Merge pull request huggingface#1 from chenglu99/main

running python utils/code_formatter.py

chapters/de/chapter1/3.mdx

@@ -150,7 +150,9 @@ from transformers import pipeline
 
 generator = pipeline("text-generation", model="distilgpt2")
 generator(
-    "In this course, we will teach you how to", max_length=30, num_return_sequences=2,
+    "In this course, we will teach you how to",
+    max_length=30,
+    num_return_sequences=2,
 )
 ```
 

chapters/de/chapter3/3_tf.mdx

@@ -85,7 +85,8 @@ model.compile(
     metrics=["accuracy"],
 )
 model.fit(
-    tf_train_dataset, validation_data=tf_validation_dataset,
+    tf_train_dataset,
+    validation_data=tf_validation_dataset,
 )
 ```
 

chapters/en/chapter1/3.mdx

@@ -150,7 +150,9 @@ from transformers import pipeline
 
 generator = pipeline("text-generation", model="distilgpt2")
 generator(
-    "In this course, we will teach you how to", max_length=30, num_return_sequences=2,
+    "In this course, we will teach you how to",
+    max_length=30,
+    num_return_sequences=2,
 )
 ```
 

chapters/en/chapter2/2.mdx

@@ -39,7 +39,10 @@ from transformers import pipeline
 
 classifier = pipeline("sentiment-analysis")
 classifier(
-    ["I've been waiting for a HuggingFace course my whole life.", "I hate this so much!",]
+    [
+        "I've been waiting for a HuggingFace course my whole life.",
+        "I hate this so much!",
+    ]
 )
 ```
 

chapters/en/chapter3/3_tf.mdx

@@ -85,7 +85,8 @@ model.compile(
     metrics=["accuracy"],
 )
 model.fit(
-    tf_train_dataset, validation_data=tf_validation_dataset,
+    tf_train_dataset,
+    validation_data=tf_validation_dataset,
 )
 ```
 

chapters/en/chapter5/4.mdx

@@ -88,7 +88,7 @@ Here the `rss` attribute refers to the _resident set size_, which is the fractio
 
 ```py
 print(f"Number of files in dataset : {pubmed_dataset.dataset_size}")
-size_gb = pubmed_dataset.dataset_size / (1024 ** 3)
+size_gb = pubmed_dataset.dataset_size / (1024**3)
 print(f"Dataset size (cache file) : {size_gb:.2f} GB")
 ```
 

chapters/en/chapter6/8.mdx

@@ -404,7 +404,9 @@ Great! Now that we're done, we can save the tokenizer like before, and wrap it i
 from transformers import PreTrainedTokenizerFast
 
 wrapped_tokenizer = PreTrainedTokenizerFast(
-    tokenizer_object=tokenizer, bos_token="<|endoftext|>", eos_token="<|endoftext|>",
+    tokenizer_object=tokenizer,
+    bos_token="<|endoftext|>",
+    eos_token="<|endoftext|>",
 )
 ```
 

chapters/en/chapter7/2.mdx

@@ -413,7 +413,9 @@ Now we can just pass them to the `TFAutoModelForTokenClassification.from_pretrai
 from transformers import TFAutoModelForTokenClassification
 
 model = TFAutoModelForTokenClassification.from_pretrained(
-    model_checkpoint, id2label=id2label, label2id=label2id,
+    model_checkpoint,
+    id2label=id2label,
+    label2id=label2id,
 )
 ```
 
@@ -661,7 +663,9 @@ Now we can just pass them to the `AutoModelForTokenClassification.from_pretraine
 from transformers import AutoModelForTokenClassification
 
 model = AutoModelForTokenClassification.from_pretrained(
-    model_checkpoint, id2label=id2label, label2id=label2id,
+    model_checkpoint,
+    id2label=id2label,
+    label2id=label2id,
 )
 ```
 
