Doc styler examples (#14953)

* Fix bad examples

* Add black formatting to style_doc

* Use first nonempty line

* Put it at the right place

* Don't add spaces to empty lines

* Better templates

* Deal with triple quotes in docstrings

* Result of style_doc

* Enable mdx treatment and fix code examples in MDXs

* Result of doc styler on doc source files

* Last fixes

* Break copy from

docs/source/migration.mdx

@@ -209,7 +209,7 @@ Here is a `pytorch-pretrained-bert` to 🤗 Transformers conversion example for
 
 ```python
 # Let's load our model
-model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
+model = BertForSequenceClassification.from_pretrained("bert-base-uncased")
 
 # If you used to have this line in pytorch-pretrained-bert:
 loss = model(input_ids, labels=labels)
@@ -222,7 +222,7 @@ loss = outputs[0]
 loss, logits = outputs[:2]
 
 # And even the attention weights if you configure the model to output them (and other outputs too, see the docstrings and documentation)
-model = BertForSequenceClassification.from_pretrained('bert-base-uncased', output_attentions=True)
+model = BertForSequenceClassification.from_pretrained("bert-base-uncased", output_attentions=True)
 outputs = model(input_ids, labels=labels)
 loss, logits, attentions = outputs
 ```
@@ -241,23 +241,23 @@ Here is an example:
 
 ```python
 ### Let's load a model and tokenizer
-model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model = BertForSequenceClassification.from_pretrained("bert-base-uncased")
+tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
 
 ### Do some stuff to our model and tokenizer
 # Ex: add new tokens to the vocabulary and embeddings of our model
-tokenizer.add_tokens(['[SPECIAL_TOKEN_1]', '[SPECIAL_TOKEN_2]'])
+tokenizer.add_tokens(["[SPECIAL_TOKEN_1]", "[SPECIAL_TOKEN_2]"])
 model.resize_token_embeddings(len(tokenizer))
 # Train our model
 train(model)
 
 ### Now let's save our model and tokenizer to a directory
-model.save_pretrained('./my_saved_model_directory/')
-tokenizer.save_pretrained('./my_saved_model_directory/')
+model.save_pretrained("./my_saved_model_directory/")
+tokenizer.save_pretrained("./my_saved_model_directory/")
 
 ### Reload the model and the tokenizer
-model = BertForSequenceClassification.from_pretrained('./my_saved_model_directory/')
-tokenizer = BertTokenizer.from_pretrained('./my_saved_model_directory/')
+model = BertForSequenceClassification.from_pretrained("./my_saved_model_directory/")
+tokenizer = BertTokenizer.from_pretrained("./my_saved_model_directory/")
 ```
 
 ### Optimizers: BertAdam & OpenAIAdam are now AdamW, schedules are standard PyTorch schedules
@@ -283,7 +283,13 @@ num_warmup_steps = 100
 warmup_proportion = float(num_warmup_steps) / float(num_training_steps)  # 0.1
 
 ### Previously BertAdam optimizer was instantiated like this:
-optimizer = BertAdam(model.parameters(), lr=lr, schedule='warmup_linear', warmup=warmup_proportion, num_training_steps=num_training_steps)
+optimizer = BertAdam(
+    model.parameters(),
+    lr=lr,
+    schedule="warmup_linear",
+    warmup=warmup_proportion,
+    num_training_steps=num_training_steps,
+)
 ### and used like this:
 for batch in train_data:
     loss = model(batch)
@@ -291,13 +297,19 @@ for batch in train_data:
     optimizer.step()
 
 ### In 🤗 Transformers, optimizer and schedules are split and instantiated like this:
-optimizer = AdamW(model.parameters(), lr=lr, correct_bias=False)  # To reproduce BertAdam specific behavior set correct_bias=False
-scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps)  # PyTorch scheduler
+optimizer = AdamW(
+    model.parameters(), lr=lr, correct_bias=False
+)  # To reproduce BertAdam specific behavior set correct_bias=False
+scheduler = get_linear_schedule_with_warmup(
+    optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps
+)  # PyTorch scheduler
 ### and used like this:
 for batch in train_data:
     loss = model(batch)
     loss.backward()
-    torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm)  # Gradient clipping is not in AdamW anymore (so you can use amp without issue)
+    torch.nn.utils.clip_grad_norm_(
+        model.parameters(), max_grad_norm
+    )  # Gradient clipping is not in AdamW anymore (so you can use amp without issue)
     optimizer.step()
     scheduler.step()
 ```