Buckets:
| import{s as Fe,o as Be,n as pt}from"../chunks/scheduler.5eb9d175.js";import{S as Ee,i as Qe,g as b,s as r,r as u,A as qe,h as j,f as l,c as o,j as Ne,u as $,x as T,k as ze,y as Se,a,v as d,d as M,t as h,w as g,m as Le,n as Ae}from"../chunks/index.fcdcb606.js";import{T as Et}from"../chunks/Tip.9272e506.js";import{Y as Pe}from"../chunks/Youtube.398fab2b.js";import{C as v}from"../chunks/CodeBlock.a7036e06.js";import{D as De}from"../chunks/DocNotebookDropdown.2547080e.js";import{F as we,M as zt}from"../chunks/Markdown.927e6a50.js";import{H as Nt,E as Ke}from"../chunks/EditOnGithub.98bf070f.js";function Oe(k){let e,m='لرؤية جميع البنى ونقاط التحقق المتوافقة مع هذه المهمة، نوصي بالتحقق من <a href="https://huggingface.co/tasks/text-classification" rel="nofollow">صفحة المهمة</a>.';return{c(){e=b("p"),e.innerHTML=m},l(s){e=j(s,"P",{"data-svelte-h":!0}),T(e)!=="svelte-e8lnkz"&&(e.innerHTML=m)},m(s,c){a(s,e,c)},p:pt,d(s){s&&l(e)}}}function ts(k){let e,m;return e=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERhdGFDb2xsYXRvcldpdGhQYWRkaW5nJTBBJTBBZGF0YV9jb2xsYXRvciUyMCUzRCUyMERhdGFDb2xsYXRvcldpdGhQYWRkaW5nKHRva2VuaXplciUzRHRva2VuaXplcik=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DataCollatorWithPadding | |
| <span class="hljs-meta">>>> </span>data_collator = DataCollatorWithPadding(tokenizer=tokenizer)`,wrap:!1}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p:pt,i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function es(k){let e,m;return e=new zt({props:{$$slots:{default:[ts]},$$scope:{ctx:k}}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p(s,c){const y={};c&2&&(y.$$scope={dirty:c,ctx:s}),e.$set(y)},i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function ss(k){let e,m;return e=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMERhdGFDb2xsYXRvcldpdGhQYWRkaW5nJTBBJTBBZGF0YV9jb2xsYXRvciUyMCUzRCUyMERhdGFDb2xsYXRvcldpdGhQYWRkaW5nKHRva2VuaXplciUzRHRva2VuaXplciUyQyUyMHJldHVybl90ZW5zb3JzJTNEJTIydGYlMjIp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DataCollatorWithPadding | |
| <span class="hljs-meta">>>> </span>data_collator = DataCollatorWithPadding(tokenizer=tokenizer, return_tensors=<span class="hljs-string">"tf"</span>)`,wrap:!1}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p:pt,i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function ls(k){let e,m;return e=new zt({props:{$$slots:{default:[ss]},$$scope:{ctx:k}}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p(s,c){const y={};c&2&&(y.$$scope={dirty:c,ctx:s}),e.$set(y)},i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function as(k){let e,m='إذا لم تكن على دراية بضبط نموذج دقيق باستخدام <code>Trainer</code>, فالق نظرة على البرنامج التعليمي الأساسي <a href="../training#train-with-pytorch-trainer">هنا</a>!';return{c(){e=b("p"),e.innerHTML=m},l(s){e=j(s,"P",{"data-svelte-h":!0}),T(e)!=="svelte-w6z43j"&&(e.innerHTML=m)},m(s,c){a(s,e,c)},p:pt,d(s){s&&l(e)}}}function ns(k){let e,m="يستخدم <code>Trainer</code> الحشو الديناميكي افتراضيًا عند تمرير <code>tokenizer</code> إليه. في هذه الحالة، لا تحتاج لتحديد مُجمِّع البيانات صراحةً.";return{c(){e=b("p"),e.innerHTML=m},l(s){e=j(s,"P",{"data-svelte-h":!0}),T(e)!=="svelte-10390hw"&&(e.innerHTML=m)},m(s,c){a(s,e,c)},p:pt,d(s){s&&l(e)}}}function ps(k){let e,m,s,c="أنت مستعد الآن لبدء تدريب نموذجك! قم بتحميل DistilBERT مع <code>AutoModelForSequenceClassification</code> جنبًا إلى جنب مع عدد التصنيفات المتوقعة، وتصنيفات الخرائط:",y,Z,V,W,C="في هذه المرحلة، هناك ثلاث خطوات فقط متبقية:",x,_,N="<li>حدد مُعامِلات التدريب في <code>TrainingArguments</code>. المُعامل المطلوب الوحيد هو <code>output_dir</code>، لتحديد مكان حفظ النموذج. يمكنك رفع النموذج إلى Hub بتعيين <code>push_to_hub=True</code> (يجب تسجيل الدخول إلى Hugging Face لرفع النموذج). سيقوم <code>Trainer</code> بتقييم الدقة وحفظ نقاط التحقق في نهاية كل حقبة.</li> <li>مرر مُعامِلات التدريب إلى <code>Trainer</code> مع النموذج، ومجموعة البيانات، والمحلل اللغوي، ومُجمِّع البيانات، ووظيفة <code>compute_metrics</code>.</li> <li>استدعِ <code>train()</code> لضبط النموذج.</li>",R,J,X,i,U,H,E="بعد اكتمال التدريب، شارك نموذجك على Hub باستخدام الطريقة <code>push_to_hub()</code> ليستخدمه الجميع:",Y,z,I;return e=new Et({props:{$$slots:{default:[as]},$$scope:{ctx:k}}}),Z=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMEF1dG9Nb2RlbEZvclNlcXVlbmNlQ2xhc3NpZmljYXRpb24lMkMlMjBUcmFpbmluZ0FyZ3VtZW50cyUyQyUyMFRyYWluZXIlMEElMEFtb2RlbCUyMCUzRCUyMEF1dG9Nb2RlbEZvclNlcXVlbmNlQ2xhc3NpZmljYXRpb24uZnJvbV9wcmV0cmFpbmVkKCUwQSUyMCUyMCUyMCUyMCUyMmRpc3RpbGJlcnQlMkZkaXN0aWxiZXJ0LWJhc2UtdW5jYXNlZCUyMiUyQyUyMG51bV9sYWJlbHMlM0QyJTJDJTIwaWQybGFiZWwlM0RpZDJsYWJlbCUyQyUyMGxhYmVsMmlkJTNEbGFiZWwyaWQlMEEp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForSequenceClassification, TrainingArguments, Trainer | |
| <span class="hljs-meta">>>> </span>model = AutoModelForSequenceClassification.from_pretrained( | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"distilbert/distilbert-base-uncased"</span>, num_labels=<span class="hljs-number">2</span>, id2label=id2label, label2id=label2id | |
| <span class="hljs-meta">... </span>)`,wrap:!1}}),J=new v({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">"my_awesome_model"</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">2</span>, | |
| <span class="hljs-meta">... </span> weight_decay=<span class="hljs-number">0.01</span>, | |
