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

src/transformers/models/vision_encoder_decoder/configuration_vision_encoder_decoder.py

@@ -58,17 +58,17 @@ class VisionEncoderDecoderConfig(PretrainedConfig):
 
     >>> # Accessing the model configuration
     >>> config_encoder = model.config.encoder
-    >>> config_decoder  = model.config.decoder
+    >>> config_decoder = model.config.decoder
     >>> # set decoder config to causal lm
     >>> config_decoder.is_decoder = True
     >>> config_decoder.add_cross_attention = True
 
     >>> # Saving the model, including its configuration
-    >>> model.save_pretrained('my-model')
+    >>> model.save_pretrained("my-model")
 
     >>> # loading model and config from pretrained folder
-    >>> encoder_decoder_config = VisionEncoderDecoderConfig.from_pretrained('my-model')
-    >>> model = VisionEncoderDecoderModel.from_pretrained('my-model', config=encoder_decoder_config)
+    >>> encoder_decoder_config = VisionEncoderDecoderConfig.from_pretrained("my-model")
+    >>> model = VisionEncoderDecoderModel.from_pretrained("my-model", config=encoder_decoder_config)
     ```"""
     model_type = "vision-encoder-decoder"
     is_composition = True

src/transformers/models/vision_encoder_decoder/modeling_flax_vision_encoder_decoder.py

@@ -397,13 +397,13 @@ class FlaxVisionEncoderDecoderModel(FlaxPreTrainedModel):
         >>> from PIL import Image
         >>> import requests
 
-        >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
+        >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
 
         >>> # initialize a vit-gpt2 from pretrained ViT and GPT2 models. Note that the cross-attention layers will be randomly initialized
-        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained('vit', 'gpt2')
+        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained("vit", "gpt2")
 
         >>> pixel_values = feature_extractor(images=image, return_tensors="np").pixel_values
         >>> encoder_outputs = model.encode(pixel_values)
@@ -474,13 +474,13 @@ class FlaxVisionEncoderDecoderModel(FlaxPreTrainedModel):
         >>> from PIL import Image
         >>> import requests
 
-        >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
+        >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
 
         >>> # initialize a vit-gpt2 from pretrained ViT and GPT2 models. Note that the cross-attention layers will be randomly initialized
-        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained('vit', 'gpt2')
+        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained("vit", "gpt2")
 
         >>> pixel_values = feature_extractor(images=image, return_tensors="np").pixel_values
         >>> encoder_outputs = model.encode(pixel_values)
@@ -601,16 +601,16 @@ class FlaxVisionEncoderDecoderModel(FlaxPreTrainedModel):
         >>> from PIL import Image
         >>> import requests
 
-        >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
+        >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
 
         >>> # load output tokenizer
-        >>> tokenizer_output = GPT2Tokenizer.from_pretrained('gpt2')
+        >>> tokenizer_output = GPT2Tokenizer.from_pretrained("gpt2")
 
         >>> # initialize a vit-gpt2 from pretrained ViT and GPT2 models. Note that the cross-attention layers will be randomly initialized
-        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained('vit', 'gpt2')
+        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained("vit", "gpt2")
 
         >>> pixel_values = feature_extractor(images=image, return_tensors="np").pixel_values
 
@@ -746,8 +746,11 @@ class FlaxVisionEncoderDecoderModel(FlaxPreTrainedModel):
 
         ```python
         >>> from transformers import FlaxVisionEncoderDecoderModel
+
         >>> # initialize a vit-gpt2 from a pretrained ViT and a pretrained GPT2 model. Note that the cross-attention layers will be randomly initialized
-        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained('google/vit-base-patch16-224-in21k', 'gpt2')
+        >>> model = FlaxVisionEncoderDecoderModel.from_encoder_decoder_pretrained(
+        ...     "google/vit-base-patch16-224-in21k", "gpt2"
+        ... )
         >>> # saving model after fine-tuning
         >>> model.save_pretrained("./vit-gpt2")
         >>> # load fine-tuned model

src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py

@@ -302,8 +302,11 @@ class VisionEncoderDecoderModel(PreTrainedModel):
 
         ```python
         >>> from transformers import VisionEncoderDecoderModel
+
         >>> # initialize a vit-bert from a pretrained ViT and a pretrained BERT model. Note that the cross-attention layers will be randomly initialized
-        >>> model = VisionEncoderDecoderModel.from_encoder_decoder_pretrained('google/vit-base-patch16-224-in21k', 'bert-base-uncased')
+        >>> model = VisionEncoderDecoderModel.from_encoder_decoder_pretrained(
+        ...     "google/vit-base-patch16-224-in21k", "bert-base-uncased"
+        ... )
         >>> # saving model after fine-tuning
         >>> model.save_pretrained("./vit-bert")
         >>> # load fine-tuned model
@@ -417,8 +420,8 @@ class VisionEncoderDecoderModel(PreTrainedModel):
         >>> from PIL import Image
         >>> import torch
 
