Buckets:
| import{s as Ds,o as Ls,n as Ms}from"../chunks/scheduler.36a0863c.js";import{S as Ps,i as Ks,g as U,s as M,r as m,A as Os,h as J,f as t,c,j as Ys,u,x as $,k as qs,y as se,a as n,v as d,d as j,t as y,w as f}from"../chunks/index.f891bdb2.js";import{T as Rs}from"../chunks/Tip.a8272f7f.js";import{Y as Hs}from"../chunks/Youtube.0cbacd3d.js";import{C as k}from"../chunks/CodeBlock.3ec784ea.js";import{F as Ss,M as xs}from"../chunks/Markdown.7b58822e.js";import{H as Gs,E as ee}from"../chunks/EditOnGithub.a58e27a9.js";function ae(T){let e,r='Revisa la <a href="https://huggingface.co/tasks/question-answering" rel="nofollow">página de la tarea</a> de responder preguntas para tener más información sobre otras formas de responder preguntas y los modelos, datasets y métricas asociadas.';return{c(){e=U("p"),e.innerHTML=r},l(a){e=J(a,"P",{"data-svelte-h":!0}),$(e)!=="svelte-1yfogxf"&&(e.innerHTML=r)},m(a,o){n(a,e,o)},p:Ms,d(a){a&&t(e)}}}function te(T){let e,r;return e=new k({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERlZmF1bHREYXRhQ29sbGF0b3IlMEElMEFkYXRhX2NvbGxhdG9yJTIwJTNEJTIwRGVmYXVsdERhdGFDb2xsYXRvcigp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DefaultDataCollator | |
| <span class="hljs-meta">>>> </span>data_collator = DefaultDataCollator()`,wrap:!1}}),{c(){m(e.$$.fragment)},l(a){u(e.$$.fragment,a)},m(a,o){d(e,a,o),r=!0},p:Ms,i(a){r||(j(e.$$.fragment,a),r=!0)},o(a){y(e.$$.fragment,a),r=!1},d(a){f(e,a)}}}function le(T){let e,r;return e=new xs({props:{$$slots:{default:[te]},$$scope:{ctx:T}}}),{c(){m(e.$$.fragment)},l(a){u(e.$$.fragment,a)},m(a,o){d(e,a,o),r=!0},p(a,o){const h={};o&2&&(h.$$scope={dirty:o,ctx:a}),e.$set(h)},i(a){r||(j(e.$$.fragment,a),r=!0)},o(a){y(e.$$.fragment,a),r=!1},d(a){f(e,a)}}}function ne(T){let e,r;return e=new k({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERlZmF1bHREYXRhQ29sbGF0b3IlMEElMEFkYXRhX2NvbGxhdG9yJTIwJTNEJTIwRGVmYXVsdERhdGFDb2xsYXRvcihyZXR1cm5fdGVuc29ycyUzRCUyMnRmJTIyKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DefaultDataCollator | |
| <span class="hljs-meta">>>> </span>data_collator = DefaultDataCollator(return_tensors=<span class="hljs-string">"tf"</span>)`,wrap:!1}}),{c(){m(e.$$.fragment)},l(a){u(e.$$.fragment,a)},m(a,o){d(e,a,o),r=!0},p:Ms,i(a){r||(j(e.$$.fragment,a),r=!0)},o(a){y(e.$$.fragment,a),r=!1},d(a){f(e,a)}}}function pe(T){let e,r;return e=new xs({props:{$$slots:{default:[ne]},$$scope:{ctx:T}}}),{c(){m(e.$$.fragment)},l(a){u(e.$$.fragment,a)},m(a,o){d(e,a,o),r=!0},p(a,o){const h={};o&2&&(h.$$scope={dirty:o,ctx:a}),e.$set(h)},i(a){r||(j(e.$$.fragment,a),r=!0)},o(a){y(e.$$.fragment,a),r=!1},d(a){f(e,a)}}}function re(T){let e,r='Para familiarizarte con el fine-tuning con <code>Trainer</code>, ¡mira el tutorial básico <a href="../training#finetune-with-trainer">aquí</a>!';return{c(){e=U("p"),e.innerHTML=r},l(a){e=J(a,"P",{"data-svelte-h":!0}),$(e)!=="svelte-1sco78m"&&(e.innerHTML=r)},m(a,o){n(a,e,o)},p:Ms,d(a){a&&t(e)}}}function oe(T){let e,r="Carga el modelo DistilBERT con <code>AutoModelForQuestionAnswering</code>:",a,o,h,C,A,b,E="En este punto, solo quedan tres pasos:",B,I,G="<li>Definir tus hiperparámetros de entrenamiento en <code>TrainingArguments</code>.</li> <li>Pasarle los argumentos del entrenamiento al <code>Trainer</code> junto con el modelo, el dataset, el tokenizer y el collator de datos.</li> <li>Invocar el método <code>train()</code> para realizar el fine-tuning del modelo.</li>",R,x,Z;return o=new k({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMEF1dG9Nb2RlbEZvclF1ZXN0aW9uQW5zd2VyaW5nJTJDJTIwVHJhaW5pbmdBcmd1bWVudHMlMkMlMjBUcmFpbmVyJTBBJTBBbW9kZWwlMjAlM0QlMjBBdXRvTW9kZWxGb3JRdWVzdGlvbkFuc3dlcmluZy5mcm9tX3ByZXRyYWluZWQoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForQuestionAnswering, TrainingArguments, Trainer | |