| <span class="hljs-meta">... </span> eval_strategy=<span class="hljs-string">"epoch"</span>, | |
| <span class="hljs-meta">... </span> save_strategy=<span class="hljs-string">"epoch"</span>, | |
| <span class="hljs-meta">... </span> load_best_model_at_end=<span class="hljs-literal">True</span>, | |
| <span class="hljs-meta">... </span> push_to_hub=<span class="hljs-literal">True</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_imdb[<span class="hljs-string">"train"</span>], | |
| <span class="hljs-meta">... </span> eval_dataset=tokenized_imdb[<span class="hljs-string">"test"</span>], | |
| <span class="hljs-meta">... </span> processing_class=tokenizer, | |
| <span class="hljs-meta">... </span> data_collator=data_collator, | |
| <span class="hljs-meta">... </span> compute_metrics=compute_metrics, | |
| <span class="hljs-meta">... </span>) | |
| <span class="hljs-meta">>>> </span>trainer.train()`,wrap:!1}}),i=new Et({props:{$$slots:{default:[ns]},$$scope:{ctx:k}}}),z=new v({props:{code:"dHJhaW5lci5wdXNoX3RvX2h1Yigp",highlighted:'<span class="hljs-meta">>>> </span>trainer.push_to_hub()',wrap:!1}}),{c(){u(e.$$.fragment),m=r(),s=b("p"),s.innerHTML=c,y=r(),u(Z.$$.fragment),V=r(),W=b("p"),W.textContent=C,x=r(),_=b("ol"),_.innerHTML=N,R=r(),u(J.$$.fragment),X=r(),u(i.$$.fragment),U=r(),H=b("p"),H.innerHTML=E,Y=r(),u(z.$$.fragment)},l(f){$(e.$$.fragment,f),m=o(f),s=j(f,"P",{"data-svelte-h":!0}),T(s)!=="svelte-1grj7j7"&&(s.innerHTML=c),y=o(f),$(Z.$$.fragment,f),V=o(f),W=j(f,"P",{"data-svelte-h":!0}),T(W)!=="svelte-js7en6"&&(W.textContent=C),x=o(f),_=j(f,"OL",{"data-svelte-h":!0}),T(_)!=="svelte-3osmkk"&&(_.innerHTML=N),R=o(f),$(J.$$.fragment,f),X=o(f),$(i.$$.fragment,f),U=o(f),H=j(f,"P",{"data-svelte-h":!0}),T(H)!=="svelte-1xlo2wh"&&(H.innerHTML=E),Y=o(f),$(z.$$.fragment,f)},m(f,G){d(e,f,G),a(f,m,G),a(f,s,G),a(f,y,G),d(Z,f,G),a(f,V,G),a(f,W,G),a(f,x,G),a(f,_,G),a(f,R,G),d(J,f,G),a(f,X,G),d(i,f,G),a(f,U,G),a(f,H,G),a(f,Y,G),d(z,f,G),I=!0},p(f,G){const F={};G&2&&(F.$$scope={dirty:G,ctx:f}),e.$set(F);const B={};G&2&&(B.$$scope={dirty:G,ctx:f}),i.$set(B)},i(f){I||(M(e.$$.fragment,f),M(Z.$$.fragment,f),M(J.$$.fragment,f),M(i.$$.fragment,f),M(z.$$.fragment,f),I=!0)},o(f){h(e.$$.fragment,f),h(Z.$$.fragment,f),h(J.$$.fragment,f),h(i.$$.fragment,f),h(z.$$.fragment,f),I=!1},d(f){f&&(l(m),l(s),l(y),l(V),l(W),l(x),l(_),l(R),l(X),l(U),l(H),l(Y)),g(e,f),g(Z,f),g(J,f),g(i,f),g(z,f)}}}function is(k){let e,m;return e=new zt({props:{$$slots:{default:[ps]},$$scope:{ctx:k}}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p(s,c){const y={};c&2&&(y.$$scope={dirty:c,ctx:s}),e.$set(y)},i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function rs(k){let e,m='إذا لم تكن على دراية بضبط نموذج باستخدام Keras، قم بالاطلاع على البرنامج التعليمي الأساسي <a href="../training#train-a-tensorflow-model-with-keras">هنا</a>!';return{c(){e=b("p"),e.innerHTML=m},l(s){e=j(s,"P",{"data-svelte-h":!0}),T(e)!=="svelte-1ne649t"&&(e.innerHTML=m)},m(s,c){a(s,e,c)},p:pt,d(s){s&&l(e)}}}function os(k){let e,m,s,c,y,Z="ثم يمكنك تحميل DistilBERT مع <code>TFAutoModelForSequenceClassification</code> بالإضافة إلى عدد التصنيفات المتوقعة، وتعيينات التسميات:",V,W,C,x,_="قم بتحويل مجموعات بياناتك إلى تنسيق <code>tf.data.Dataset</code> باستخدام <code>prepare_tf_dataset()</code>:",N,R,J,X,i='قم بتهيئة النموذج للتدريب باستخدام <a href="https://keras.io/api/models/model_training_apis/#compile-method" rel="nofollow"><code>compile</code></a>. لاحظ أن جميع نماذج Transformers لديها دالة خسارة ذات صلة بالمهمة بشكل افتراضي، لذلك لا تحتاج إلى تحديد واحدة ما لم ترغب في ذلك:',U,H,E,Y,z='آخر أمرين يجب إعدادهما قبل بدء التدريب هو حساب الدقة من التوقعات، وتوفير طريقة لدفع نموذجك إلى Hub. يتم ذلك باستخدام <a href="../main_classes/keras_callbacks">Keras callbacks</a>.',I,f,G="قم بتمرير دالة <code>compute_metrics</code> الخاصة بك إلى <code>KerasMetricCallback</code>:",F,B,Q,st,ct="حدد مكان دفع نموذجك والمجزئ اللغوي في <code>PushToHubCallback</code>:",q,S,L,A,lt="ثم اجمع الاستدعاءات معًا:",ft,P,D,K,at='أخيرًا، أنت مستعد لبدء تدريب نموذجك! قم باستدعاء <a href="https://keras.io/api/models/model_training_apis/#fit-method" rel="nofollow"><code>fit</code></a> مع مجموعات بيانات التدريب والتحقق، وعدد الحقبات، واستدعاءاتك لضبط النموذج:',ut,O,tt,et,nt="بمجرد اكتمال التدريب، يتم تحميل نموذجك تلقائيًا إلى Hub حتى يتمكن الجميع من استخدامه!",$t;return e=new Et({props:{$$slots:{default:[rs]},$$scope:{ctx:k}}}),s=new v({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><span class="hljs-keyword">import</span> tensorflow <span class="hljs-keyword">as</span> tf | |
| <span class="hljs-meta">>>> </span>batch_size = <span class="hljs-number">16</span> | |
| <span class="hljs-meta">>>> </span>num_epochs = <span class="hljs-number">5</span> | |
| <span class="hljs-meta">>>> </span>batches_per_epoch = <span class="hljs-built_in">len</span>(tokenized_imdb[<span class="hljs-string">"train"</span>]) // batch_size | |
| <span class="hljs-meta">>>> </span>total_train_steps = <span class="hljs-built_in">int</span>(batches_per_epoch * num_epochs) | |