-        >>> processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-handwritten')
-        >>> model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-handwritten')
+        >>> processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
+        >>> model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
 
         >>> # load image from the IAM dataset
         >>> url = "https://fki.tic.heia-fr.ch/static/img/a01-122-02.jpg"

src/transformers/models/vision_text_dual_encoder/configuration_vision_text_dual_encoder.py

@@ -61,15 +61,15 @@ class VisionTextDualEncoderConfig(PretrainedConfig):
     >>> model = VisionTextDualEncoderModel(config=config)
 
     >>> # Accessing the model configuration
-    >>> config_vision  = model.config.vision_config
+    >>> config_vision = model.config.vision_config
     >>> config_text = model.config.text_config
 
     >>> # Saving the model, including its configuration
-    >>> model.save_pretrained('my-model')
+    >>> model.save_pretrained("my-model")
 
     >>> # loading model and config from pretrained folder
-    >>> vision_text_config = VisionTextDualEncoderConfig.from_pretrained('vit-bert')
-    >>> model = VisionTextDualEncoderModel.from_pretrained('vit-bert', config=vision_text_config)
+    >>> vision_text_config = VisionTextDualEncoderConfig.from_pretrained("vit-bert")
+    >>> model = VisionTextDualEncoderModel.from_pretrained("vit-bert", config=vision_text_config)
     ```"""
 
     model_type = "vision-text-dual-encoder"

src/transformers/models/vision_text_dual_encoder/modeling_flax_vision_text_dual_encoder.py

@@ -446,12 +446,15 @@ class FlaxVisionTextDualEncoderModel(FlaxPreTrainedModel):
 
         ```python
         >>> from transformers import FlaxVisionTextDualEncoderModel
+
         >>> # initialize a model from pretrained ViT and BERT models. Note that the projection layers will be randomly initialized.
-        >>> model =  FlaxVisionTextDualEncoderModel.from_vision_text_pretrained('bert-base-uncased', 'google/vit-base-patch16-224')
+        >>> model = FlaxVisionTextDualEncoderModel.from_vision_text_pretrained(
+        ...     "bert-base-uncased", "google/vit-base-patch16-224"
+        ... )
         >>> # saving model after fine-tuning
         >>> model.save_pretrained("./vit-bert")
         >>> # load fine-tuned model
-        >>> model =  FlaxVisionTextDualEncoderModel.from_pretrained("./vit-bert")
+        >>> model = FlaxVisionTextDualEncoderModel.from_pretrained("./vit-bert")
         ```"""
 
         kwargs_vision = {
@@ -531,19 +534,36 @@ VISION_TEXT_DUAL_ENCODER_MODEL_DOCSTRING = r"""
     >>> from PIL import Image
     >>> import requests
     >>> import jax
-    >>> from transformers import FlaxVisionTextDualEncoderModel, VisionTextDualEncoderProcessor, ViTFeatureExtractor, BertTokenizer
+    >>> from transformers import (
+    ...     FlaxVisionTextDualEncoderModel,
+    ...     VisionTextDualEncoderProcessor,
+    ...     ViTFeatureExtractor,
+    ...     BertTokenizer,
+    ... )
 
     >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
     >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
     >>> processor = VisionTextDualEncoderProcessor(feature_extractor, tokenizer)
-    >>> model = FlaxVisionTextDualEncoderModel.from_vision_text_pretrained("google/vit-base-patch16-224", "bert-base-uncased")
+    >>> model = FlaxVisionTextDualEncoderModel.from_vision_text_pretrained(
+    ...     "google/vit-base-patch16-224", "bert-base-uncased"
+    ... )
 
     >>> # contrastive training
-    >>> urls = ["http://images.cocodataset.org/val2017/000000039769.jpg", "https://farm3.staticflickr.com/2674/5850229113_4fe05d5265_z.jpg]
+    >>> urls = [
+    ...     "http://images.cocodataset.org/val2017/000000039769.jpg",
+    ...     "https://farm3.staticflickr.com/2674/5850229113_4fe05d5265_z.jpg",
+    ... ]
     >>> images = [Image.open(requests.get(url, stream=True).raw) for url in urls]
-    >>> inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=images, return_tensors="np", padding=True)
-    >>> outputs = model(input_ids=inputs.input_ids, attention_mask=inputs.attention_mask, pixel_values=inputs.pixel_values, return_loss=True)
-    >>> loss, logits_per_image = outputs.loss, outputs.logits_per_imag # this is the image-text similarity score
+    >>> inputs = processor(
+    ...     text=["a photo of a cat", "a photo of a dog"], images=images, return_tensors="np", padding=True
+    ... )
+    >>> outputs = model(
+    ...     input_ids=inputs.input_ids,
+    ...     attention_mask=inputs.attention_mask,
+    ...     pixel_values=inputs.pixel_values,
+    ...     return_loss=True,
+    ... )
+    >>> loss, logits_per_image = outputs.loss, outputs.logits_per_imag  # this is the image-text similarity score
 