| <span class="hljs-meta">>>> </span>model = AutoModelForQuestionAnswering.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),C=new Rs({props:{$$slots:{default:[re]},$$scope:{ctx:T}}}),x=new k({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span>training_args = TrainingArguments( | |
| <span class="hljs-meta">... </span> output_dir=<span class="hljs-string">"./results"</span>, | |
| <span class="hljs-meta">... </span> eval_strategy=<span class="hljs-string">"epoch"</span>, | |
| <span class="hljs-meta">... </span> learning_rate=<span class="hljs-number">2e-5</span>, | |
| <span class="hljs-meta">... </span> per_device_train_batch_size=<span class="hljs-number">16</span>, | |
| <span class="hljs-meta">... </span> per_device_eval_batch_size=<span class="hljs-number">16</span>, | |
| <span class="hljs-meta">... </span> num_train_epochs=<span class="hljs-number">3</span>, | |
| <span class="hljs-meta">... </span> weight_decay=<span class="hljs-number">0.01</span>, | |
| <span class="hljs-meta">... </span>) | |
| <span class="hljs-meta">>>> </span>trainer = Trainer( | |
| <span class="hljs-meta">... </span> model=model, | |
| <span class="hljs-meta">... </span> args=training_args, | |
| <span class="hljs-meta">... </span> train_dataset=tokenized_squad[<span class="hljs-string">"train"</span>], | |
| <span class="hljs-meta">... </span> eval_dataset=tokenized_squad[<span class="hljs-string">"validation"</span>], | |
| <span class="hljs-meta">... </span> tokenizer=tokenizer, | |
| <span class="hljs-meta">... </span> data_collator=data_collator, | |
| <span class="hljs-meta">... </span>) | |
| <span class="hljs-meta">>>> </span>trainer.train()`,wrap:!1}}),{c(){e=U("p"),e.innerHTML=r,a=M(),m(o.$$.fragment),h=M(),m(C.$$.fragment),A=M(),b=U("p"),b.textContent=E,B=M(),I=U("ol"),I.innerHTML=G,R=M(),m(x.$$.fragment)},l(i){e=J(i,"P",{"data-svelte-h":!0}),$(e)!=="svelte-1jpacxl"&&(e.innerHTML=r),a=c(i),u(o.$$.fragment,i),h=c(i),u(C.$$.fragment,i),A=c(i),b=J(i,"P",{"data-svelte-h":!0}),$(b)!=="svelte-bd5x35"&&(b.textContent=E),B=c(i),I=J(i,"OL",{"data-svelte-h":!0}),$(I)!=="svelte-omqmsj"&&(I.innerHTML=G),R=c(i),u(x.$$.fragment,i)},m(i,g){n(i,e,g),n(i,a,g),d(o,i,g),n(i,h,g),d(C,i,g),n(i,A,g),n(i,b,g),n(i,B,g),n(i,I,g),n(i,R,g),d(x,i,g),Z=!0},p(i,g){const _={};g&2&&(_.$$scope={dirty:g,ctx:i}),C.$set(_)},i(i){Z||(j(o.$$.fragment,i),j(C.$$.fragment,i),j(x.$$.fragment,i),Z=!0)},o(i){y(o.$$.fragment,i),y(C.$$.fragment,i),y(x.$$.fragment,i),Z=!1},d(i){i&&(t(e),t(a),t(h),t(A),t(b),t(B),t(I),t(R)),f(o,i),f(C,i),f(x,i)}}}function ie(T){let e,r;return e=new xs({props:{$$slots:{default:[oe]},$$scope:{ctx:T}}}),{c(){m(e.$$.fragment)},l(a){u(e.$$.fragment,a)},m(a,o){d(e,a,o),r=!0},p(a,o){const h={};o&2&&(h.$$scope={dirty:o,ctx:a}),e.$set(h)},i(a){r||(j(e.$$.fragment,a),r=!0)},o(a){y(e.$$.fragment,a),r=!1},d(a){f(e,a)}}}function Me(T){let e,r='Para familiarizarte con el fine-tuning con Keras, ¡mira el tutorial básico <a href="training#finetune-with-keras">aquí</a>!';return{c(){e=U("p"),e.innerHTML=r},l(a){e=J(a,"P",{"data-svelte-h":!0}),$(e)!