course/pr_1027/en/_app/immutable/nodes/4.d724efa9.js

import{s as De,n as je,o as Ge}from"../chunks/scheduler.37c15a92.js";import{S as Ye,i as Fe,g as s,s as l,r as m,A as Ke,h as r,f as i,c as a,j as Ne,u as p,x as o,k as Re,y as We,a as n,v as d,d as f,t as u,w as c}from"../chunks/index.7cb9c9b8.js";import{C as Oe}from"../chunks/CourseFloatingBanner.df82c153.js";import{H as $,E as Je}from"../chunks/getInferenceSnippets.c47ae3ea.js";function Qe(xe){let h,K,Y,W,g,O,v,J,T,ye="In this chapter, you’ve been introduced to the fundamentals of Transformer models, Large Language Models (LLMs), and how they’re revolutionizing AI and beyond.",Q,L,V,w,X,x,Me="We explored what NLP is and how Large Language Models have transformed the field. You learned that:",Z,y,Ce="<li>NLP encompasses a wide range of tasks from classification to generation</li> <li>LLMs are powerful models trained on massive amounts of text data</li> <li>These models can perform multiple tasks within a single architecture</li> <li>Despite their capabilities, LLMs have limitations including hallucinations and bias</li>",ee,M,te,C,be="You saw how the <code>pipeline()</code> function from 🤗 Transformers makes it easy to use pre-trained models for various tasks:",ie,b,_e="<li>Text classification, token classification, and question answering</li> <li>Text generation and summarization</li> <li>Translation and other sequence-to-sequence tasks</li> <li>Speech recognition and image classification</li>",ne,_,le,P,Pe="We discussed how Transformer models work at a high level, including:",ae,H,He="<li>The importance of the attention mechanism</li> <li>How transfer learning enables models to adapt to specific tasks</li> <li>The three main architectural variants: encoder-only, decoder-only, and encoder-decoder</li>",se,k,re,E,ke="A key aspect of this chapter was understanding which architecture to use for different tasks:",oe,q,Ee="<thead><tr><th>Model</th> <th>Examples</th> <th>Tasks</th></tr></thead> <tbody><tr><td>Encoder-only</td> <td>BERT, DistilBERT, ModernBERT</td> <td>Sentence classification, named entity recognition, extractive question answering</td></tr> <tr><td>Decoder-only</td> <td>GPT, LLaMA, Gemma, SmolLM</td> <td>Text generation, conversational AI, creative writing</td></tr> <tr><td>Encoder-decoder</td> <td>BART, T5, Marian, mBART</td> <td>Summarization, translation, generative question answering</td></tr></tbody>",me,A,pe,z,qe="You also learned about recent developments in the field:",de,S,Ae="<li>How LLMs have grown in size and capability over time</li> <li>The concept of scaling laws and how they guide model development</li> <li>Specialized attention mechanisms that help models process longer sequences</li> <li>The two-phase training approach of pretraining and instruction tuning</li>",fe,U,ue,B,ze="Throughout the chapter, you’ve seen how these models can be applied to real-world problems:",ce,I,Se="<li>Using the Hugging Face Hub to find and use pre-trained models</li> <li>Leveraging the Inference API to test models directly in your browser</li> <li>Understanding which models are best suited for specific tasks</li>",he,N,$e,R,Ue="Now that you have a solid understanding of what Transformer models are and how they work at a high level, you’re ready to dive deeper into how to use them effectively. In