     >>> # save and load from pretrained
     >>> model.save_pretrained("vit-bert")
@@ -551,8 +571,8 @@ VISION_TEXT_DUAL_ENCODER_MODEL_DOCSTRING = r"""
 
     >>> # inference
     >>> outputs = model(**inputs)
-    >>> logits_per_image = outputs.logits_per_image # this is the image-text similarity score
-    >>> probs = jax.nn.softmax(logits_per_image, axis=1) # we can take the softmax to get the label probabilities
+    >>> logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
+    >>> probs = jax.nn.softmax(logits_per_image, axis=1)  # we can take the softmax to get the label probabilities
     ```
 """
 

src/transformers/models/vision_text_dual_encoder/modeling_vision_text_dual_encoder.py

@@ -231,7 +231,7 @@ class VisionTextDualEncoderModel(PreTrainedModel):
         >>> model = VisionTextDualEncoderModel.from_pretrained("clip-italian/clip-italian")
         >>> tokenizer = AutoTokenizer.from_pretrained("clip-italian/clip-italian")
 
-        >>> inputs = tokenizer(["una foto di un gatto", "una foto di un cane"],  padding=True, return_tensors="pt")
+        >>> inputs = tokenizer(["una foto di un gatto", "una foto di un cane"], padding=True, return_tensors="pt")
         >>> text_features = model.get_text_features(**inputs)
         ```"""
         text_outputs = self.text_model(
@@ -312,19 +312,36 @@ class VisionTextDualEncoderModel(PreTrainedModel):
         ```python
         >>> from PIL import Image
         >>> import requests
-        >>> from transformers import VisionTextDualEncoderModel, VisionTextDualEncoderProcessor, ViTFeatureExtractor, BertTokenizer
+        >>> from transformers import (
+        ...     VisionTextDualEncoderModel,
+        ...     VisionTextDualEncoderProcessor,
+        ...     ViTFeatureExtractor,
+        ...     BertTokenizer,
+        ... )
 
         >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
         >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
         >>> processor = VisionTextDualEncoderProcessor(feature_extractor, tokenizer)
-        >>> model = VisionTextDualEncoderModel.from_vision_text_pretrained("google/vit-base-patch16-224", "bert-base-uncased")
+        >>> model = VisionTextDualEncoderModel.from_vision_text_pretrained(
+        ...     "google/vit-base-patch16-224", "bert-base-uncased"
+        ... )
 
         >>> # contrastive training
-        >>> urls = ["http://images.cocodataset.org/val2017/000000039769.jpg", "https://farm3.staticflickr.com/2674/5850229113_4fe05d5265_z.jpg]
+        >>> urls = [
+        ...     "http://images.cocodataset.org/val2017/000000039769.jpg",
+        ...     "https://farm3.staticflickr.com/2674/5850229113_4fe05d5265_z.jpg",
+        ... ]
         >>> images = [Image.open(requests.get(url, stream=True).raw) for url in urls]
-        >>> inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=images, return_tensors="pt", padding=True)
-        >>> outputs = model(input_ids=inputs.input_ids, attention_mask=inputs.attention_mask, pixel_values=inputs.pixel_values, return_loss=True)
-        >>> loss, logits_per_image = outputs.loss, outputs.logits_per_imag # this is the image-text similarity score
+        >>> inputs = processor(
+        ...     text=["a photo of a cat", "a photo of a dog"], images=images, return_tensors="pt", padding=True
+        ... )
+        >>> outputs = model(
+        ...     input_ids=inputs.input_ids,
+        ...     attention_mask=inputs.attention_mask,
+        ...     pixel_values=inputs.pixel_values,
+        ...     return_loss=True,
+        ... )
+        >>> loss, logits_per_image = outputs.loss, outputs.logits_per_imag  # this is the image-text similarity score
 
         >>> # save and load from pretrained
         >>> model.save_pretrained("vit-bert")
@@ -332,8 +349,8 @@ class VisionTextDualEncoderModel(PreTrainedModel):
 
         >>> # inference
         >>> outputs = model(**inputs)
-        >>> logits_per_image = outputs.logits_per_image # this is the image-text similarity score
-        >>> probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities
+        >>> logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
+        >>> probs = logits_per_image.softmax(dim=1)  # we can take the softmax to get the label probabilities
         ```"""
         return_dict = return_dict if return_dict is not None else self.config.return_dict
 
@@ -447,8 +464,11 @@ class VisionTextDualEncoderModel(PreTrainedModel):
 