=="svelte-66s4ry"&&(e.innerHTML=r)},m(a,o){n(a,e,o)},p:Ms,d(a){a&&t(e)}}}function ce(T){let e,r="Para realizar el fine-tuning de un modelo en TensorFlow, primero convierte tus datasets al formato <code>tf.data.Dataset</code> con el método <code>prepare_tf_dataset()</code>.",a,o,h,C,A,b,E="Prepara una función de optimización, un programa para la tasa de aprendizaje y algunos hiperparámetros de entrenamiento:",B,I,G,R,x="Carga el modelo DistilBERT con <code>TFAutoModelForQuestionAnswering</code>:",Z,i,g,_,S='Configura el modelo para entrenarlo con <a href="https://keras.io/api/models/model_training_apis/#compile-method" rel="nofollow"><code>compile</code></a>:',X,v,V,F,D='Invoca el método <a href="https://keras.io/api/models/model_training_apis/#fit-method" rel="nofollow"><code>fit</code></a> para realizar el fine-tuning del modelo:',z,Q,W;return o=new k({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span>tf_train_set = model.prepare_tf_dataset( | |
| <span class="hljs-meta">... </span> tokenized_squad[<span class="hljs-string">"train"</span>], | |
| <span class="hljs-meta">... </span> shuffle=<span class="hljs-literal">True</span>, | |
| <span class="hljs-meta">... </span> batch_size=<span class="hljs-number">16</span>, | |
| <span class="hljs-meta">... </span> collate_fn=data_collator, | |
| <span class="hljs-meta">... </span>) | |
| <span class="hljs-meta">>>> </span>tf_validation_set = model.prepare_tf_dataset( | |
| <span class="hljs-meta">... </span> tokenized_squad[<span class="hljs-string">"validation"</span>], | |
| <span class="hljs-meta">... </span> shuffle=<span class="hljs-literal">False</span>, | |
| <span class="hljs-meta">... </span> batch_size=<span class="hljs-number">16</span>, | |
| <span class="hljs-meta">... </span> collate_fn=data_collator, | |
| <span class="hljs-meta">... </span>)`,wrap:!1}}),C=new Rs({props:{$$slots:{default:[Me]},$$scope:{ctx:T}}}),I=new k({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> create_optimizer | |
| <span class="hljs-meta">>>> </span>batch_size = <span class="hljs-number">16</span> | |
| <span class="hljs-meta">>>> </span>num_epochs = <span class="hljs-number">2</span> | |
| <span class="hljs-meta">>>> </span>total_train_steps = (<span class="hljs-built_in">len</span>(tokenized_squad[<span class="hljs-string">"train"</span>]) // batch_size) * num_epochs | |
| <span class="hljs-meta">>>> </span>optimizer, schedule = create_optimizer( | |
| <span class="hljs-meta">... </span> init_lr=<span class="hljs-number">2e-5</span>, | |
| <span class="hljs-meta">... </span> num_warmup_steps=<span class="hljs-number">0</span>, | |
| <span class="hljs-meta">... </span> num_train_steps=total_train_steps, | |
| <span class="hljs-meta">... </span>)`,wrap:!1}}),i=new k({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFRGQXV0b01vZGVsRm9yUXVlc3Rpb25BbnN3ZXJpbmclMEElMEFtb2RlbCUyMCUzRCUyMFRGQXV0b01vZGVsRm9yUXVlc3Rpb25BbnN3ZXJpbmcoJTIyZGlzdGlsYmVydCUyRmRpc3RpbGJlcnQtYmFzZS11bmNhc2VkJTIyKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFAutoModelForQuestionAnswering | |
| <span class="hljs-meta">>>> </span>model = TFAutoModelForQuestionAnswering(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),v=new k({props:{code:"aW1wb3J0JTIwdGVuc29yZmxvdyUyMGFzJTIwdGYlMEElMEFtb2RlbC5jb21waWxlKG9wdGltaXplciUzRG9wdGltaXplcik=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> tensorflow <span class="hljs-keyword">as</span> tf | |
