva a preguntas.",j,g,J="Los miembros de esta familia de modelos incluyen:",A,h,O='<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>',U,_,k,x,N;return m=new ae({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),c=new se({props:{title:"Modelos de codificadores",local:"modelos-de-codificadores",headingTag:"h1"}}),f=new le({props:{chapter:1,classNames:"absolute z-10 right-0 top-0"}}),d=new oe({props:{id:"MUqNwgPjJvQ"}}),_=new ne({props:{source:"https://github.com/huggingface/course/blob/main/chapters/es/chapter1/5.mdx"}}),{c(){s=i("meta"),M=o(),b=i("p"),P=o(),C(m.$$.fragment),z=o(),C(c.$$.fragment),R=o(),C(f.$$.fragment),H=o(),C(d.$$.fragment),q=o(),p=i("p"),p.innerHTML=D,B=o(),u=i("p"),u.textContent=F,S=o(),$=i("p"),$.textContent=G,j=o(),g=i("p"),g.textContent=J,A=o(),h=i("ul"),h.innerHTML=O,U=o(),C(_.$$.fragment),k=o(),x=i("p"),this.h()},l(e){const t=ee("svelte-u9bgzb",document.head);s=r(t,"META",{name:!0,content:!0}),t.forEach(a),M=l(e),b=r(e,"P",{}),Q(b).forEach(a),P=l(e),v(m.$$.fragment,e),z=l(e),v(c.$$.fragment,e),R=l(e),v(f.$$.fragment,e),H=l(e),v(d.$$.fragment,e),q=l(e),p=r(e,"P",{"data-svelte-h":!0}),w(p)!=="svelte-1a8zafg"&&(p.innerHTML=D),B=l(e),u=r(e,"P",{"data-svelte-h":!0}),w(u)!=="svelte-1u8bex3"&&(u.textContent=F),S=l(e),$=r(e,"P",{"data-svelte-h":!0}),w($)!=="svelte-s7s47n"&&($.textContent=G),j=l(e),g=r(e,"P",{"data-svelte-h":!0}),w(g)!=="svelte-umsuzu"&&(g.textContent=J),A=l(e),h=r(e,"UL",{"data-svelte-h":!0}),w(h)!=="svelte-18kzzol"&&(h.innerHTML=O),U=l(e),v(_.$$.fragment,e),k=l(e),x=r(e,"P",{}),Q(x).forEach(a),this.h()},h(){I(s,"name","hf:doc:metadata"),I(s,"content",re)},m(e,t){te(document.head,s),n(e,M,t),n(e,b,t),n(e,P,t),E(m,e,t),n(e,z,t),E(c,e,t),n(e,R,t),E(f,e,t),n(e,H,t),E(d,e,t),n(e,q,t),n(e,p,t),n(e,B,t),n(e,u,t),n(e,S,t),n(e,$,t),n(e,j,t),n(e,g,t),n(e,A,t),n(e,h,t),n(e,U,t),E(_,e,t),n(e,k,t),n(e,x,t),N=!0},p:V,i(e){N||(y(m.$$.fragment,e),y(c.$$.fragment,e),y(f.$$.fragment,e),y(d.$$.fragment,e),y(_.$$.fragment,e),N=!0)},o(e){L(m.$$.fragment,e),L(c.$$.fragment,e),L(f.$$.fragment,e),L(d.$$.fragment,e),L(_.$$.fragment,e),N=!1},d(e){e&&(a(M),a(b),a(P),a(z),a(R),a(H),a(q),a(p),a(B),a(u),a(S),a($),a(j),a(g),a(A),a(h),a(U),a(k),a(x)),a(s),T(m,e),T(c,e),T(f,e),T(d,e),T(_,e)}}}const re='{"title":"Modelos de codificadores","local":"modelos-de-codificadores","sections":[],"depth":1}';function me(Y){return W(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ge extends X{constructor(s){super(),Z(this,s,me,ie,K,{})}}export{ge as component};

Xet Storage Details

Size:
4.43 kB
·
Xet hash:
1fb5e22e9f906ca4fcc7f4872dcc40b88bf4c48f92e6ee635e24dd3fe0535fdc

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