         ```python
         >>> from transformers import VisionTextDualEncoderModel
+
         >>> # initialize a model from pretrained ViT and BERT models. Note that the projection layers will be randomly initialized.
-        >>> model = VisionTextDualEncoderModel.from_vision_text_pretrained('bert-base-uncased', 'google/vit-base-patch16-224')
+        >>> model = VisionTextDualEncoderModel.from_vision_text_pretrained(
+        ...     "bert-base-uncased", "google/vit-base-patch16-224"
+        ... )
         >>> # saving model after fine-tuning
         >>> model.save_pretrained("./vit-bert")
         >>> # load fine-tuned model

src/transformers/models/visual_bert/configuration_visual_bert.py

@@ -93,7 +93,7 @@ class VisualBertConfig(PretrainedConfig):
     >>> from transformers import VisualBertModel, VisualBertConfig
 
     >>> # Initializing a VisualBERT visualbert-vqa-coco-pre style configuration
-    >>> configuration = VisualBertConfig.from_pretrained('visualbert-vqa-coco-pre')
+    >>> configuration = VisualBertConfig.from_pretrained("visualbert-vqa-coco-pre")
 
     >>> # Initializing a model from the visualbert-vqa-coco-pre style configuration
     >>> model = VisualBertModel(configuration)

src/transformers/models/visual_bert/modeling_visual_bert.py

@@ -745,19 +745,21 @@ class VisualBertModel(VisualBertPreTrainedModel):
         from transformers import BertTokenizer, VisualBertModel
         import torch
 
-        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-        model = VisualBertModel.from_pretrained('uclanlp/visualbert-vqa-coco-pre')
+        tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+        model = VisualBertModel.from_pretrained("uclanlp/visualbert-vqa-coco-pre")
 
         inputs = tokenizer("The capital of France is Paris.", return_tensors="pt")
         visual_embeds = get_visual_embeddings(image).unsqueeze(0)
         visual_token_type_ids = torch.ones(visual_embeds.shape[:-1], dtype=torch.long)
         visual_attention_mask = torch.ones(visual_embeds.shape[:-1], dtype=torch.float)
 
-        inputs.update({
-            "visual_embeds": visual_embeds,
-            "visual_token_type_ids": visual_token_type_ids,
-            "visual_attention_mask": visual_attention_mask
-        })
+        inputs.update(
+            {
+                "visual_embeds": visual_embeds,
+                "visual_token_type_ids": visual_token_type_ids,
+                "visual_attention_mask": visual_attention_mask,
+            }
+        )
 
         outputs = model(**inputs)
 
@@ -927,22 +929,26 @@ class VisualBertForPreTraining(VisualBertPreTrainedModel):
         # Assumption: *get_visual_embeddings(image)* gets the visual embeddings of the image in the batch.
         from transformers import BertTokenizer, VisualBertForPreTraining
 
-        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-        model = VisualBertForPreTraining.from_pretrained('uclanlp/visualbert-vqa-coco-pre')
+        tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+        model = VisualBertForPreTraining.from_pretrained("uclanlp/visualbert-vqa-coco-pre")
 
         inputs = tokenizer("The capital of France is {mask}.", return_tensors="pt")
         visual_embeds = get_visual_embeddings(image).unsqueeze(0)
         visual_token_type_ids = torch.ones(visual_embeds.shape[:-1], dtype=torch.long)
         visual_attention_mask = torch.ones(visual_embeds.shape[:-1], dtype=torch.float)
 
-        inputs.update({
-        "visual_embeds": visual_embeds,
-        "visual_token_type_ids": visual_token_type_ids,
-        "visual_attention_mask": visual_attention_mask
-        })
-        max_length  = inputs["input_ids"].shape[-1]+visual_embeds.shape[-2]
-        labels = tokenizer("The capital of France is Paris.", return_tensors="pt", padding="max_length", max_length=max_length)["input_ids"]
-        sentence_image_labels = torch.tensor(1).unsqueeze(0) # Batch_size
+        inputs.update(
+            {
+                "visual_embeds": visual_embeds,
+                "visual_token_type_ids": visual_token_type_ids,
+                "visual_attention_mask": visual_attention_mask,
+            }
+        )
+        max_length = inputs["input_ids"].shape[-1] + visual_embeds.shape[-2]
+        labels = tokenizer(
+            "The capital of France is Paris.", return_tensors="pt", padding="max_length", max_length=max_length
+        )["input_ids"]
+        sentence_image_labels = torch.tensor(1).unsqueeze(0)  # Batch_size
 
 
         outputs = model(**inputs, labels=labels, sentence_image_labels=sentence_image_labels)
@@ -1063,8 +1069,8 @@ class VisualBertForMultipleChoice(VisualBertPreTrainedModel):
         from transformers import BertTokenizer, VisualBertForMultipleChoice
         import torch
 
-        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-        model = VisualBertForMultipleChoice.from_pretrained('uclanlp/visualbert-vcr')
+        tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+        model = VisualBertForMultipleChoice.from_pretrained("uclanlp/visualbert-vcr")
 
         prompt = "In Italy, pizza served in formal settings, such as at a restaurant, is presented unsliced."
         choice0 = "It is eaten with a fork and a knife."
@@ -1078,15 +1084,17 @@ class VisualBertForMultipleChoice(VisualBertPreTrainedModel):
 
         labels = torch.tensor(0).unsqueeze(0)  # choice0 is correct (according to Wikipedia ;)), batch size 1
 