| <span class="hljs-meta">>>> </span>model.<span class="hljs-built_in">compile</span>(optimizer=optimizer)`,wrap:!1}}),Q=new k({props:{code:"bW9kZWwuZml0KHglM0R0Zl90cmFpbl9zZXQlMkMlMjB2YWxpZGF0aW9uX2RhdGElM0R0Zl92YWxpZGF0aW9uX3NldCUyQyUyMGVwb2NocyUzRDMp",highlighted:'<span class="hljs-meta">>>> </span>model.fit(x=tf_train_set, validation_data=tf_validation_set, epochs=<span class="hljs-number">3</span>)',wrap:!1}}),{c(){e=U("p"),e.innerHTML=r,a=M(),m(o.$$.fragment),h=M(),m(C.$$.fragment),A=M(),b=U("p"),b.textContent=E,B=M(),m(I.$$.fragment),G=M(),R=U("p"),R.innerHTML=x,Z=M(),m(i.$$.fragment),g=M(),_=U("p"),_.innerHTML=S,X=M(),m(v.$$.fragment),V=M(),F=U("p"),F.innerHTML=D,z=M(),m(Q.$$.fragment)},l(p){e=J(p,"P",{"data-svelte-h":!0}),$(e)!=="svelte-1dn6k4v"&&(e.innerHTML=r),a=c(p),u(o.$$.fragment,p),h=c(p),u(C.$$.fragment,p),A=c(p),b=J(p,"P",{"data-svelte-h":!0}),$(b)!=="svelte-81yq28"&&(b.textContent=E),B=c(p),u(I.$$.fragment,p),G=c(p),R=J(p,"P",{"data-svelte-h":!0}),$(R)!=="svelte-owfaiz"&&(R.innerHTML=x),Z=c(p),u(i.$$.fragment,p),g=c(p),_=J(p,"P",{"data-svelte-h":!0}),$(_)!=="svelte-jy7mgr"&&(_.innerHTML=S),X=c(p),u(v.$$.fragment,p),V=c(p),F=J(p,"P",{"data-svelte-h":!0}),$(F)!=="svelte-1dz4xz1"&&(F.innerHTML=D),z=c(p),u(Q.$$.fragment,p)},m(p,w){n(p,e,w),n(p,a,w),d(o,p,w),n(p,h,w),d(C,p,w),n(p,A,w),n(p,b,w),n(p,B,w),d(I,p,w),n(p,G,w),n(p,R,w),n(p,Z,w),d(i,p,w),n(p,g,w),n(p,_,w),n(p,X,w),d(v,p,w),n(p,V,w),n(p,F,w),n(p,z,w),d(Q,p,w),W=!0},p(p,w){const N={};w&2&&(N.$$scope={dirty:w,ctx:p}),C.$set(N)},i(p){W||(j(o.$$.fragment,p),j(C.$$.fragment,p),j(I.$$.fragment,p),j(i.$$.fragment,p),j(v.$$.fragment,p),j(Q.$$.fragment,p),W=!0)},o(p){y(o.$$.fragment,p),y(C.$$.fragment,p),y(I.$$.fragment,p),y(i.$$.fragment,p),y(v.$$.fragment,p),y(Q.$$.fragment,p),W=!1},d(p){p&&(t(e),t(a),t(h),t(A),t(b),t(B),t(G),t(R),t(Z),t(g),t(_),t(X),t(V),t(F),t(z)),f(o,p),f(C,p),f(I,p),f(i,p),f(v,p),f(Q,p)}}}function me(T){let e,r;return e=new xs({props:{$$slots:{default:[ce]},$$scope:{ctx:T}}}),{c(){m(e.$$.fragment)},l(a){u(e.$$.fragment,a)},m(a,o){d(e,a,o),r=!0},p(a,o){const h={};o&2&&(h.$$scope={dirty:o,ctx:a}),e.$set(h)},i(a){r||(j(e.$$.fragment,a),r=!0)},o(a){y(e.$$.fragment,a),r=!1},d(a){f(e,a)}}}function ue(T){let e,r=`Para un ejemplo con mayor profundidad de cómo hacer fine-tuning a un modelo para responder preguntas, échale un vistazo al | |
| <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering.ipynb" rel="nofollow">cuaderno de PyTorch</a> o al | |
| <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering-tf.ipynb" rel="nofollow">cuaderno de TensorFlow</a> correspondiente.`;return{c(){e=U("p"),e.innerHTML=r},l(a){e=J(a,"P",{"data-svelte-h":!0}),$(e)!=="svelte-1vvpf09"&&(e.innerHTML=r)},m(a,o){n(a,e,o)},p:Ms,d(a){a&&t(e)}}}function de(T){let e,r,a,o,h,C,A,b,E,B="La respuesta a preguntas devuelve una respuesta a partir de una pregunta dada. Existen dos formas comunes de responder preguntas:",I,G,R="<li>Extractiva: extraer la respuesta a partir del contexto dado.</li> <li>Abstractiva: generar una respuesta que responda correctamente la pregunta a partir del contexto dado.</li>",x,Z,i='Esta guía te mostrará como hacer fine-tuning de <a href="https://huggingface.co/distilbert/distilbert-base-uncased" rel="nofollow">DistilBERT</a> en el dataset <a href="https://huggingface.co/datasets/squad" rel="nofollow">SQuAD</a> para responder preguntas de forma extractiva.',g,_,S,X,v,V,F="Carga el dataset SQuAD con la biblioteca 🤗 Datasets:",D,z,Q,W,p="Ahora, échale un vistazo a una muestra:",w,N,ms,L,ks="El campo <code>answers</code> es un diccionario que contiene la posición inicial de la respuesta y el <code>texto</code> de la respuesta.",us,P,ds,K,js,O,Es="Carga el tokenizer de DistilBERT para procesar los campos <code>question</code> (pregunta) y <code>context</code> (contexto):",ys,ss,fs,es,Bs="Hay algunos pasos de preprocesamiento específicos para la tarea de respuesta a preguntas que debes tener en cuenta:",hs,as,Xs=`<li>Algunos ejemplos en un dataset pueden tener un contexto que supera la longitud máxima de entrada de un modelo. Trunca solamente el contexto asignándole el valor <code>"only_second"</code> al parámetro <code>truncation</code>.