@@ -770,7 +774,10 @@ First we need to build the `DataLoader`s from our datasets. We'll reuse our `dat
 from torch.utils.data import DataLoader
 
 train_dataloader = DataLoader(
-    tokenized_datasets["train"], shuffle=True, collate_fn=data_collator, batch_size=8,
+    tokenized_datasets["train"],
+    shuffle=True,
+    collate_fn=data_collator,
+    batch_size=8,
 )
 eval_dataloader = DataLoader(
     tokenized_datasets["validation"], collate_fn=data_collator, batch_size=8
@@ -781,7 +788,9 @@ Next we reinstantiate our model, to make sure we're not continuing the fine-tuni
 
 ```py
 model = AutoModelForTokenClassification.from_pretrained(
-    model_checkpoint, id2label=id2label, label2id=label2id,
+    model_checkpoint,
+    id2label=id2label,
+    label2id=label2id,
 )
 ```
 

chapters/en/chapter7/3.mdx

@@ -639,11 +639,17 @@ Once we're logged in, we can create our `tf.data` datasets. To do so, we'll use
 
 ```python
 tf_train_dataset = model.prepare_tf_dataset(
-    downsampled_dataset["train"], collate_fn=data_collator, shuffle=True, batch_size=32,
+    downsampled_dataset["train"],
+    collate_fn=data_collator,
+    shuffle=True,
+    batch_size=32,
 )
 
 tf_eval_dataset = model.prepare_tf_dataset(
-    downsampled_dataset["test"], collate_fn=data_collator, shuffle=False, batch_size=32,
+    downsampled_dataset["test"],
+    collate_fn=data_collator,
+    shuffle=False,
+    batch_size=32,
 )
 ```
 

chapters/en/chapter7/4.mdx

@@ -379,7 +379,10 @@ We can now use this `data_collator` to convert each of our datasets to a `tf.dat
 
 ```python
 tf_train_dataset = model.prepare_tf_dataset(
-    tokenized_datasets["train"], collate_fn=data_collator, shuffle=True, batch_size=32,
+    tokenized_datasets["train"],
+    collate_fn=data_collator,
+    shuffle=True,
+    batch_size=32,
 )
 tf_eval_dataset = model.prepare_tf_dataset(
     tokenized_datasets["validation"],
@@ -793,7 +796,10 @@ from torch.utils.data import DataLoader
 
 tokenized_datasets.set_format("torch")
 train_dataloader = DataLoader(
-    tokenized_datasets["train"], shuffle=True, collate_fn=data_collator, batch_size=8,
+    tokenized_datasets["train"],
+    shuffle=True,
+    collate_fn=data_collator,
+    batch_size=8,
 )
 eval_dataloader = DataLoader(
     tokenized_datasets["validation"], collate_fn=data_collator, batch_size=8

chapters/en/chapter7/5.mdx

@@ -285,7 +285,9 @@ max_target_length = 30
 
 def preprocess_function(examples):
     model_inputs = tokenizer(
-        examples["review_body"], max_length=max_input_length, truncation=True,
+        examples["review_body"],
+        max_length=max_input_length,
+        truncation=True,
     )
     labels = tokenizer(
         examples["review_title"], max_length=max_target_length, truncation=True
@@ -673,7 +675,10 @@ We're almost ready to train! We just need to convert our datasets to `tf.data.Da
 
 ```python
 tf_train_dataset = model.prepare_tf_dataset(
-    tokenized_datasets["train"], collate_fn=data_collator, shuffle=True, batch_size=8,
+    tokenized_datasets["train"],
+    collate_fn=data_collator,
+    shuffle=True,
+    batch_size=8,
 )
 tf_eval_dataset = model.prepare_tf_dataset(
     tokenized_datasets["validation"],
@@ -944,7 +949,8 @@ for epoch in range(num_train_epochs):
     for step, batch in enumerate(eval_dataloader):
         with torch.no_grad():
             generated_tokens = accelerator.unwrap_model(model).generate(
-                batch["input_ids"], attention_mask=batch["attention_mask"],
+                batch["input_ids"],
+                attention_mask=batch["attention_mask"],
             )
 