the next chapters, you’ll learn how to:",ge,D,Be="<li>Use the Transformers library to load and fine-tune models</li> <li>Process different types of data for model input</li> <li>Adapt pre-trained models to your specific tasks</li> <li>Deploy models for practical applications</li>",ve,j,Ie="The foundation you’ve built in this chapter will serve you well as you explore more advanced topics and techniques in the coming sections.",Te,G,Le,F,we;return g=new $({props:{title:"Summary",local:"summary",headingTag:"h1"}}),v=new Oe({props:{chapter:1,classNames:"absolute z-10 right-0 top-0"}}),L=new $({props:{title:"Key concepts covered",local:"key-concepts-covered",headingTag:"h2"}}),w=new $({props:{title:"Natural Language Processing and LLMs",local:"natural-language-processing-and-llms",headingTag:"h3"}}),M=new $({props:{title:"Transformer capabilities",local:"transformer-capabilities",headingTag:"h3"}}),_=new $({props:{title:"Transformer architecture",local:"transformer-architecture",headingTag:"h3"}}),k=new $({props:{title:"Model architectures and their applications",local:"model-architectures-and-their-applications",headingTag:"h3"}}),A=new $({props:{title:"Modern LLM developments",local:"modern-llm-developments",headingTag:"h3"}}),U=new $({props:{title:"Practical applications",local:"practical-applications",headingTag:"h3"}}),N=new $({props:{title:"Looking ahead",local:"looking-ahead",headingTag:"h2"}}),G=new Je({props:{source:"https://github.com/huggingface/course/blob/main/chapters/en/chapter1/10.mdx"}}),{c(){h=s("meta"),K=l(),Y=s("p"),W=l(),m(g.$$.fragment),O=l(),m(v.$$.fragment),J=l(),T=s("p"),T.textContent=ye,Q=l(),m(L.$$.fragment),V=l(),m(w.$$.fragment),X=l(),x=s("p"),x.textContent=Me,Z=l(),y=s("ul"),y.innerHTML=Ce,ee=l(),m(M.$$.fragment),te=l(),C=s("p"),C.innerHTML=be,ie=l(),b=s("ul"),b.innerHTML=_e,ne=l(),m(_.$$.fragment),le=l(),P=s("p"),P.textContent=Pe,ae=l(),H=s("ul"),H.innerHTML=He,se=l(),m(k.$$.fragment),re=l(),E=s("p"),E.textContent=ke,oe=l(),q=s("table"),q.innerHTML=Ee,me=l(),m(A.$$.fragment),pe=l(),z=s("p"),z.textContent=qe,de=l(),S=s("ul"),S.innerHTML=Ae,fe=l(),m(U.$$.fragment),ue=l(),B=s("p"),B.textContent=ze,ce=l(),I=s("ul"),I.innerHTML=Se,he=l(),m(N.$$.fragment),$e=l(),R=s("p"),R.textContent=Ue,ge=l(),D=s("ul"),D.innerHTML=Be,ve=l(),j=s("p"),j.textContent=Ie,Te=l(),m(G.$$.fragment),Le=l(),F=s("p"),this.h()},l(e){const t=Ke("svelte-u9bgzb",document.head);h=r(t,"META",{name:!0,content:!0}),t.forEach(i),K=a(e),Y=r(e,"P",{}),Ne(Y).forEach(i),W=a(e),p(g.$$.fragment,e),O=a(e),p(v.$$.fragment,e),J=a(e),T=r(e,"P",{"data-svelte-h":!0}),o(T)!=="svelte-i3fshz"&&(T.textContent=ye),Q=a(e),p(L.$$.fragment,e),V=a(e),p(w.$$.fragment,e),X=a(e),x=r(e,"P",{"data-svelte-h":!0}),o(x)!=="svelte-1lit2zm"&&(x.textContent=Me),Z=a(e),y=r(e,"UL",{"data-svelte-h":!0}),o(y)!=="svelte-17sn8p4"&&(y.innerHTML=Ce),ee=a(e),p(M.$$.fragment,e),te=a(e),C=r(e,"P",{"data-svelte-h":!0}),o(C)!=="svelte-jhecjx"&&(C.innerHTML=be),ie=a(e),b=r(e,"UL",{"data-svelte-h":!0}),o(b)!=="svelte-1shrou"&&(b.innerHTML=_e),ne=a(e),p(_.$$.fragment,e),le=a(e),P=r(e,"P",{"data-svelte-h":!0}),o(P)!=="svelte-1f8v9li"&&(P.textContent=Pe),ae=a(e),H=r(e,"UL",{"data-svelte-h":!0}),o(H)!=="svelte-1q9ne17"&&(H.innerHTML=He),se=a(e),p(k.$$.fragment,e),re=a(e),E=r(e,"P",{"data-svelte-h":!0}),o(E)!