</li> <li>A continuación, mapea las posiciones de inicio y fin de la respuesta al contexto original asignándole el valor <code>True</code> al parámetro <code>return_offsets_mapping</code>.</li> <li>Una vez tengas el mapeo, puedes encontrar los tokens de inicio y fin de la respuesta. Usa el método <a href="https://huggingface.co/docs/tokenizers/python/latest/api/reference.html#tokenizers.Encoding.sequence_ids" rel="nofollow"><code>sequence_ids</code></a> | |
| para encontrar qué parte de la lista de tokens desplazados corresponde a la pregunta y cuál corresponde al contexto.</li>`,ws,ts,vs="A continuación puedes ver como se crea una función para truncar y mapear los tokens de inicio y fin de la respuesta al <code>context</code>:",Us,ls,Js,ns,Vs=`Usa la función <code>map</code> de 🤗 Datasets para aplicarle la función de preprocesamiento al dataset entero. Puedes acelerar la función <code>map</code> haciendo <code>batched=True</code> para procesar varios elementos del dataset a la vez. | |
| Quita las columnas que no necesites:`,Ts,ps,gs,rs,zs="Usa el <code>DefaultDataCollator</code> para crear un lote de ejemplos. A diferencia de los otros collators de datos en 🤗 Transformers, el <code>DefaultDataCollator</code> no aplica ningún procesamiento adicional (como el rellenado).",$s,Y,Cs,os,bs,q,Is,H,_s,is,As,cs,Zs;return h=new Gs({props:{title:"Respuesta a preguntas",local:"respuesta-a-preguntas",headingTag:"h1"}}),A=new Hs({props:{id:"ajPx5LwJD-I"}}),_=new Rs({props:{$$slots:{default:[ae]},$$scope:{ctx:T}}}),X=new Gs({props:{title:"Carga el dataset SQuAD",local:"carga-el-dataset-squad",headingTag:"h2"}}),z=new k({props:{code:"ZnJvbSUyMGRhdGFzZXRzJTIwaW1wb3J0JTIwbG9hZF9kYXRhc2V0JTBBJTBBc3F1YWQlMjAlM0QlMjBsb2FkX2RhdGFzZXQoJTIyc3F1YWQlMjIp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset | |
| <span class="hljs-meta">>>> </span>squad = load_dataset(<span class="hljs-string">"squad"</span>)`,wrap:!1}}),N=new k({props:{code:"c3F1YWQlNUIlMjJ0cmFpbiUyMiU1RCU1QjAlNUQ=",highlighted:`<span class="hljs-meta">>>> </span>squad[<span class="hljs-string">"train"</span>][<span class="hljs-number">0</span>] | |
| {<span class="hljs-string">'answers'</span>: {<span class="hljs-string">'answer_start'</span>: [<span class="hljs-number">515</span>], <span class="hljs-string">'text'</span>: [<span class="hljs-string">'Saint Bernadette Soubirous'</span>]}, | |
| <span class="hljs-string">'context'</span>: <span class="hljs-string">'Architecturally, the school has a Catholic character. Atop the Main Building\\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend "Venite Ad Me Omnes". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.'</span>, | |
| <span class="hljs-string">'id'</span>: <span class="hljs-string">'5733be284776f41900661182'</span>, | |
| <span class="hljs-string">'question'</span>: <span class="hljs-string">'To whom did the Virgin Mary allegedly appear in 1858 in Lourdes France?'</span>, | |
| <span class="hljs-string">'title'</span>: <span class="hljs-string">'University_of_Notre_Dame'</span> | |
| }`,wrap:!1}}),P=new Gs({props:{title:"Preprocesamiento",local:"preprocesamiento",headingTag:"h2"}}),K=new Hs({props:{id:"qgaM0weJHpA"}}),ss=new k({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMEF1dG9Ub2tlbml6ZXIlMEElMEF0b2tlbml6ZXIlMjAlM0QlMjBBdXRvVG9rZW5pemVyLmZyb21fcHJldHJhaW5lZCglMjJkaXN0aWxiZXJ0JTJGZGlzdGlsYmVydC1iYXNlLXVuY2FzZWQlMjIp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer | |
| <span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>)`,wrap:!1}}),ls=new k({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">preprocess_function</span>(<span class="hljs-params">examples</span>): | |
| <span class="hljs-meta">... </span> questions = [q.strip() <span class="hljs-keyword">for</span> q <span class="hljs-keyword">in</span> examples[<span class="hljs-string">"question"</span>]] | |
| <span class="hljs-meta">... </span> inputs = tokenizer( | |
| <span class="hljs-meta">... </span> questions, | |
| <span class="hljs-meta">... </span> examples[<span class="hljs-string">"context"</span>], | |
| <span class="hljs-meta">... </span> max_length=<span class="hljs-number">384</span>, | |
| <span class="hljs-meta">... </span> truncation=<span class="hljs-string">"only_second"</span>, | |
| <span class="hljs-meta">... </span> return_offsets_mapping=<span class="hljs-literal">True</span>, | |
| <span class="hljs-meta">... </span> padding=<span class="hljs-string">"max_length"</span>, | |
| <span class="hljs-meta">... </span> ) | |
| <span class="hljs-meta">... </span> offset_mapping = inputs.pop(<span class="hljs-string">"offset_mapping"</span>) | |
| <span class="hljs-meta">... </span> answers = examples[<span class="hljs-string">"answers"</span>] | |
| <span class="hljs-meta">... </span> start_positions = [] | |
| <span class="hljs-meta">... </span> end_positions = [] | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">for</span> i, offset <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(offset_mapping): | |
| <span class="hljs-meta">... </span> answer = answers[i] | |
| <span class="hljs-meta">... </span> start_char = answer[<span class="hljs-string">"answer_start"</span>][<span class="hljs-number">0</span>] | |
| <span class="hljs-meta">... </span> end_char = answer[<span class="hljs-string">"answer_start"</span>][<span class="hljs-number">0</span>] + <span class="hljs-built_in">len</span>(answer[<span class="hljs-string">"text"</span>][<span class="hljs-number">0</span>]) | |
| <span class="hljs-meta">... </span> sequence_ids = inputs.sequence_ids(i) | |
| <span class="hljs-meta">... </span> <span class="hljs-comment"># Encuentra el inicio y el fin del contexto</span> | |
| <span class="hljs-meta">... </span> idx = <span class="hljs-number">0</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">while</span> sequence_ids[idx] != <span class="hljs-number">1</span>: | |
| <span class="hljs-meta">... </span> idx += <span class="hljs-number">1</span> | |
| <span class="hljs-meta">... </span> context_start = idx | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">while</span> sequence_ids[idx] == <span class="hljs-number">1</span>: | |
| <span class="hljs-meta">... </span> idx += <span class="hljs-number">1</span> | |
| <span class="hljs-meta">... </span> context_end = idx - <span class="hljs-number">1</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-comment"># Si la respuesta entera no está dentro del contexto, etiquétala como (0, 0)</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> offset[context_start][<span class="hljs-number">0</span>] > end_char <span class="hljs-keyword">or</span> offset[context_end][<span class="hljs-number">1</span>] < start_char: | |
| <span class="hljs-meta">... </span> start_positions.append(<span class="hljs-number">0</span>) | |
| <span class="hljs-meta">... </span> end_positions.append(<span class="hljs-number">0</span>) | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">else</span>: | |
| <span class="hljs-meta">... </span> <span class="hljs-comment"># De lo contrario, esta es la posición de los tokens de inicio y fin</span> | |