| <span class="hljs-meta">>>> </span>optimizer, schedule = create_optimizer(init_lr=<span class="hljs-number">2e-5</span>, num_warmup_steps=<span class="hljs-number">0</span>, num_train_steps=total_train_steps)`,wrap:!1}}),W=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFRGQXV0b01vZGVsRm9yU2VxdWVuY2VDbGFzc2lmaWNhdGlvbiUwQSUwQW1vZGVsJTIwJTNEJTIwVEZBdXRvTW9kZWxGb3JTZXF1ZW5jZUNsYXNzaWZpY2F0aW9uLmZyb21fcHJldHJhaW5lZCglMEElMjAlMjAlMjAlMjAlMjJkaXN0aWxiZXJ0JTJGZGlzdGlsYmVydC1iYXNlLXVuY2FzZWQlMjIlMkMlMjBudW1fbGFiZWxzJTNEMiUyQyUyMGlkMmxhYmVsJTNEaWQybGFiZWwlMkMlMjBsYWJlbDJpZCUzRGxhYmVsMmlkJTBBKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFAutoModelForSequenceClassification | |
| <span class="hljs-meta">>>> </span>model = TFAutoModelForSequenceClassification.from_pretrained( | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"distilbert/distilbert-base-uncased"</span>, num_labels=<span class="hljs-number">2</span>, id2label=id2label, label2id=label2id | |
| <span class="hljs-meta">... </span>)`,wrap:!1}}),R=new v({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_imdb[<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_imdb[<span class="hljs-string">"test"</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}}),H=new v({props:{code:"aW1wb3J0JTIwdGVuc29yZmxvdyUyMGFzJTIwdGYlMEElMEFtb2RlbC5jb21waWxlKG9wdGltaXplciUzRG9wdGltaXplciklMjAlMjAlMjMlMjBObyUyMGxvc3MlMjBhcmd1bWVudCE=",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) <span class="hljs-comment"># No loss argument!</span>`,wrap:!1}}),B=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycy5rZXJhc19jYWxsYmFja3MlMjBpbXBvcnQlMjBLZXJhc01ldHJpY0NhbGxiYWNrJTBBJTBBbWV0cmljX2NhbGxiYWNrJTIwJTNEJTIwS2VyYXNNZXRyaWNDYWxsYmFjayhtZXRyaWNfZm4lM0Rjb21wdXRlX21ldHJpY3MlMkMlMjBldmFsX2RhdGFzZXQlM0R0Zl92YWxpZGF0aW9uX3NldCk=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers.keras_callbacks <span class="hljs-keyword">import</span> KerasMetricCallback | |
| <span class="hljs-meta">>>> </span>metric_callback = KerasMetricCallback(metric_fn=compute_metrics, eval_dataset=tf_validation_set)`,wrap:!1}}),S=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycy5rZXJhc19jYWxsYmFja3MlMjBpbXBvcnQlMjBQdXNoVG9IdWJDYWxsYmFjayUwQSUwQXB1c2hfdG9faHViX2NhbGxiYWNrJTIwJTNEJTIwUHVzaFRvSHViQ2FsbGJhY2soJTBBJTIwJTIwJTIwJTIwb3V0cHV0X2RpciUzRCUyMm15X2F3ZXNvbWVfbW9kZWwlMjIlMkMlMEElMjAlMjAlMjAlMjB0b2tlbml6ZXIlM0R0b2tlbml6ZXIlMkMlMEEp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers.keras_callbacks <span class="hljs-keyword">import</span> PushToHubCallback | |
| <span class="hljs-meta">>>> </span>push_to_hub_callback = PushToHubCallback( | |
| <span class="hljs-meta">... </span> output_dir=<span class="hljs-string">"my_awesome_model"</span>, | |
| <span class="hljs-meta">... </span> tokenizer=tokenizer, | |
| <span class="hljs-meta">... </span>)`,wrap:!1}}),P=new v({props:{code:"Y2FsbGJhY2tzJTIwJTNEJTIwJTVCbWV0cmljX2NhbGxiYWNrJTJDJTIwcHVzaF90b19odWJfY2FsbGJhY2slNUQ=",highlighted:'<span class="hljs-meta">>>> </span>callbacks = [metric_callback, push_to_hub_callback]',wrap:!1}}),O=new v({props:{code:"bW9kZWwuZml0KHglM0R0Zl90cmFpbl9zZXQlMkMlMjB2YWxpZGF0aW9uX2RhdGElM0R0Zl92YWxpZGF0aW9uX3NldCUyQyUyMGVwb2NocyUzRDMlMkMlMjBjYWxsYmFja3MlM0RjYWxsYmFja3Mp",highlighted:'<span class="hljs-meta">>>> </span>model.fit(x=tf_train_set, validation_data=tf_validation_set, epochs=<span class="hljs-number">3</span>, callbacks=callbacks)',wrap:!1}}),{c(){u(e.$$.fragment),m=Le(` | |
| لضبط نموذج في TensorFlow، ابدأ بإعداد دالة المحسن، وجدول معدل التعلم، وبعض معلمات التدريب: | |
| `),u(s.$$.fragment),c=r(),y=b("p"),y.innerHTML=Z,V=r(),u(W.$$.fragment),C=r(),x=b("p"),x.innerHTML=_,N=r(),u(R.$$.fragment),J=r(),X=b("p"),X.innerHTML=i,U=r(),u(H.$$.fragment),E=r(),Y=b("p"),Y.innerHTML=z,I=r(),f=b("p"),f.innerHTML=G,F=r(),u(B.$$.fragment),Q=r(),st=b("p"),st.innerHTML=ct,q=r(),u(S.$$.fragment),L=r(),A=b("p"),A.textContent=lt,ft=r(),u(P.$$.fragment),D=r(),K=b("p"),K.innerHTML=at,ut=r(),u(O.$$.fragment),tt=r(),et=b("p"),et.textContent=nt},l(p){$(e.$$.fragment,p),m=Ae(p,` | |
| لضبط نموذج في TensorFlow، ابدأ بإعداد دالة المحسن، وجدول معدل التعلم، وبعض معلمات التدريب: | |
| `),$(s.$$.fragment,p),c=o(p),y=j(p,"P",{"data-svelte-h":!0}),T(y)!=="svelte-8tmnh8"&&(y.innerHTML=Z),V=o(p),$(W.$$.fragment,p),C=o(p),x=j(p,"P",{"data-svelte-h":!0}),T(x)!=="svelte-1rim6wr"&&(x.innerHTML=_),N=o(p),$(R.$$.fragment,p),J=o(p),X=j(p,"P",{"data-svelte-h":!0}),T(X)!=="svelte-1dmvon3"&&(X.innerHTML=i),U=o(p),$(H.$$.fragment,p),E=o(p),Y=j(p,"P",{"data-svelte-h":!0}),T(Y)!=="svelte-1p8top0"&&(Y.innerHTML=z),I=o(p),f=j(p,"P",{"data-svelte-h":!0}),T(f)!=="svelte-p26coy"&&(f.innerHTML=G),F=o(p),$(B.$$.fragment,p),Q=o(p),st=j(p,"P",{"data-svelte-h":!0}),T(st)!=="svelte-1tj224v"&&(st.innerHTML=ct),q=o(p),$(S.$$.fragment,p),L=o(p),A=j(p,"P",{"data-svelte-h":!0}),T(A)!=="svelte-rbmmdr"&&(A.textContent=lt),ft=o(p),$(P.$$.fragment,p),D=o(p),K=j(p,"P",{"data-svelte-h":!0}),T(K)!=="svelte-1ydpuyn"&&(K.innerHTML=at),ut=o(p),$(O.$$.fragment,p),tt=o(p),et=j(p,"P",{"data-svelte-h":!0}),T(et)!=="svelte-2i53kw"&&(et.textContent=nt)},m(p,w){d(e,p,w),a(p,m,w),d(s,p,w),a(p,c,w),a(p,y,w),a(p,V,w),d(W,p,w),a(p,C,w),a(p,x,w),a(p,N,w),d(R,p,w),a(p,J,w),a(p,X,w),a(p,U,w),d(H,p,w),a(p,E,w),a(p,Y,w),a(p,I,w),a(p,f,w),a(p,F,w),d(B,p,w),a(p,Q,w),a(p,st,w),a(p,q,w),d(S,p,w),a(p,L,w),a(p,A,w),a(p,ft,w),d(P,p,w),a(p,D,w),a(p,K,w),a(p,ut,w),d(O,p,w),a(p,tt,w),a(p,et,w),$t=!0},p(p,w){const Ft={};w&2&&(Ft.$$scope={dirty:w,ctx:p}),e.$set(Ft)},i(p){$t||(M(e.$$.fragment,p),M(s.$$.fragment,p),M(W.$$.fragment,p),M(R.$$.fragment,p),M(H.$$.fragment,p),M(B.$$.fragment,p),M(S.