-        encoding = tokenizer([[prompt, prompt], [choice0, choice1]], return_tensors='pt', padding=True)
+        encoding = tokenizer([[prompt, prompt], [choice0, choice1]], return_tensors="pt", padding=True)
         # batch size is 1
-        inputs_dict = {k: v.unsqueeze(0) for k,v in encoding.items()}
-        inputs_dict.update({
-        "visual_embeds": visual_embeds,
-        "visual_attention_mask": visual_attention_mask,
-        "visual_token_type_ids": visual_token_type_ids,
-        "labels": labels
-        })
+        inputs_dict = {k: v.unsqueeze(0) for k, v in encoding.items()}
+        inputs_dict.update(
+            {
+                "visual_embeds": visual_embeds,
+                "visual_attention_mask": visual_attention_mask,
+                "visual_token_type_ids": visual_token_type_ids,
+                "labels": labels,
+            }
+        )
         outputs = model(**inputs_dict)
 
         loss = outputs.loss
@@ -1212,22 +1220,24 @@ class VisualBertForQuestionAnswering(VisualBertPreTrainedModel):
         from transformers import BertTokenizer, VisualBertForQuestionAnswering
         import torch
 
-        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-        model = VisualBertForQuestionAnswering.from_pretrained('uclanlp/visualbert-vqa')
+        tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+        model = VisualBertForQuestionAnswering.from_pretrained("uclanlp/visualbert-vqa")
 
         text = "Who is eating the apple?"
-        inputs = tokenizer(text, return_tensors='pt')
+        inputs = tokenizer(text, return_tensors="pt")
         visual_embeds = get_visual_embeddings(image).unsqueeze(0)
         visual_token_type_ids = torch.ones(visual_embeds.shape[:-1], dtype=torch.long)
         visual_attention_mask = torch.ones(visual_embeds.shape[:-1], dtype=torch.float)
 
-        inputs.update({
-        "visual_embeds": visual_embeds,
-        "visual_token_type_ids": visual_token_type_ids,
-        "visual_attention_mask": visual_attention_mask
-        })
+        inputs.update(
+            {
+                "visual_embeds": visual_embeds,
+                "visual_token_type_ids": visual_token_type_ids,
+                "visual_attention_mask": visual_attention_mask,
+            }
+        )
 
-        labels = torch.tensor([[0.0,1.0]]).unsqueeze(0)  # Batch size 1, Num labels 2
+        labels = torch.tensor([[0.0, 1.0]]).unsqueeze(0)  # Batch size 1, Num labels 2
 
         outputs = model(**inputs, labels=labels)
         loss = outputs.loss
@@ -1336,20 +1346,22 @@ class VisualBertForVisualReasoning(VisualBertPreTrainedModel):
         from transformers import BertTokenizer, VisualBertForVisualReasoning
         import torch
 
-        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-        model = VisualBertForVisualReasoning.from_pretrained('uclanlp/visualbert-nlvr2')
+        tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+        model = VisualBertForVisualReasoning.from_pretrained("uclanlp/visualbert-nlvr2")
 
         text = "Who is eating the apple?"
-        inputs = tokenizer(text, return_tensors='pt')
+        inputs = tokenizer(text, return_tensors="pt")
         visual_embeds = get_visual_embeddings(image).unsqueeze(0)
         visual_token_type_ids = torch.ones(visual_embeds.shape[:-1], dtype=torch.long)
         visual_attention_mask = torch.ones(visual_embeds.shape[:-1], dtype=torch.float)
 
-        inputs.update({
-        "visual_embeds": visual_embeds,
-        "visual_token_type_ids": visual_token_type_ids,
-        "visual_attention_mask": visual_attention_mask
-        })
+        inputs.update(
+            {
+                "visual_embeds": visual_embeds,
+                "visual_token_type_ids": visual_token_type_ids,
+                "visual_attention_mask": visual_attention_mask,
+            }
+        )
 
         labels = torch.tensor(1).unsqueeze(0)  # Batch size 1, Num choices 2
 
@@ -1498,24 +1510,28 @@ class VisualBertForRegionToPhraseAlignment(VisualBertPreTrainedModel):
         from transformers import BertTokenizer, VisualBertForRegionToPhraseAlignment
         import torch
 