| <span class="hljs-meta">... </span> idx = context_start | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">while</span> idx <= context_end <span class="hljs-keyword">and</span> offset[idx][<span class="hljs-number">0</span>] <= start_char: | |
| <span class="hljs-meta">... </span> idx += <span class="hljs-number">1</span> | |
| <span class="hljs-meta">... </span> start_positions.append(idx - <span class="hljs-number">1</span>) | |
| <span class="hljs-meta">... </span> idx = context_end | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">while</span> idx >= context_start <span class="hljs-keyword">and</span> offset[idx][<span class="hljs-number">1</span>] >= end_char: | |
| <span class="hljs-meta">... </span> idx -= <span class="hljs-number">1</span> | |
| <span class="hljs-meta">... </span> end_positions.append(idx + <span class="hljs-number">1</span>) | |
| <span class="hljs-meta">... </span> inputs[<span class="hljs-string">"start_positions"</span>] = start_positions | |
| <span class="hljs-meta">... </span> inputs[<span class="hljs-string">"end_positions"</span>] = end_positions | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> inputs`,wrap:!1}}),ps=new k({props:{code:"dG9rZW5pemVkX3NxdWFkJTIwJTNEJTIwc3F1YWQubWFwKHByZXByb2Nlc3NfZnVuY3Rpb24lMkMlMjBiYXRjaGVkJTNEVHJ1ZSUyQyUyMHJlbW92ZV9jb2x1bW5zJTNEc3F1YWQlNUIlMjJ0cmFpbiUyMiU1RC5jb2x1bW5fbmFtZXMp",highlighted:'<span class="hljs-meta">>>> </span>tokenized_squad = squad.<span class="hljs-built_in">map</span>(preprocess_function, batched=<span class="hljs-literal">True</span>, remove_columns=squad[<span class="hljs-string">"train"</span>].column_names)',wrap:!1}}),Y=new Ss({props:{pytorch:!0,tensorflow:!0,jax:!1,$$slots:{tensorflow:[pe],pytorch:[le]},$$scope:{ctx:T}}}),os=new Gs({props:{title:"Entrenamiento",local:"entrenamiento",headingTag:"h2"}}),q=new Ss({props:{pytorch:!0,tensorflow:!0,jax:!1,$$slots:{tensorflow:[me],pytorch:[ie]},$$scope:{ctx:T}}}),H=new Rs({props:{$$slots:{default:[ue]},$$scope:{ctx:T}}}),is=new ee({props:{source:"https://github.com/huggingface/transformers/blob/main/docs/source/es/tasks/question_answering.md"}}),{c(){e=U("meta"),r=M(),a=U("p"),o=M(),m(h.$$.fragment),C=M(),m(A.$$.fragment),b=M(),E=U("p"),E.textContent=B,I=M(),G=U("ul"),G.innerHTML=R,x=M(),Z=U("p"),Z.innerHTML=i,g=M(),m(_.$$.fragment),S=M(),m(X.$$.fragment),v=M(),V=U("p"),V.textContent=F,D=M(),m(z.$$.fragment),Q=M(),W=U("p"),W.textContent=p,w=M(),m(N.$$.fragment),ms=M(),L=U("p"),L.innerHTML=ks,us=M(),m(P.$$.fragment),ds=M(),m(K.$$.fragment),js=M(),O=U("p"),O.innerHTML=Es,ys=M(),m(ss.$$.fragment),fs=M(),es=U("p"),es.textContent=Bs,hs=M(),as=U("ol"),as.innerHTML=Xs,ws=M(),ts=U("p"),ts.innerHTML=vs,Us=M(),m(ls.$$.fragment),Js=M(),ns=U("p"),ns.innerHTML=Vs,Ts=M(),m(ps.$$.fragment),gs=M(),rs=U("p"),rs.innerHTML=zs,$s=M(),m(Y.$$.fragment),Cs=M(),m(os.$$.fragment),bs=M(),m(q.$$.fragment),Is=M(),m(H.$$.fragment),_s=M(),m(is.$$.fragment),As=M(),cs=U("p"),this.h()},l(s){const l=Os("svelte-u9bgzb",document.head);e=J(l,"META",{name:!0,content:!0}),l.forEach(t),r=c(s),a=J(s,"P",{}),Ys(a).forEach(t),o=c(s),u(h.$$.fragment,s),C=c(s),u(A.$$.fragment,s),b=c(s),E=J(s,"P",{"data-svelte-h":!0}),$(E)!=="svelte-dwstrz"&&(E.textContent=B),I=c(s),G=J(s,"UL",{"data-svelte-h":!0}),$(G)!=="svelte-3bop09"&&(G.innerHTML=R),x=c(s),Z=J(s,"P",{"data-svelte-h":!0}),$(Z)!=="svelte-1kfpo64"&&(Z.innerHTML=i),g=c(s),u(_.$$.fragment,s),S=c(s),u(X.$$.fragment,s),v=c(s),V=J(s,"P",{"data-svelte-h":!0}),$(V)!=="svelte-pf8yi"&&(V.textContent=F),D=c(s),u(z.$$.fragment,s),Q=c(s),W=J(s,"P",{"data-svelte-h":!0}),$(W)!