             generated_tokens = accelerator.pad_across_processes(

chapters/en/chapter7/6.mdx

@@ -383,10 +383,16 @@ Now we can use the `prepare_tf_dataset()` method to convert our datasets to Tens
 
 ```python
 tf_train_dataset = model.prepare_tf_dataset(
-    tokenized_dataset["train"], collate_fn=data_collator, shuffle=True, batch_size=32,
+    tokenized_dataset["train"],
+    collate_fn=data_collator,
+    shuffle=True,
+    batch_size=32,
 )
 tf_eval_dataset = model.prepare_tf_dataset(
-    tokenized_dataset["valid"], collate_fn=data_collator, shuffle=False, batch_size=32,
+    tokenized_dataset["valid"],
+    collate_fn=data_collator,
+    shuffle=False,
+    batch_size=32,
 )
 ```
 

chapters/en/chapter7/7.mdx

@@ -863,10 +863,16 @@ And now we create the datasets as usual.
 
 ```python
 tf_train_dataset = model.prepare_tf_dataset(
-    train_dataset, collate_fn=data_collator, shuffle=True, batch_size=16,
+    train_dataset,
+    collate_fn=data_collator,
+    shuffle=True,
+    batch_size=16,
 )
 tf_eval_dataset = model.prepare_tf_dataset(
-    validation_dataset, collate_fn=data_collator, shuffle=False, batch_size=16,
+    validation_dataset,
+    collate_fn=data_collator,
+    shuffle=False,
+    batch_size=16,
 )
 ```
 
@@ -1017,7 +1023,10 @@ validation_set = validation_dataset.remove_columns(["example_id", "offset_mappin
 validation_set.set_format("torch")
 
 train_dataloader = DataLoader(
-    train_dataset, shuffle=True, collate_fn=default_data_collator, batch_size=8,
+    train_dataset,
+    shuffle=True,
+    collate_fn=default_data_collator,
+    batch_size=8,
 )
 eval_dataloader = DataLoader(
     validation_set, collate_fn=default_data_collator, batch_size=8

chapters/es/chapter1/3.mdx

@@ -153,7 +153,9 @@ from transformers import pipeline
 
 generator = pipeline("text-generation", model="distilgpt2")
 generator(
-    "In this course, we will teach you how to", max_length=30, num_return_sequences=2,
+    "In this course, we will teach you how to",
+    max_length=30,
+    num_return_sequences=2,
 )
 ```
 

chapters/es/chapter5/4.mdx

@@ -87,7 +87,7 @@ El atributo `rss` se refiere al _resident set size_, que es la fracción de memo
 
 ```py
 print(f"Number of files in dataset : {pubmed_dataset.dataset_size}")
-size_gb = pubmed_dataset.dataset_size / (1024 ** 3)
+size_gb = pubmed_dataset.dataset_size / (1024**3)
 print(f"Dataset size (cache file) : {size_gb:.2f} GB")
 ```
 

chapters/fa/chapter2/2.mdx

@@ -43,7 +43,10 @@ from transformers import pipeline
 
 classifier = pipeline("sentiment-analysis")
 classifier(
-    ["I've been waiting for a HuggingFace course my whole life.", "I hate this so much!",]
+    [
+        "I've been waiting for a HuggingFace course my whole life.",
+        "I hate this so much!",
+    ]
 )
 ```
 

chapters/fr/chapter3/3_tf.mdx

@@ -87,7 +87,8 @@ model.compile(
     metrics=["accuracy"],
 )
 model.fit(
-    tf_train_dataset, validation_data=tf_validation_dataset,
+    tf_train_dataset,
+    validation_data=tf_validation_dataset,
 )
 ```
 

chapters/fr/chapter5/4.mdx

@@ -92,7 +92,7 @@ Ici, l'attribut `rss` fait référence à la _taille de l'ensemble résident_, q
 