=="svelte-1ftf9m3"&&(E.textContent=ke),oe=a(e),q=r(e,"TABLE",{"data-svelte-h":!0}),o(q)!=="svelte-19df94o"&&(q.innerHTML=Ee),me=a(e),p(A.$$.fragment,e),pe=a(e),z=r(e,"P",{"data-svelte-h":!0}),o(z)!=="svelte-t6urrr"&&(z.textContent=qe),de=a(e),S=r(e,"UL",{"data-svelte-h":!0}),o(S)!=="svelte-1re5xby"&&(S.innerHTML=Ae),fe=a(e),p(U.$$.fragment,e),ue=a(e),B=r(e,"P",{"data-svelte-h":!0}),o(B)!=="svelte-1uuqwsg"&&(B.textContent=ze),ce=a(e),I=r(e,"UL",{"data-svelte-h":!0}),o(I)!=="svelte-ha9wcz"&&(I.innerHTML=Se),he=a(e),p(N.$$.fragment,e),$e=a(e),R=r(e,"P",{"data-svelte-h":!0}),o(R)!=="svelte-9vvrc8"&&(R.textContent=Ue),ge=a(e),D=r(e,"UL",{"data-svelte-h":!0}),o(D)!=="svelte-lytq9t"&&(D.innerHTML=Be),ve=a(e),j=r(e,"P",{"data-svelte-h":!0}),o(j)!=="svelte-9onihf"&&(j.textContent=Ie),Te=a(e),p(G.$$.fragment,e),Le=a(e),F=r(e,"P",{}),Ne(F).forEach(i),this.h()},h(){Re(h,"name","hf:doc:metadata"),Re(h,"content",Ve)},m(e,t){We(document.head,h),n(e,K,t),n(e,Y,t),n(e,W,t),d(g,e,t),n(e,O,t),d(v,e,t),n(e,J,t),n(e,T,t),n(e,Q,t),d(L,e,t),n(e,V,t),d(w,e,t),n(e,X,t),n(e,x,t),n(e,Z,t),n(e,y,t),n(e,ee,t),d(M,e,t),n(e,te,t),n(e,C,t),n(e,ie,t),n(e,b,t),n(e,ne,t),d(_,e,t),n(e,le,t),n(e,P,t),n(e,ae,t),n(e,H,t),n(e,se,t),d(k,e,t),n(e,re,t),n(e,E,t),n(e,oe,t),n(e,q,t),n(e,me,t),d(A,e,t),n(e,pe,t),n(e,z,t),n(e,de,t),n(e,S,t),n(e,fe,t),d(U,e,t),n(e,ue,t),n(e,B,t),n(e,ce,t),n(e,I,t),n(e,he,t),d(N,e,t),n(e,$e,t),n(e,R,t),n(e,ge,t),n(e,D,t),n(e,ve,t),n(e,j,t),n(e,Te,t),d(G,e,t),n(e,Le,t),n(e,F,t),we=!0},p:je,i(e){we||(f(g.$$.fragment,e),f(v.$$.fragment,e),f(L.$$.fragment,e),f(w.$$.fragment,e),f(M.$$.fragment,e),f(_.$$.fragment,e),f(k.$$.fragment,e),f(A.$$.fragment,e),f(U.$$.fragment,e),f(N.$$.fragment,e),f(G.$$.fragment,e),we=!0)},o(e){u(g.$$.fragment,e),u(v.$$.fragment,e),u(L.$$.fragment,e),u(w.$$.fragment,e),u(M.$$.fragment,e),u(_.$$.fragment,e),u(k.$$.fragment,e),u(A.$$.fragment,e),u(U.$$.fragment,e),u(N.$$.fragment,e),u(G.$$.fragment,e),we=!1},d(e){e&&(i(K),i(Y),i(W),i(O),i(J),i(T),i(Q),i(V),i(X),i(x),i(Z),i(y),i(ee),i(te),i(C),i(ie),i(b),i(ne),i(le),i(P),i(ae),i(H),i(se),i(re),i(E),i(oe),i(q),i(me),i(pe),i(z),i(de),i(S),i(fe),i(ue),i(B),i(ce),i(I),i(he),i($e),i(R),i(ge),i(D),i(ve),i(j),i(Te),i(Le),i(F)),i(h),c(g,e),c(v,e),c(L,e),c(w,e),c(M,e),c(_,e),c(k,e),c(A,e),c(U,e),c(N,e),c(G,e)}}}const Ve='{"title":"Summary","local":"summary","sections":[{"title":"Key concepts covered","local":"key-concepts-covered","sections":[{"title":"Natural Language Processing and LLMs","local":"natural-language-processing-and-llms","sections":[],"depth":3},{"title":"Transformer capabilities","local":"transformer-capabilities","sections":[],"depth":3},{"title":"Transformer architecture","local":"transformer-architecture","sections":[],"depth":3},{"title":"Model architectures and their applications","local":"model-architectures-and-their-applications","sections":[],"depth":3},{"title":"Modern LLM developments","local":"modern-llm-developments","sections":[],"depth":3},{"title":"Practical applications","local":"practical-applications","sections":[],"depth":3}],"depth":2},{"title":"Looking ahead","local":"looking-ahead","sections":[],"depth":2}],"depth":1}';function Xe(xe){return Ge(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class nt extends Ye{constructor(h){super(),Fe(this,h,Xe,Qe,De,{})}}export{nt as component};