=="svelte-161h43k"&&(W.textContent=p),w=c(s),u(N.$$.fragment,s),ms=c(s),L=J(s,"P",{"data-svelte-h":!0}),$(L)!=="svelte-14mr2wr"&&(L.innerHTML=ks),us=c(s),u(P.$$.fragment,s),ds=c(s),u(K.$$.fragment,s),js=c(s),O=J(s,"P",{"data-svelte-h":!0}),$(O)!=="svelte-10ihzcv"&&(O.innerHTML=Es),ys=c(s),u(ss.$$.fragment,s),fs=c(s),es=J(s,"P",{"data-svelte-h":!0}),$(es)!=="svelte-1p9uuun"&&(es.textContent=Bs),hs=c(s),as=J(s,"OL",{"data-svelte-h":!0}),$(as)!=="svelte-1av8agk"&&(as.innerHTML=Xs),ws=c(s),ts=J(s,"P",{"data-svelte-h":!0}),$(ts)!=="svelte-x2vphs"&&(ts.innerHTML=vs),Us=c(s),u(ls.$$.fragment,s),Js=c(s),ns=J(s,"P",{"data-svelte-h":!0}),$(ns)!=="svelte-1eq69ea"&&(ns.innerHTML=Vs),Ts=c(s),u(ps.$$.fragment,s),gs=c(s),rs=J(s,"P",{"data-svelte-h":!0}),$(rs)!=="svelte-1w3gd6z"&&(rs.innerHTML=zs),$s=c(s),u(Y.$$.fragment,s),Cs=c(s),u(os.$$.fragment,s),bs=c(s),u(q.$$.fragment,s),Is=c(s),u(H.$$.fragment,s),_s=c(s),u(is.$$.fragment,s),As=c(s),cs=J(s,"P",{}),Ys(cs).forEach(t),this.h()},h(){qs(e,"name","hf:doc:metadata"),qs(e,"content",je)},m(s,l){se(document.head,e),n(s,r,l),n(s,a,l),n(s,o,l),d(h,s,l),n(s,C,l),d(A,s,l),n(s,b,l),n(s,E,l),n(s,I,l),n(s,G,l),n(s,x,l),n(s,Z,l),n(s,g,l),d(_,s,l),n(s,S,l),d(X,s,l),n(s,v,l),n(s,V,l),n(s,D,l),d(z,s,l),n(s,Q,l),n(s,W,l),n(s,w,l),d(N,s,l),n(s,ms,l),n(s,L,l),n(s,us,l),d(P,s,l),n(s,ds,l),d(K,s,l),n(s,js,l),n(s,O,l),n(s,ys,l),d(ss,s,l),n(s,fs,l),n(s,es,l),n(s,hs,l),n(s,as,l),n(s,ws,l),n(s,ts,l),n(s,Us,l),d(ls,s,l),n(s,Js,l),n(s,ns,l),n(s,Ts,l),d(ps,s,l),n(s,gs,l),n(s,rs,l),n(s,$s,l),d(Y,s,l),n(s,Cs,l),d(os,s,l),n(s,bs,l),d(q,s,l),n(s,Is,l),d(H,s,l),n(s,_s,l),d(is,s,l),n(s,As,l),n(s,cs,l),Zs=!0},p(s,[l]){const Qs={};l&2&&(Qs.$$scope={dirty:l,ctx:s}),_.$set(Qs);const Ws={};l&2&&(Ws.$$scope={dirty:l,ctx:s}),Y.$set(Ws);const Fs={};l&2&&(Fs.$$scope={dirty:l,ctx:s}),q.$set(Fs);const Ns={};l&2&&(Ns.$$scope={dirty:l,ctx:s}),H.$set(Ns)},i(s){Zs||(j(h.$$.fragment,s),j(A.$$.fragment,s),j(_.$$.fragment,s),j(X.$$.fragment,s),j(z.$$.fragment,s),j(N.$$.fragment,s),j(P.$$.fragment,s),j(K.$$.fragment,s),j(ss.$$.fragment,s),j(ls.$$.fragment,s),j(ps.$$.fragment,s),j(Y.$$.fragment,s),j(os.$$.fragment,s),j(q.$$.fragment,s),j(H.$$.fragment,s),j(is.$$.fragment,s),Zs=!0)},o(s){y(h.$$.fragment,s),y(A.$$.fragment,s),y(_.$$.fragment,s),y(X.$$.fragment,s),y(z.$$.fragment,s),y(N.$$.fragment,s),y(P.$$.fragment,s),y(K.$$.fragment,s),y(ss.$$.fragment,s),y(ls.$$.fragment,s),y(ps.$$.fragment,s),y(Y.$$.fragment,s),y(os.$$.fragment,s),y(q.$$.fragment,s),y(H.$$.fragment,s),y(is.$$.fragment,s),Zs=!1},d(s){s&&(t(r),t(a),t(o),t(C),t(b),t(E),t(I),t(G),t(x),t(Z),t(g),t(S),t(v),t(V),t(D),t(Q),t(W),t(w),t(ms),t(L),t(us),t(ds),t(js),t(O),t(ys),t(fs),t(es),t(hs),t(as),t(ws),t(ts),t(Us),t(Js),t(ns),t(Ts),t(gs),t(rs),t($s),t(Cs),t(bs),t(Is),t(_s),t(As),t(cs)),t(e),f(h,s),f(A,s),f(_,s),f(X,s),f(z,s),f(N,s),f(P,s),f(K,s),f(ss,s),f(ls,s),f(ps,s),f(Y,s),f(os,s),f(q,s),f(H,s),f(is,s)}}}const je='{"title":"Respuesta a preguntas","local":"respuesta-a-preguntas","sections":[{"title":"Carga el dataset SQuAD","local":"carga-el-dataset-squad","sections":[],"depth":2},{"title":"Preprocesamiento","local":"preprocesamiento","sections":[],"depth":2},{"title":"Entrenamiento","local":"entrenamiento","sections":[],"depth":2}],"depth":1}';function ye(T){return Ls(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class $e extends Ps{constructor(e){super(),Ks(this,e,ye,de,Ds,{})}}export{$e as component}; | |
Xet Storage Details
- Size:
- 37.1 kB
- Xet hash:
- 5d1a9c4b6b75523e3a00c47f1fc5fdc639a698c5304a6c2336a06905d9a65b10
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.