-        tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-        model = VisualBertForRegionToPhraseAlignment.from_pretrained('uclanlp/visualbert-vqa-coco-pre')
+        tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+        model = VisualBertForRegionToPhraseAlignment.from_pretrained("uclanlp/visualbert-vqa-coco-pre")
 
         text = "Who is eating the apple?"
-        inputs = tokenizer(text, return_tensors='pt')
+        inputs = tokenizer(text, return_tensors="pt")
         visual_embeds = get_visual_embeddings(image).unsqueeze(0)
         visual_token_type_ids = torch.ones(visual_embeds.shape[:-1], dtype=torch.long)
         visual_attention_mask = torch.ones(visual_embeds.shape[:-1], dtype=torch.float)
-        region_to_phrase_position = torch.ones((1, inputs["input_ids"].shape[-1]+visual_embeds.shape[-2]))
-
-        inputs.update({
-        "region_to_phrase_position": region_to_phrase_position,
-        "visual_embeds": visual_embeds,
-        "visual_token_type_ids": visual_token_type_ids,
-        "visual_attention_mask": visual_attention_mask
-        })
+        region_to_phrase_position = torch.ones((1, inputs["input_ids"].shape[-1] + visual_embeds.shape[-2]))
+
+        inputs.update(
+            {
+                "region_to_phrase_position": region_to_phrase_position,
+                "visual_embeds": visual_embeds,
+                "visual_token_type_ids": visual_token_type_ids,
+                "visual_attention_mask": visual_attention_mask,
+            }
+        )
 
-        labels = torch.ones((1, inputs["input_ids"].shape[-1]+visual_embeds.shape[-2], visual_embeds.shape[-2])) # Batch size 1
+        labels = torch.ones(
+            (1, inputs["input_ids"].shape[-1] + visual_embeds.shape[-2], visual_embeds.shape[-2])
+        )  # Batch size 1
 
         outputs = model(**inputs, labels=labels)
         loss = outputs.loss

src/transformers/models/vit/modeling_flax_vit.py

@@ -521,11 +521,11 @@ FLAX_VISION_MODEL_DOCSTRING = """
     >>> from PIL import Image
     >>> import requests
 
-    >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+    >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
     >>> image = Image.open(requests.get(url, stream=True).raw)
 
-    >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
-    >>> model = FlaxViTModel.from_pretrained('google/vit-base-patch16-224-in21k')
+    >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
+    >>> model = FlaxViTModel.from_pretrained("google/vit-base-patch16-224-in21k")
 
     >>> inputs = feature_extractor(images=image, return_tensors="np")
     >>> outputs = model(**inputs)
@@ -603,11 +603,11 @@ FLAX_VISION_CLASSIF_DOCSTRING = """
     >>> import jax
     >>> import requests
 
-    >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+    >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
     >>> image = Image.open(requests.get(url, stream=True).raw)
 
-    >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
-    >>> model = FlaxViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
+    >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
+    >>> model = FlaxViTForImageClassification.from_pretrained("google/vit-base-patch16-224")
 
     >>> inputs = feature_extractor(images=image, return_tensors="np")
     >>> outputs = model(**inputs)

src/transformers/models/vit/modeling_tf_vit.py

@@ -682,11 +682,11 @@ class TFViTModel(TFViTPreTrainedModel):
         >>> from PIL import Image
         >>> import requests
 
-        >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
-        >>> model = TFViTModel.from_pretrained('google/vit-base-patch16-224-in21k')
+        >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
+        >>> model = TFViTModel.from_pretrained("google/vit-base-patch16-224-in21k")
 
         >>> inputs = feature_extractor(images=image, return_tensors="tf")
         >>> outputs = model(**inputs)
@@ -803,11 +803,11 @@ class TFViTForImageClassification(TFViTPreTrainedModel, TFSequenceClassification
         >>> from PIL import Image
         >>> import requests
 
-        >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
-        >>> model = TFViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
+        >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
+        >>> model = TFViTForImageClassification.from_pretrained("google/vit-base-patch16-224")
 
         >>> inputs = feature_extractor(images=image, return_tensors="tf")
         >>> outputs = model(**inputs)

src/transformers/models/vit/modeling_vit.py

@@ -522,11 +522,11 @@ class ViTModel(ViTPreTrainedModel):
         >>> from PIL import Image
         >>> import requests
 
-        >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
-        >>> model = ViTModel.from_pretrained('google/vit-base-patch16-224-in21k')
+        >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
+        >>> model = ViTModel.from_pretrained("google/vit-base-patch16-224-in21k")
 
         >>> inputs = feature_extractor(images=image, return_tensors="pt")
         >>> outputs = model(**inputs)
@@ -634,11 +634,11 @@ class ViTForImageClassification(ViTPreTrainedModel):
         >>> from PIL import Image
         >>> import requests
 
-        >>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
-        >>> model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
+        >>> feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
+        >>> model = ViTForImageClassification.from_pretrained("google/vit-base-patch16-224")
 
         >>> inputs = feature_extractor(images=image, return_tensors="pt")
         >>> outputs = model(**inputs)

src/transformers/models/wav2vec2/modeling_flax_wav2vec2.py

@@ -952,15 +952,19 @@ FLAX_WAV2VEC2_MODEL_DOCSTRING = """
     >>> processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-lv60")
     >>> model = FlaxWav2Vec2Model.from_pretrained("facebook/wav2vec2-large-lv60")
 