$$.fragment,p),M(P.$$.fragment,p),M(O.$$.fragment,p),$t=!0)},o(p){h(e.$$.fragment,p),h(s.$$.fragment,p),h(W.$$.fragment,p),h(R.$$.fragment,p),h(H.$$.fragment,p),h(B.$$.fragment,p),h(S.$$.fragment,p),h(P.$$.fragment,p),h(O.$$.fragment,p),$t=!1},d(p){p&&(l(m),l(c),l(y),l(V),l(C),l(x),l(N),l(J),l(X),l(U),l(E),l(Y),l(I),l(f),l(F),l(Q),l(st),l(q),l(L),l(A),l(ft),l(D),l(K),l(ut),l(tt),l(et)),g(e,p),g(s,p),g(W,p),g(R,p),g(H,p),g(B,p),g(S,p),g(P,p),g(O,p)}}}function ms(k){let e,m;return e=new zt({props:{$$slots:{default:[os]},$$scope:{ctx:k}}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p(s,c){const y={};c&2&&(y.$$scope={dirty:c,ctx:s}),e.$set(y)},i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function cs(k){let e,m=`للحصول على مثال أكثر عمقًا حول كيفية ضبط نموذج لتصنيف النصوص، قم بالاطلاع على الدفتر المقابل | |
| <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification.ipynb" rel="nofollow">دفتر PyTorch</a> | |
| أو <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification-tf.ipynb" rel="nofollow">دفتر TensorFlow</a>.`;return{c(){e=b("p"),e.innerHTML=m},l(s){e=j(s,"P",{"data-svelte-h":!0}),T(e)!=="svelte-4b2ydh"&&(e.innerHTML=m)},m(s,c){a(s,e,c)},p:pt,d(s){s&&l(e)}}}function fs(k){let e,m="قم يتجزئة النص وإرجاع تنسورات PyTorch:",s,c,y,Z,V="مرر المدخلات إلى النموذج واسترجع <code>logits</code>:",W,C,x,_,N="استخرج الفئة ذات الاحتمالية الأعلى، واستخدم <code>id2label</code> لتحويلها إلى تصنيف نصي:",R,J,X;return c=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMEF1dG9Ub2tlbml6ZXIlMEElMEF0b2tlbml6ZXIlMjAlM0QlMjBBdXRvVG9rZW5pemVyLmZyb21fcHJldHJhaW5lZCglMjJzdGV2aGxpdSUyRm15X2F3ZXNvbWVfbW9kZWwlMjIpJTBBaW5wdXRzJTIwJTNEJTIwdG9rZW5pemVyKHRleHQlMkMlMjByZXR1cm5fdGVuc29ycyUzRCUyMnB0JTIyKQ==",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">"stevhliu/my_awesome_model"</span>) | |
| <span class="hljs-meta">>>> </span>inputs = tokenizer(text, return_tensors=<span class="hljs-string">"pt"</span>)`,wrap:!1}}),C=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMEF1dG9Nb2RlbEZvclNlcXVlbmNlQ2xhc3NpZmljYXRpb24lMEElMEFtb2RlbCUyMCUzRCUyMEF1dG9Nb2RlbEZvclNlcXVlbmNlQ2xhc3NpZmljYXRpb24uZnJvbV9wcmV0cmFpbmVkKCUyMnN0ZXZobGl1JTJGbXlfYXdlc29tZV9tb2RlbCUyMiklMEF3aXRoJTIwdG9yY2gubm9fZ3JhZCgpJTNBJTBBJTIwJTIwJTIwJTIwbG9naXRzJTIwJTNEJTIwbW9kZWwoKippbnB1dHMpLmxvZ2l0cw==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForSequenceClassification | |
| <span class="hljs-meta">>>> </span>model = AutoModelForSequenceClassification.from_pretrained(<span class="hljs-string">"stevhliu/my_awesome_model"</span>) | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">with</span> torch.no_grad(): | |
| <span class="hljs-meta">... </span> logits = model(**inputs).logits`,wrap:!1}}),J=new v({props:{code:"cHJlZGljdGVkX2NsYXNzX2lkJTIwJTNEJTIwbG9naXRzLmFyZ21heCgpLml0ZW0oKSUwQW1vZGVsLmNvbmZpZy5pZDJsYWJlbCU1QnByZWRpY3RlZF9jbGFzc19pZCU1RA==",highlighted:`<span class="hljs-meta">>>> </span>predicted_class_id = logits.argmax().item() | |
| <span class="hljs-meta">>>> </span>model.config.id2label[predicted_class_id] | |
| <span class="hljs-string">'POSITIVE'</span>`,wrap:!1}}),{c(){e=b("p"),e.textContent=m,s=r(),u(c.$$.fragment),y=r(),Z=b("p"),Z.innerHTML=V,W=r(),u(C.$$.fragment),x=r(),_=b("p"),_.innerHTML=N,R=r(),u(J.$$.fragment)},l(i){e=j(i,"P",{"data-svelte-h":!0}),T(e)!=="svelte-nf8blq"&&(e.textContent=m),s=o(i),$(c.$$.fragment,i),y=o(i),Z=j(i,"P",{"data-svelte-h":!0}),T(Z)!=="svelte-yov4ta"&&(Z.innerHTML=V),W=o(i),$(C.$$.fragment,i),x=o(i),_=j(i,"P",{"data-svelte-h":!0}),T(_)!=="svelte-1tpzhtv"&&(_.innerHTML=N),R=o(i),$(J.$$.fragment,i)},m(i,U){a(i,e,U),a(i,s,U),d(c,i,U),a(i,y,U),a(i,Z,U),a(i,W,U),d(C,i,U),a(i,x,U),a(i,_,U),a(i,R,U),d(J,i,U),X=!0},p:pt,i(i){X||(M(c.$$.fragment,i),M(C.$$.fragment,i),M(J.$$.fragment,i),X=!0)},o(i){h(c.$$.fragment,i),h(C.$$.fragment,i),h(J.$$.fragment,i),X=!1},d(i){i&&(l(e),l(s),l(y),l(Z),l(W),l(x),l(_),l(R)),g(c,i),g(C,i),g(J,i)}}}function us(k){let e,m;return e=new zt({props:{$$slots:{default:[fs]},$$scope:{ctx:k}}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p(s,c){const y={};c&2&&(y.$$scope={dirty:c,ctx:s}),e.$set(y)},i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function $s(k){let e,m="قم بتحليل النص وإرجاع تنسيقات TensorFlow:",s,c,y,Z,V="قم بتمرير مدخلاتك إلى النموذج وإرجاع <code>logits</code>:",W,C,x,_,N="استخرج الفئة ذات الاحتمالية الأعلى، واستخدم <code>id2label</code> لتحويلها إلى تصنيف نصي:",R,J,X;return c=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMEF1dG9Ub2tlbml6ZXIlMEElMEF0b2tlbml6ZXIlMjAlM0QlMjBBdXRvVG9rZW5pemVyLmZyb21fcHJldHJhaW5lZCglMjJzdGV2aGxpdSUyRm15X2F3ZXNvbWVfbW9kZWwlMjIpJTBBaW5wdXRzJTIwJTNEJTIwdG9rZW5pemVyKHRleHQlMkMlMjByZXR1cm5fdGVuc29ycyUzRCUyMnRmJTIyKQ==",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">"stevhliu/my_awesome_model"</span>) | |
| <span class="hljs-meta">>>> </span>inputs = tokenizer(text, return_tensors=<span class="hljs-string">"tf"</span>)`,wrap:!1}}),C=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMFRGQXV0b01vZGVsRm9yU2VxdWVuY2VDbGFzc2lmaWNhdGlvbiUwQSUwQW1vZGVsJTIwJTNEJTIwVEZBdXRvTW9kZWxGb3JTZXF1ZW5jZUNsYXNzaWZpY2F0aW9uLmZyb21fcHJldHJhaW5lZCglMjJzdGV2aGxpdSUyRm15X2F3ZXNvbWVfbW9kZWwlMjIpJTBBbG9naXRzJTIwJTNEJTIwbW9kZWwoKippbnB1dHMpLmxvZ2l0cw==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFAutoModelForSequenceClassification | |
| <span class="hljs-meta">>>> </span>model = TFAutoModelForSequenceClassification.from_pretrained(<span class="hljs-string">"stevhliu/my_awesome_model"</span>) | |
| <span class="hljs-meta">>>> </span>logits = model(**inputs).logits`,wrap:!1}}),J=new v({props:{code:"cHJlZGljdGVkX2NsYXNzX2lkJTIwJTNEJTIwaW50KHRmLm1hdGguYXJnbWF4KGxvZ2l0cyUyQyUyMGF4aXMlM0QtMSklNUIwJTVEKSUwQW1vZGVsLmNvbmZpZy5pZDJsYWJlbCU1QnByZWRpY3RlZF9jbGFzc19pZCU1RA==",highlighted:`<span class="hljs-meta">>>> </span>predicted_class_id = <span class="hljs-built_in">int</span>(tf.math.argmax(logits, axis=-<span class="hljs-number">1</span>)[<span class="hljs-number">0</span>]) | |
| <span class="hljs-meta">>>> </span>model.config.id2label[predicted_class_id] | |
| <span class="hljs-string">'POSITIVE'</span>`,wrap:!1}}),{c(){e=b("p"),e.textContent=m,s=r(),u(c.$$.fragment),y=r(),Z=b("p"),Z.innerHTML=V,W=r(),u(C.$$.fragment),x=r(),_=b("p"),_.innerHTML=N,R=r(),u(J.$$.fragment)},l(i){e=j(i,"P",{"data-svelte-h":!0}),T(e)!=="svelte-s59v6b"&&(e.textContent=m),s=o(i),$(c.$$.fragment,i),y=o(i),Z=j(i,"P",{"data-svelte-h":!0}),T(Z)!=="svelte-jqu6gj"&&(Z.innerHTML=V),W=o(i),$(C.$$.fragment,i),x=o(i),_=j(i,"P",{"data-svelte-h":!0}),T(_)!=="svelte-1tpzhtv"&&(_.innerHTML=N),R=o(i),$(J.$$.fragment,i)},m(i,U){a(i,e,U),a(i,s,U),d(c,i,U),a(i,y,U),a(i,Z,U),a(i,W,U),d(C,i,U),a(i,x,U),a(i,_,U),a(i,R,U),d(J,i,U),X=!0},p:pt,i(i){X||(M(c.$$.fragment,i),M(C.$$.fragment,i),M(J.$$.fragment,i),X=!0)},o(i){h(c.$$.fragment,i),h(C.$$.fragment,i),h(J.$$.fragment,i),X=!1},d(i){i&&(l(e),l(s),l(y),l(Z),l(W),l(x),l(_),l(R)),g(c,i),g(C,i),g(J,i)}}}function ds(k){let e,m;return e=new zt({props:{$$slots:{default:[$s]},$$scope:{ctx:k}}}),{c(){u(e.$$.fragment)},l(s){$(e.$$.fragment,s)},m(s,c){d(e,s,c),m=!0},p(s,c){const y={};c&2&&(y.$$scope={dirty:c,ctx:s}),e.$set(y)},i(s){m||(M(e.$$.fragment,s),m=!0)},o(s){h(e.$$.fragment,s),m=!1},d(s){g(e,s)}}}function Ms(k){let e,m,s,c,y,Z,V,W,C,x,_,N="تصنيف النص هو مهمة NLP شائعة حيث يُعيّن تصنيفًا أو فئة للنص. تستخدم بعض أكبر الشركات تصنيف النصوص في الإنتاج لمجموعة واسعة من التطبيقات العملية. أحد أكثر أشكال تصنيف النص شيوعًا هو تحليل المشاعر، والذي يقوم بتعيين تسمية مثل 🙂 إيجابية، 🙁 سلبية، أو 😐 محايدة لتسلسل نصي.",R,J,X="سيوضح لك هذا الدليل كيفية:",i,U,H='<li>ضبط <a href="https://huggingface.co/distilbert/distilbert-base-uncased" rel="nofollow">DistilBERT</a> على مجموعة بيانات <a href="https://huggingface.co/datasets/imdb" rel="nofollow">IMDb</a> لتحديد ما إذا كانت مراجعة الفيلم إيجابية أو سلبية.</li> <li>استخدام نموذج الضبط الدقيق للتنبؤ.</li>',E,Y,z,I,f="قبل أن تبدأ، تأكد من تثبيت جميع المكتبات الضرورية:",G,F,B,Q,st="نحن نشجعك على تسجيل الدخول إلى حساب Hugging Face الخاص بك حتى تتمكن من تحميل ومشاركة نموذجك مع المجتمع. عند المطالبة، أدخل رمزك لتسجيل الدخول:",ct,q,S,L,A,lt,ft="ابدأ بتحميل مجموعة بيانات IMDb من مكتبة 🤗 Datasets:",P,D,K,at,ut="ثم ألق نظرة على مثال:",O,tt,et,nt,$t="هناك حقولان في هذه المجموعة من البيانات:",p,w,Ft="<li><code>text</code>: نص مراجعة الفيلم.</li> <li><code>label</code>: قيمة إما <code>0</code> لمراجعة سلبية أو <code>1</code> لمراجعة إيجابية.</li>",Qt,dt,qt,Mt,Te="الخطوة التالية هي تحميل المُجزِّئ النص DistilBERT لتهيئة لحقل <code>text</code>:",St,ht,Lt,gt,Ue="أنشئ دالة لتهيئة حقل <code>text</code> وتقصير السلاسل النصية بحيث لا يتجاوز طولها الحد الأقصى لإدخالات DistilBERT:",At,yt,Pt,bt,Je="لتطبيق دالة التهيئة على مجموعة البيانات بأكملها، استخدم دالة 🤗 Datasets <code>map</code> . يمكنك تسريع <code>map</code> باستخدام <code>batched=True</code> لمعالجة دفعات من البيانات:",Dt,jt,Kt,wt,_e="الآن قم بإنشاء دفعة من الأمثلة باستخدام <code>DataCollatorWithPadding</code>. الأكثر كفاءة هو استخدام الحشو الديناميكي لجعل الجمل متساوية في الطول داخل كل دفعة، بدلًا من حشو كامل البيانات إلى الحد الأقصى للطول.",Ot,it,te,Tt,ee,Ut,ke='يُعدّ تضمين مقياس أثناء التدريب مفيدًا لتقييم أداء النموذج. يمكنك تحميل طريقة تقييم بسرعة باستخدام مكتبة 🤗 <a href="https://huggingface.co/docs/evaluate/index" rel="nofollow">Evaluate</a> . بالنسبة لهذه المهمة، قم بتحميل مقياس <a href="https://huggingface.co/spaces/evaluate-metric/accuracy" rel="nofollow">الدقة</a> (راجع جولة 🤗 Evaluate <a href="https://huggingface.co/docs/evaluate/a_quick_tour" rel="nofollow">السريعة</a> لمعرفة المزيد حول كيفية تحميل وحساب مقياس):',se,Jt,le,_t,Ze="ثم أنشئ دالة تقوم بتمرير تنبؤاتك وتصنيفاتك إلى <code>compute</code> لحساب الدقة:",ae,kt,ne,Zt,Ce="دالة <code>compute_metrics</code> جاهزة الآن، وستعود إليها عند إعداد التدريب.",pe,Ct,ie,vt,ve="قبل أن تبدأ في تدريب نموذجك، قم بإنشاء خريطة من المعرفات المتوقعة إلى تسمياتها باستخدام <code>id2label</code> و <code>label2id</code>:",re,Wt,oe,rt,me,ot,ce,Gt,fe,xt,We="رائع، الآن بعد أن قمت بضبط نموذج، يمكنك استخدامه للاستدلال!",ue,Rt,Ge="احصل على بعض النصوص التي ترغب في إجراء الاستدلال عليها:",$e,Xt,de,Vt,xe="أسهل طريقة لتجربة النموذج المضبوط للاستدلال هي استخدامه ضمن <code>pipeline()</code>. قم بإنشاء <code>pipeline</code> لتحليل المشاعر مع نموذجك، ومرر نصك إليه:",Me,Yt,he,Ht,Re="يمكنك أيضًا تكرار نتائج <code>pipeline</code> يدويًا إذا أردت:",ge,mt,ye,It,be,Bt,je;return y=new Nt({props:{title:"تصنيف النص(Text classification)",local:"تصنيف-النصtext-classification",headingTag:"h1"}}),V=new De({props:{classNames:"absolute z-10 right-0 