Buckets:

rtrm's picture
download
raw
3.07 kB
import{s as N,n as O,o as R}from"../chunks/scheduler.505acc25.js";import{S as W,i as D,e as d,s,c as w,h as I,a as $,d as a,b as r,f as A,g as E,j as q,k as F,l as J,m as n,n as L,t as S,o as M,p as H}from"../chunks/index.ccc5f2c1.js";import{C as K,E as Q}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.786114b7.js";import{C as V}from"../chunks/CourseFloatingBanner.edb13094.js";import{H as X}from"../chunks/Heading.666af0ac.js";function Y(U){let o,h,z,x,i,_,l,b,m,k,p,j="Gran trabajo terminando este capítulo!",C,u,B="Luego de esta profundizacion en los tokenizadores, deberías:",v,f,G="<li>Ser capaz de entrenar un nuevo tokenizador usando un existente como plantilla</li> <li>Entender como usar los offsets para mapear las posiciones de los tokens a sus trozos de texto original</li> <li>Conocer las diferencias entre BPE, WordPiece y Unigram</li> <li>Ser capaz de mezclar y combinar los bloques provistos por la librería 🤗 Tokenizers para construir tu propio tokenizador</li> <li>Ser capaz de usar el tokenizador dentro de la librería 🤗 Transformers.</li>",P,c,y,g,T;return i=new K({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),l=new X({props:{title:"Tokenizadores, listo!",local:"tokenizers-check",headingTag:"h1"}}),m=new V({props:{chapter:6,classNames:"absolute z-10 right-0 top-0"}}),c=new Q({props:{source:"https://github.com/huggingface/course/blob/main/chapters/es/chapter6/9.mdx"}}),{c(){o=d("meta"),h=s(),z=d("p"),x=s(),w(i.$$.fragment),_=s(),w(l.$$.fragment),b=s(),w(m.$$.fragment),k=s(),p=d("p"),p.textContent=j,C=s(),u=d("p"),u.textContent=B,v=s(),f=d("ul"),f.innerHTML=G,P=s(),w(c.$$.fragment),y=s(),g=d("p"),this.h()},l(e){const t=I("svelte-u9bgzb",document.head);o=$(t,"META",{name:!0,content:!0}),t.forEach(a),h=r(e),z=$(e,"P",{}),A(z).forEach(a),x=r(e),E(i.$$.fragment,e),_=r(e),E(l.$$.fragment,e),b=r(e),E(m.$$.fragment,e),k=r(e),p=$(e,"P",{"data-svelte-h":!0}),q(p)!=="svelte-3z1det"&&(p.textContent=j),C=r(e),u=$(e,"P",{"data-svelte-h":!0}),q(u)!=="svelte-6klo4x"&&(u.textContent=B),v=r(e),f=$(e,"UL",{"data-svelte-h":!0}),q(f)!=="svelte-qla4gz"&&(f.innerHTML=G),P=r(e),E(c.$$.fragment,e),y=r(e),g=$(e,"P",{}),A(g).forEach(a),this.h()},h(){F(o,"name","hf:doc:metadata"),F(o,"content",Z)},m(e,t){J(document.head,o),n(e,h,t),n(e,z,t),n(e,x,t),L(i,e,t),n(e,_,t),L(l,e,t),n(e,b,t),L(m,e,t),n(e,k,t),n(e,p,t),n(e,C,t),n(e,u,t),n(e,v,t),n(e,f,t),n(e,P,t),L(c,e,t),n(e,y,t),n(e,g,t),T=!0},p:O,i(e){T||(S(i.$$.fragment,e),S(l.$$.fragment,e),S(m.$$.fragment,e),S(c.$$.fragment,e),T=!0)},o(e){M(i.$$.fragment,e),M(l.$$.fragment,e),M(m.$$.fragment,e),M(c.$$.fragment,e),T=!1},d(e){e&&(a(h),a(z),a(x),a(_),a(b),a(k),a(p),a(C),a(u),a(v),a(f),a(P),a(y),a(g)),a(o),H(i,e),H(l,e),H(m,e),H(c,e)}}}const Z='{"title":"Tokenizadores, listo!","local":"tokenizers-check","sections":[],"depth":1}';function ee(U){return R(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class re extends W{constructor(o){super(),D(this,o,ee,Y,N,{})}}export{re as component};

Xet Storage Details

Size:
3.07 kB
·
Xet hash:
43916445e43a859eb4cd84de69248df33c748fac6c7a472fe9e0abedca812b7a

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