+
     >>> def map_to_array(batch):
-    >>>     speech, _ = sf.read(batch["file"])
-    >>>     batch["speech"] = speech
-    >>>     return batch
+    ...     speech, _ = sf.read(batch["file"])
+    ...     batch["speech"] = speech
+    ...     return batch
+
 
     >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> ds = ds.map(map_to_array)
 
-    >>> input_values = processor(ds["speech"][0], sampling_rate=16_000, return_tensors="np").input_values  # Batch size 1
+    >>> input_values = processor(
+    ...     ds["speech"][0], sampling_rate=16_000, return_tensors="np"
+    >>> ).input_values  # Batch size 1
     >>> hidden_states = model(input_values).last_hidden_state
     ```
 """
@@ -1055,15 +1059,19 @@ FLAX_WAV2VEC2_FOR_CTC_DOCSTRING = """
     >>> processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-large-960h-lv60")
     >>> model = FlaxWav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h-lv60")
 
+
     >>> def map_to_array(batch):
-    >>>     speech, _ = sf.read(batch["file"])
-    >>>     batch["speech"] = speech
-    >>>     return batch
+    ...     speech, _ = sf.read(batch["file"])
+    ...     batch["speech"] = speech
+    ...     return batch
+
 
     >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
     >>> ds = ds.map(map_to_array)
 
-    >>> input_values = processor(ds["speech"][0], sampling_rate=16_000, return_tensors="np").input_values  # Batch size 1
+    >>> input_values = processor(
+    ...     ds["speech"][0], sampling_rate=16_000, return_tensors="np"
+    >>> ).input_values  # Batch size 1
     >>> logits = model(input_values).logits
     >>> predicted_ids = jnp.argmax(logits, axis=-1)
 
@@ -1264,9 +1272,7 @@ FLAX_WAV2VEC2_FOR_PRETRAINING_DOCSTRING = """
     >>> outputs = model(input_values, mask_time_indices=mask_time_indices)
 
     >>> # compute cosine similarity between predicted (=projected_states) and target (=projected_quantized_states)
-    >>> cosine_sim = optax.cosine_similarity(
-    ...     outputs.projected_states, outputs.projected_quantized_states
-    ... )
+    >>> cosine_sim = optax.cosine_similarity(outputs.projected_states, outputs.projected_quantized_states)
 
     >>> # show that cosine similarity is much higher than random
     >>> assert np.asarray(cosine_sim)[mask_time_indices].mean() > 0.5

src/transformers/models/wav2vec2/modeling_tf_wav2vec2.py

@@ -1408,10 +1408,12 @@ class TFWav2Vec2Model(TFWav2Vec2PreTrainedModel):
         >>> processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
         >>> model = TFWav2Vec2Model.from_pretrained("facebook/wav2vec2-base-960h")
 
+
         >>> def map_to_array(batch):
-        >>>     speech, _ = sf.read(batch["file"])
-        >>>     batch["speech"] = speech
-        >>>     return batch
+        ...     speech, _ = sf.read(batch["file"])
+        ...     batch["speech"] = speech
+        ...     return batch
+
 
         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.map(map_to_array)
@@ -1519,15 +1521,17 @@ class TFWav2Vec2ForCTC(TFWav2Vec2PreTrainedModel):
         >>> processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
         >>> model = TFWav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
 
+
         >>> def map_to_array(batch):
-        >>>     speech, _ = sf.read(batch["file"])
-        >>>     batch["speech"] = speech
-        >>>     return batch
+        ...     speech, _ = sf.read(batch["file"])
+        ...     batch["speech"] = speech
+        ...     return batch
+
 
         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.map(map_to_array)
 
-        >>> input_values = processor(ds["speech"][0], return_tensors="tf").input_values # Batch size 1
+        >>> input_values = processor(ds["speech"][0], return_tensors="tf").input_values  # Batch size 1
         >>> logits = model(input_values).logits
         >>> predicted_ids = tf.argmax(logits, axis=-1)
 
@@ -1538,7 +1542,7 @@ class TFWav2Vec2ForCTC(TFWav2Vec2PreTrainedModel):
 
         >>> # wrap processor as target processor to encode labels
         >>> with processor.as_target_processor():
-        >>>     labels = processor(transcription, return_tensors="tf").input_ids
+        ...     labels = processor(transcription, return_tensors="tf").input_ids
 
         >>> loss = model(input_values, labels=labels).loss
         ```"""

src/transformers/models/wav2vec2/modeling_wav2vec2.py

@@ -1421,9 +1421,7 @@ class Wav2Vec2ForPreTraining(Wav2Vec2PreTrainedModel):
         ...     outputs = model(input_values, mask_time_indices=mask_time_indices)
 