top-0",options:[{label:"Mixed",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/transformers_doc/ar/sequence_classification.ipynb"},{label:"PyTorch",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/transformers_doc/ar/pytorch/sequence_classification.ipynb"},{label:"TensorFlow",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/transformers_doc/ar/tensorflow/sequence_classification.ipynb"},{label:"Mixed",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/transformers_doc/ar/sequence_classification.ipynb"},{label:"PyTorch",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/transformers_doc/ar/pytorch/sequence_classification.ipynb"},{label:"TensorFlow",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/transformers_doc/ar/tensorflow/sequence_classification.ipynb"}]}}),C=new Pe({props:{id:"leNG9fN9FQU"}}),Y=new Et({props:{$$slots:{default:[Oe]},$$scope:{ctx:k}}}),F=new v({props:{code:"cGlwJTIwaW5zdGFsbCUyMHRyYW5zZm9ybWVycyUyMGRhdGFzZXRzJTIwZXZhbHVhdGUlMjBhY2NlbGVyYXRl",highlighted:"pip install transformers datasets evaluate accelerate",wrap:!1}}),q=new v({props:{code:"ZnJvbSUyMGh1Z2dpbmdmYWNlX2h1YiUyMGltcG9ydCUyMG5vdGVib29rX2xvZ2luJTBBJTBBbm90ZWJvb2tfbG9naW4oKQ==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> notebook_login | |
| <span class="hljs-meta">>>> </span>notebook_login()`,wrap:!1}}),L=new Nt({props:{title:"تحميل مجموعة بيانات IMDb",local:"تحميل-مجموعة-بيانات-imdb",headingTag:"h2"}}),D=new v({props:{code:"ZnJvbSUyMGRhdGFzZXRzJTIwaW1wb3J0JTIwbG9hZF9kYXRhc2V0JTBBJTBBaW1kYiUyMCUzRCUyMGxvYWRfZGF0YXNldCglMjJpbWRiJTIyKQ==",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>imdb = load_dataset(<span class="hljs-string">"imdb"</span>)`,wrap:!1}}),tt=new v({props:{code:"aW1kYiU1QiUyMnRlc3QlMjIlNUQlNUIwJTVE",highlighted:`<span class="hljs-meta">>>> </span>imdb[<span class="hljs-string">"test"</span>][<span class="hljs-number">0</span>] | |
| { | |
| <span class="hljs-string">"label"</span>: <span class="hljs-number">0</span>, | |
| <span class="hljs-string">"text"</span>: <span class="hljs-string">"I love sci-fi and am willing to put up with a lot. Sci-fi movies/TV are usually underfunded, under-appreciated and misunderstood. I tried to like this, I really did, but it is to good TV sci-fi as Babylon 5 is to Star Trek (the original). Silly prosthetics, cheap cardboard sets, stilted dialogues, CG that doesn't match the background, and painfully one-dimensional characters cannot be overcome with a 'sci-fi' setting. (I'm sure there are those of you out there who think Babylon 5 is good sci-fi TV. It's not. It's clichéd and uninspiring.) While US viewers might like emotion and character development, sci-fi is a genre that does not take itself seriously (cf. Star Trek). It may treat important issues, yet not as a serious philosophy. It's really difficult to care about the characters here as they are not simply foolish, just missing a spark of life. Their actions and reactions are wooden and predictable, often painful to watch. The makers of Earth KNOW it's rubbish as they have to always say \\"Gene Roddenberry's Earth...\\" otherwise people would not continue watching. Roddenberry's ashes must be turning in their orbit as this dull, cheap, poorly edited (watching it without advert breaks really brings this home) trudging Trabant of a show lumbers into space. Spoiler. So, kill off a main character. And then bring him back as another actor. Jeeez! Dallas all over again."</span>, | |
| }`,wrap:!1}}),dt=new Nt({props:{title:"المعالجة المسبقة(Preprocess)",local:"المعالجة-المسبقةpreprocess",headingTag:"h2"}}),ht=new v({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}}),yt=new v({props:{code:"ZGVmJTIwcHJlcHJvY2Vzc19mdW5jdGlvbihleGFtcGxlcyklM0ElMEElMjAlMjAlMjAlMjByZXR1cm4lMjB0b2tlbml6ZXIoZXhhbXBsZXMlNUIlMjJ0ZXh0JTIyJTVEJTJDJTIwdHJ1bmNhdGlvbiUzRFRydWUp",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> <span class="hljs-keyword">return</span> tokenizer(examples[<span class="hljs-string">"text"</span>], truncation=<span class="hljs-literal">True</span>)`,wrap:!1}}),jt=new v({props:{code:"dG9rZW5pemVkX2ltZGIlMjAlM0QlMjBpbWRiLm1hcChwcmVwcm9jZXNzX2Z1bmN0aW9uJTJDJTIwYmF0Y2hlZCUzRFRydWUp",highlighted:'tokenized_imdb = imdb.<span class="hljs-built_in">map</span>(preprocess_function, batched=<span class="hljs-literal">True</span>)',wrap:!1}}),it=new we({props:{pytorch:!0,tensorflow:!0,jax:!1,$$slots:{tensorflow:[ls],pytorch:[es]},$$scope:{ctx:k}}}),Tt=new Nt({props:{title:"التقييم(Evaluate)",local:"التقييمevaluate",headingTag:"h2"}}),Jt=new v({props:{code:"aW1wb3J0JTIwZXZhbHVhdGUlMEElMEFhY2N1cmFjeSUyMCUzRCUyMGV2YWx1YXRlLmxvYWQoJTIyYWNjdXJhY3klMjIp",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> evaluate | |
| <span class="hljs-meta">>>> </span>accuracy = evaluate.load(<span class="hljs-string">"accuracy"</span>)`,wrap:!1}}),kt=new v({props:{code:"aW1wb3J0JTIwbnVtcHklMjBhcyUyMG5wJTBBJTBBZGVmJTIwY29tcHV0ZV9tZXRyaWNzKGV2YWxfcHJlZCklM0ElMEElMjAlMjAlMjAlMjBwcmVkaWN0aW9ucyUyQyUyMGxhYmVscyUyMCUzRCUyMGV2YWxfcHJlZCUwQSUyMCUyMCUyMCUyMHByZWRpY3Rpb25zJTIwJTNEJTIwbnAuYXJnbWF4KHByZWRpY3Rpb25zJTJDJTIwYXhpcyUzRDEpJTBBJTIwJTIwJTIwJTIwcmV0dXJuJTIwYWNjdXJhY3kuY29tcHV0ZShwcmVkaWN0aW9ucyUzRHByZWRpY3Rpb25zJTJDJTIwcmVmZXJlbmNlcyUzRGxhYmVscyk=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">compute_metrics</span>(<span class="hljs-params">eval_pred</span>): | |
| <span class="hljs-meta">... </span> predictions, labels = eval_pred | |