 ```py
 print(f"Number of files in dataset : {pubmed_dataset.dataset_size}")
-size_gb = pubmed_dataset.dataset_size / (1024 ** 3)
+size_gb = pubmed_dataset.dataset_size / (1024**3)
 print(f"Dataset size (cache file) : {size_gb:.2f} GB")
 ```
 

chapters/fr/chapter6/8.mdx

@@ -408,7 +408,9 @@ Super ! Maintenant que nous avons terminé, nous pouvons sauvegarder le tokenize
 from transformers import PreTrainedTokenizerFast
 
 wrapped_tokenizer = PreTrainedTokenizerFast(
-    tokenizer_object=tokenizer, bos_token="<|endoftext|>", eos_token="<|endoftext|>",
+    tokenizer_object=tokenizer,
+    bos_token="<|endoftext|>",
+    eos_token="<|endoftext|>",
 )
 ```
 

chapters/fr/chapter7/2.mdx

@@ -416,7 +416,9 @@ Maintenant, nous pouvons simplement les passer à la méthode `TFAutoModelForTok
 from transformers import TFAutoModelForTokenClassification
 
 model = TFAutoModelForTokenClassification.from_pretrained(
-    model_checkpoint, id2label=id2label, label2id=label2id,
+    model_checkpoint,
+    id2label=id2label,
+    label2id=label2id,
 )
 ```
 
@@ -664,7 +666,9 @@ Maintenant nous pouvons simplement les passer à la méthode `AutoModelForTokenC
 from transformers import AutoModelForTokenClassification
 
 model = AutoModelForTokenClassification.from_pretrained(
-    model_checkpoint, id2label=id2label, label2id=label2id,
+    model_checkpoint,
+    id2label=id2label,
+    label2id=label2id,
 )
 ```
 
@@ -773,7 +777,10 @@ D'abord nous devons construire le `DataLoader`s à partir de nos jeux de donnée
 from torch.utils.data import DataLoader
 
 train_dataloader = DataLoader(
-    tokenized_datasets["train"], shuffle=True, collate_fn=data_collator, batch_size=8,
+    tokenized_datasets["train"],
+    shuffle=True,
+    collate_fn=data_collator,
+    batch_size=8,
 )
 eval_dataloader = DataLoader(
     tokenized_datasets["validation"], collate_fn=data_collator, batch_size=8
@@ -784,7 +791,9 @@ Ensuite, nous réinstantifions notre modèle pour nous assurer que nous ne conti
 
 ```py
 model = AutoModelForTokenClassification.from_pretrained(
-    model_checkpoint, id2label=id2label, label2id=label2id,
+    model_checkpoint,
+    id2label=id2label,
+    label2id=label2id,
 )
 ```
 

chapters/fr/chapter7/3.mdx

@@ -644,11 +644,17 @@ Une fois que nous sommes connectés, nous pouvons créer nos jeux de données `t
 
 ```python
 tf_train_dataset = model.prepare_tf_dataset(
-    downsampled_dataset["train"], collate_fn=data_collator, shuffle=True, batch_size=32,
+    downsampled_dataset["train"],
+    collate_fn=data_collator,
+    shuffle=True,
+    batch_size=32,
 )
 
 tf_eval_dataset = model.prepare_tf_dataset(
-    downsampled_dataset["test"], collate_fn=data_collator, shuffle=False, batch_size=32,
+    downsampled_dataset["test"],
+    collate_fn=data_collator,
+    shuffle=False,
+    batch_size=32,
 )
 ```
 

chapters/fr/chapter7/4.mdx

@@ -392,7 +392,10 @@ Nous pouvons maintenant utiliser ce `data_collator` pour convertir chacun de nos
 
 ```python
 model.prepare_tf_dataset(
-    tokenized_datasets["train"], collate_fn=data_collator, shuffle=True, batch_size=32,
+    tokenized_datasets["train"],
+    collate_fn=data_collator,
+    shuffle=True,
+    batch_size=32,
 )
 tf_eval_dataset = model.prepare_tf_dataset(
     tokenized_datasets["validation"],
@@ -805,7 +808,10 @@ from torch.utils.data import DataLoader
 
 tokenized_datasets.set_format("torch")
 train_dataloader = DataLoader(
-    tokenized_datasets["train"], shuffle=True, collate_fn=data_collator, batch_size=8,
+    tokenized_datasets["train"],
+    shuffle=True,
+    collate_fn=data_collator,
+    batch_size=8,
 )
 eval_dataloader = DataLoader(
     tokenized_datasets["validation"], collate_fn=data_collator, batch_size=8