| <span class="hljs-meta">... </span> predictions = np.argmax(predictions, axis=<span class="hljs-number">1</span>) | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> accuracy.compute(predictions=predictions, references=labels)`,wrap:!1}}),Ct=new Nt({props:{title:"التدريب(Train)",local:"التدريبtrain",headingTag:"h2"}}),Wt=new v({props:{code:"aWQybGFiZWwlMjAlM0QlMjAlN0IwJTNBJTIwJTIyTkVHQVRJVkUlMjIlMkMlMjAxJTNBJTIwJTIyUE9TSVRJVkUlMjIlN0QlMEFsYWJlbDJpZCUyMCUzRCUyMCU3QiUyMk5FR0FUSVZFJTIyJTNBJTIwMCUyQyUyMCUyMlBPU0lUSVZFJTIyJTNBJTIwMSU3RA==",highlighted:`<span class="hljs-meta">>>> </span>id2label = {<span class="hljs-number">0</span>: <span class="hljs-string">"NEGATIVE"</span>, <span class="hljs-number">1</span>: <span class="hljs-string">"POSITIVE"</span>} | |
| <span class="hljs-meta">>>> </span>label2id = {<span class="hljs-string">"NEGATIVE"</span>: <span class="hljs-number">0</span>, <span class="hljs-string">"POSITIVE"</span>: <span class="hljs-number">1</span>}`,wrap:!1}}),rt=new we({props:{pytorch:!0,tensorflow:!0,jax:!1,$$slots:{tensorflow:[ms],pytorch:[is]},$$scope:{ctx:k}}}),ot=new Et({props:{$$slots:{default:[cs]},$$scope:{ctx:k}}}),Gt=new Nt({props:{title:"الاستدلال(Inference)",local:"الاستدلالinference",headingTag:"h2"}}),Xt=new v({props:{code:"dGV4dCUyMCUzRCUyMCUyMlRoaXMlMjB3YXMlMjBhJTIwbWFzdGVycGllY2UuJTIwTm90JTIwY29tcGxldGVseSUyMGZhaXRoZnVsJTIwdG8lMjB0aGUlMjBib29rcyUyQyUyMGJ1dCUyMGVudGhyYWxsaW5nJTIwZnJvbSUyMGJlZ2lubmluZyUyMHRvJTIwZW5kLiUyME1pZ2h0JTIwYmUlMjBteSUyMGZhdm9yaXRlJTIwb2YlMjB0aGUlMjB0aHJlZS4lMjI=",highlighted:'<span class="hljs-meta">>>> </span>text = <span class="hljs-string">"This was a masterpiece. Not completely faithful to the books, but enthralling from beginning to end. Might be my favorite of the three."</span>',wrap:!1}}),Yt=new v({props:{code:"ZnJvbSUyMHRyYW5zZm9ybWVycyUyMGltcG9ydCUyMHBpcGVsaW5lJTBBJTBBY2xhc3NpZmllciUyMCUzRCUyMHBpcGVsaW5lKCUyMnNlbnRpbWVudC1hbmFseXNpcyUyMiUyQyUyMG1vZGVsJTNEJTIyc3RldmhsaXUlMkZteV9hd2Vzb21lX21vZGVsJTIyKSUwQWNsYXNzaWZpZXIodGV4dCk=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline | |
| <span class="hljs-meta">>>> </span>classifier = pipeline(<span class="hljs-string">"sentiment-analysis"</span>, model=<span class="hljs-string">"stevhliu/my_awesome_model"</span>) | |
| <span class="hljs-meta">>>> </span>classifier(text) | |
| [{<span class="hljs-string">'label'</span>: <span class="hljs-string">'POSITIVE'</span>, <span class="hljs-string">'score'</span>: <span class="hljs-number">0.9994940757751465</span>}]`,wrap:!1}}),mt=new we({props:{pytorch:!0,tensorflow:!0,jax:!1,$$slots:{tensorflow:[ds],pytorch:[us]},$$scope:{ctx:k}}}),It=new Ke({props:{source:"https://github.com/huggingface/transformers/blob/main/docs/source/ar/tasks/sequence_classification.md"}}),{c(){e=b("meta"),m=r(),s=b("p"),c=r(),u(y.$$.fragment),Z=r(),u(V.$$.fragment),W=r(),u(C.$$.fragment),x=r(),_=b("p"),_.textContent=N,R=r(),J=b("p"),J.textContent=X,i=r(),U=b("ol"),U.innerHTML=H,E=r(),u(Y.$$.fragment),z=r(),I=b("p"),I.textContent=f,G=r(),u(F.$$.fragment),B=r(),Q=b("p"),Q.textContent=st,ct=r(),u(q.$$.fragment),S=r(),u(L.$$.fragment),A=r(),lt=b("p"),lt.textContent=ft,P=r(),u(D.$$.fragment),K=r(),at=b("p"),at.textContent=ut,O=r(),u(tt.$$.fragment),et=r(),nt=b("p"),nt.textContent=$t,p=r(),w=b("ul"),w.innerHTML=Ft,Qt=r(),u(dt.$$.fragment),qt=r(),Mt=b("p"),Mt.innerHTML=Te,St=r(),u(ht.$$.fragment),Lt=r(),gt=b("p"),gt.innerHTML=Ue,At=r(),u(yt.$$.fragment),Pt=r(),bt=b("p"),bt.innerHTML=Je,Dt=r(),u(jt.$$.fragment),Kt=r(),wt=b("p"),wt.innerHTML=_e,Ot=r(),u(it.$$.fragment),te=r(),u(Tt.$$.fragment),ee=r(),Ut=b("p"),Ut.innerHTML=ke,se=r(),u(Jt.$$.fragment),le=r(),_t=b("p"),_t.innerHTML=Ze,ae=r(),u(kt.$$.fragment),ne=r(),Zt=b("p"),Zt.innerHTML=Ce,pe=r(),u(Ct.$$.fragment),ie=r(),vt=b("p"),vt.innerHTML=ve,re=r(),u(Wt.$$.fragment),oe=r(),u(rt.$$.fragment),me=r(),u(ot.$$.fragment),ce=r(),u(Gt.$$.fragment),fe=r(),xt=b("p"),xt.textContent=We,ue=r(),Rt=b("p"),Rt.textContent=Ge,$e=r(),u(Xt.$$.fragment),de=r(),Vt=b("p"),Vt.innerHTML=xe,Me=r(),u(Yt.$$.fragment),he=r(),Ht=b("p"),Ht.innerHTML=Re,ge=r(),u(mt.$$.fragment),ye=r(),u(It.$$.fragment),be=r(),Bt=b("p"),this.h()},l(t){const n=qe("svelte-u9bgzb",document.head);e=j(n,"META",{name:!0,content:!0}),n.forEach(l),m=o(t),s=j(t,"P",{}),Ne(s).forEach(l),c=o(t),$(y.$$.fragment,t),Z=o(t),$(V.$$.fragment,t),W=o(t),$(C.$$.fragment,t),x=o(t),_=j(t,"P",{"data-svelte-h":!0}),T(_)!=="svelte-1xrvy97"&&(_.textContent=N),R=o(t),J=j(t,"P",{"data-svelte-h":!0}),T(J)!=="svelte-lp8700"&&(J.textContent=X),i=o(t),U=j(t,"OL",{"data-svelte-h":!0}),T(U)!=="svelte-xbekkz"&&(U.innerHTML=H),E=o(t),$(Y.$$.fragment,t),z=o(t),I=j(t,"P",{"data-svelte-h":!0}),T(I)!=="svelte-93upt2"&&(I.textContent=f),G=o(t),$(F.$$.fragment,t),B=o(t),Q=j(t,"P",{"data-svelte-h":!0}),T(Q)!=="svelte-nxp67a"&&(Q.textContent=st),ct=o(t),$(q.$$.fragment,t),S=o(t),$(L.$$.fragment,t),A=o(t),lt=j(t,"P",{"data-svelte-h":!0}),T(lt)!=="svelte-y4jgtl"&&(lt.textContent=ft),P=o(t),$(D.$$.fragment,t),K=o(t),at=j(t,"P",{"data-svelte-h":!0}),T(at)!=="svelte-1e1soci"&&(at.textContent=ut),O=o(t),$(tt.$$.fragment,t),et=o(t),nt=j(t,"P",{"data-svelte-h":!0}),T(nt)!=="svelte-j8kmh9"&&(nt.textContent=$t),p=o(t),w=j(t,"UL",{"data-svelte-h":!0}),T(w)!=="svelte-g2znyk"&&(w.innerHTML=Ft),Qt=o(t),$(dt.$$.fragment,t),qt=o(t),Mt=j(t,"P",{"data-svelte-h":!0}),T(Mt)!=="svelte-6tu8m4"&&(Mt.innerHTML=Te),St=o(t),$(ht.$$.fragment,t),Lt=o(t),gt=j(t,"P",{"data-svelte-h":!0}),T(gt)!=="svelte-158epvi"&&(gt.innerHTML=Ue),At=o(t),$(yt.$$.fragment,t),Pt=o(t),bt=j(t,"P",{"data-svelte-h":!0}),T(bt)!=="svelte-ld3zxw"&&(bt.innerHTML=Je),Dt=o(t),$(jt.$$.fragment,t),Kt=o(t),wt=j(t,"P",{"data-svelte-h":!0}),T(wt)!=="svelte-1ppw3b9"&&(wt.innerHTML=_e),Ot=o(t),$(it.$$.fragment,t),te=o(t),$(Tt.$$.fragment,t),ee=o(t),Ut=j(t,"P",{"data-svelte-h":!0}),T(Ut)!=="svelte-14bxn60"&&(Ut.innerHTML=ke),se=o(t),$(Jt.$$.fragment,t),le=o(t),_t=j(t,"P",{"data-svelte-h":!0}),T(_t)!=="svelte-1cxzzgk"&&(_t.innerHTML=Ze),ae=o(t),$(kt.$$.fragment,t),ne=o(t),Zt=j(t,"P",{"data-svelte-h":!0}),T(Zt)!=="svelte-mgw99j"&&(Zt.innerHTML=Ce),pe=o(t),$(Ct.$$.fragment,t),ie=o(t),vt=j(t,"P",{"data-svelte-h":!0}),T(vt)!=="svelte-1tqah9g"&&(vt.innerHTML=ve),re=o(t),$(Wt.$$.fragment,t),oe=o(t),$(rt.$$.fragment,t),me=o(t),$(ot.$$.fragment,t),ce=o(t),$(Gt.$$.fragment,t),fe=o(t),xt=j(t,"P",{"data-svelte-h":!0}),T(xt)!=="svelte-25dfys"&&(xt.textContent=We),ue=o(t),Rt=j(t,"P",{"data-svelte-h":!0}),T(Rt)!=="svelte-yq37kg"&&(Rt.textContent=Ge),$e=o(t),$(Xt.$$.fragment,t),de=o(t),Vt=j(t,"P",{"data-svelte-h":!0}),T(Vt)!=="svelte-1jztuub"&&(Vt.innerHTML=xe),Me=o(t),$(Yt.$$.fragment,t),he=o(t),Ht=j(t,"P",{"data-svelte-h":!0}),T(Ht)!=="svelte-asb9jo"&&(Ht.innerHTML=Re),ge=o(t),$(mt.$$.fragment,t),ye=o(t),$(It.$$.fragment,t),be=o(t),Bt=j(t,"P",{}),Ne(Bt).forEach(l),this.h()},h(){ze(e,"name","hf:doc:metadata"),ze(e,"content",hs)},m(t,n){Se(document.head,e),a(t,m,n),a(t,s,n),a(t,c,n),d(y,t,n),a(t,Z,n),d(V,t,n),a(t,W,n),d(C,t,n),a(t,x,n),a(t,_,n),a(t,R,n),a(t,J,n),a(t,i,n),a(t,U,n),a(t,E,n),d(Y,t,n),a(t,z,n),a(t,I,n),a(t,G,n),d(F,t,n),a(t,B,n),a(t,Q,n),a(t,ct,n),d(q,t,n),a(t,S,n),d(L,t,n),a(t,A,n),a(t,lt,n),a(t,P,n),d(D,t,n),a(t,K,n),a(t,at,n),a(t,O,n),d(tt,t,n),a(t,et,n),a(t,nt,n),a(t,p,n),a(t,w,n),a(t,Qt,n),d(dt,t,n),a(t,qt,n),a(t,Mt,n),a(t,St,n),d(ht,t,n),a(t,Lt,n),a(t,gt,n),a(t,At,n),d(yt,t,n),a(t,Pt,n),a(t,bt,n),a(t,Dt,n),d(jt,t,n),a(t,Kt,n),a(t,wt,n),a(t,Ot,n),d(it,t,n),a(t,te,n),d(Tt,t,n),a(t,ee,n),a(t,Ut,n),a(t,se,n),d(Jt,t,n),a(t,le,n),a(t,_t,n),a(t,ae,n),d(kt,t,n),a(t,ne,n),a(t,Zt,n),a(t,pe,n),d(Ct,t,n),a(t,ie,n),a(t,vt,n),a(t,re,n),d(Wt,t,n),a(t,oe,n),d(rt,t,n),a(t,me,n),d(ot,t,n),a(t,ce,n),d(Gt,t,n),a(t,fe,n),a(t,xt,n),a(t,ue,n),a(t,Rt,n),a(t,$e,n),d(Xt,t,n),a(t,de,n),a(t,Vt,n),a(t,Me,n),d(Yt,t,n),a(t,he,n),a(t,Ht,n),a(t,ge,n),d(mt,t,n),a(t,ye,n),d(It,t,n),a(t,be,n),a(t,Bt,n),je=!0},p(t,[n]){const Xe={};n&2&&(Xe.$$scope={dirty:n,ctx:t}),Y.$set(Xe);const Ve={};n&2&&(Ve.$$scope={dirty:n,ctx:t}),it.$set(Ve);const Ye={};n&2&&(Ye.$$scope={dirty:n,ctx:t}),rt.$set(Ye);const He={};n&2&&(He.$$scope={dirty:n,ctx:t}),ot.$set(He);const Ie={};n&2&&(Ie.$$scope={dirty:n,ctx:t}),mt.$set(Ie)},i(t){je||(M(y.$$.fragment,t),M(V.$$.fragment,t),M(C.$$.fragment,t),M(Y.$$.fragment,t),M(F.$$.fragment,t),M(q.$$.fragment,t),M(L.$$.fragment,t),M(D.$$.fragment,t),M(tt.$$.fragment,t),M(dt.$$.fragment,t),M(ht.$$.fragment,t),M(yt.$$.fragment,t),M(jt.$$.fragment,t),M(it.$$.fragment,t),M(Tt.$$.fragment,t),M(Jt.$$.fragment,t),M(kt.$$.fragment,t),M(Ct.$$.fragment,t),M(Wt.$$.fragment,t),M(rt.$$.fragment,t),M(ot.$$.fragment,t),M(Gt.$$.fragment,t),M(Xt.$$.fragment,t),M(Yt.$$.fragment,t),M(mt.$$.fragment,t),M(It.$$.fragment,t),je=!0)},o(t){h(y.$$.fragment,t),h(V.$$.fragment,t),h(C.$$.fragment,t),h(Y.$$.fragment,t),h(F.$$.fragment,t),h(q.$$.fragment,t),h(L.$$.fragment,t),h(D.$$.fragment,t),h(tt.$$.fragment,t),h(dt.$$.fragment,t),h(ht.$$.fragment,t),h(yt.$$.fragment,t),h(jt.$$.fragment,t),h(it.$$.fragment,t),h(Tt.$$.fragment,t),h(Jt.$$.fragment,t),h(kt.$$.fragment,t),h(Ct.$$.fragment,t),h(Wt.$$.fragment,t),h(rt.$$.fragment,t),h(ot.$$.fragment,t),h(Gt.$$.fragment,t),h(Xt.$$.fragment,t),h(Yt.$$.fragment,t),h(mt.$$.fragment,t),h(It.$$.fragment,t),je=!1},d(t){t&&(l(m),l(s),l(c),l(Z),l(W),l(x),l(_),l(R),l(J),l(i),l(U),l(E),l(z),l(I),l(G),l(B),l(Q),l(ct),l(S),l(A),l(lt),l(P),l(K),l(at),l(O),l(et),l(nt),l(p),l(w),l(Qt),l(qt),l(Mt),l(St),l(Lt),l(gt),l(At),l(Pt),l(bt),l(Dt),l(Kt),l(wt),l(Ot),l(te),l(ee),l(Ut),l(se),l(le),l(_t),l(ae),l(ne),l(Zt),l(pe),l(ie),l(vt),l(re),l(oe),l(me),l(ce),l(fe),l(xt),l(ue),l(Rt),l($e),l(de),l(Vt),l(Me),l(he),l(Ht),l(ge),l(ye),l(be),l(Bt)),l(e),g(y,t),g(V,t),g(C,t),g(Y,t),g(F,t),g(q,t),g(L,t),g(D,t),g(tt,t),g(dt,t),g(ht,t),g(yt,t),g(jt,t),g(it,t),g(Tt,t),g(Jt,t),g(kt,t),g(Ct,t),g(Wt,t),g(rt,t),g(ot,t),g(Gt,t),g(Xt,t),g(Yt,t),g(mt,t),g(It,t)}}}const hs='{"title":"تصنيف النص(Text classification)","local":"تصنيف-النصtext-classification","sections":[{"title":"تحميل مجموعة بيانات IMDb","local":"تحميل-مجموعة-بيانات-imdb","sections":[],"depth":2},{"title":"المعالجة المسبقة(Preprocess)","local":"المعالجة-المسبقةpreprocess","sections":[],"depth":2},{"title":"التقييم(Evaluate)","local":"التقييمevaluate","sections":[],"depth":2},{"title":"التدريب(Train)","local":"التدريبtrain","sections":[],"depth":2},{"title":"الاستدلال(Inference)","local":"الاستدلالinference","sections":[],"depth":2}],"depth":1}';function gs(k){return Be(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ks extends Ee{constructor(e){super(),Qe(this,e,gs,Ms,Fe,{})}}export{ks as component}; | |
Xet Storage Details
- Size:
- 53.8 kB
- Xet hash:
- def30cada6dff0c8327b5e1c18b8b97f2d862ae77a78459613c3cb13fb785df2
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.