         >>> # compute cosine similarity between predicted (=projected_states) and target (=projected_quantized_states)
-        >>> cosine_sim = torch.cosine_similarity(
-        ...     outputs.projected_states, outputs.projected_quantized_states, dim=-1
-        ... )
+        >>> cosine_sim = torch.cosine_similarity(outputs.projected_states, outputs.projected_quantized_states, dim=-1)
 
         >>> # show that cosine similarity is much higher than random
         >>> assert cosine_sim[mask_time_indices].mean() > 0.5
@@ -1568,10 +1566,12 @@ class Wav2Vec2ForMaskedLM(Wav2Vec2PreTrainedModel):
         >>> processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
         >>> model = Wav2Vec2ForMaskedLM.from_pretrained("facebook/wav2vec2-base-960h")
 
+
         >>> def map_to_array(batch):
-        >>>     speech, _ = sf.read(batch["file"])
-        >>>     batch["speech"] = speech
-        >>>     return batch
+        ...     speech, _ = sf.read(batch["file"])
+        ...     batch["speech"] = speech
+        ...     return batch
+
 
         >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
         >>> ds = ds.map(map_to_array)

src/transformers/models/wav2vec2/tokenization_wav2vec2.py

@@ -298,11 +298,11 @@ class Wav2Vec2CTCTokenizer(PreTrainedTokenizer):
 
         ```python
         # Let's see how to increase the vocabulary of Bert model and tokenizer
-        tokenizer = Wav2Vec2CTCTokenizer.from_pretrained('facebook/wav2vec2-base-960h')
-        model = Wav2Vec2ForCTC.from_pretrained('facebook/wav2vec2-base-960h')
+        tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
+        model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
 
-        num_added_toks = tokenizer.add_tokens(['new_tok1', 'my_new-tok2'])
-        print('We have added', num_added_toks, 'tokens')
+        num_added_toks = tokenizer.add_tokens(["new_tok1", "my_new-tok2"])
+        print("We have added", num_added_toks, "tokens")
         # Note: resize_token_embeddings expects to receive the full size of the new vocabulary, i.e. the length of the tokenizer.
         model.resize_token_embeddings(len(tokenizer))
         ```"""

src/transformers/models/wav2vec2_phoneme/tokenization_wav2vec2_phoneme.py

@@ -370,11 +370,11 @@ class Wav2Vec2PhonemeCTCTokenizer(PreTrainedTokenizer):
 
         ```python
         # Let's see how to increase the vocabulary of Bert model and tokenizer
-        tokenizer = Wav2Vec2PhonemeCTCTokenizer.from_pretrained('facebook/wav2vec2-lv-60-espeak-cv-ft')
-        model = Wav2Vec2PhonemeForCTC.from_pretrained('facebook/wav2vec2-lv-60-espeak-cv-ft')
+        tokenizer = Wav2Vec2PhonemeCTCTokenizer.from_pretrained("facebook/wav2vec2-lv-60-espeak-cv-ft")
+        model = Wav2Vec2PhonemeForCTC.from_pretrained("facebook/wav2vec2-lv-60-espeak-cv-ft")
 
-        num_added_toks = tokenizer.add_tokens(['new_tok1', 'my_new-tok2'])
-        print('We have added', num_added_toks, 'tokens')
+        num_added_toks = tokenizer.add_tokens(["new_tok1", "my_new-tok2"])
+        print("We have added", num_added_toks, "tokens")
         # Note: resize_token_embeddings expects to receive the full size of the new vocabulary, i.e. the length of the tokenizer.
         model.resize_token_embeddings(len(tokenizer))
         ```"""

src/transformers/models/xlm/modeling_xlm.py

@@ -1042,10 +1042,12 @@ class XLMForQuestionAnswering(XLMPreTrainedModel):
         >>> from transformers import XLMTokenizer, XLMForQuestionAnswering
         >>> import torch
 
-        >>> tokenizer = XLMTokenizer.from_pretrained('xlm-mlm-en-2048')
-        >>> model = XLMForQuestionAnswering.from_pretrained('xlm-mlm-en-2048')
+        >>> tokenizer = XLMTokenizer.from_pretrained("xlm-mlm-en-2048")
+        >>> model = XLMForQuestionAnswering.from_pretrained("xlm-mlm-en-2048")
 
-        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
+        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(
+        ...     0
+        >>> )  # Batch size 1
         >>> start_positions = torch.tensor([1])
         >>> end_positions = torch.tensor([3])
 

src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.py

@@ -46,8 +46,8 @@ class XLMProphetNetEncoder(ProphetNetEncoder):
     >>> from transformers import XLMProphetNetTokenizer, XLMProphetNetEncoder
     >>> import torch
 
-    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
-    >>> model = XLMProphetNetEncoder.from_pretrained('patrickvonplaten/xprophetnet-large-uncased-standalone')
+    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
+    >>> model = XLMProphetNetEncoder.from_pretrained("patrickvonplaten/xprophetnet-large-uncased-standalone")
     >>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder."
     >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
     >>> outputs = model(**inputs)
@@ -69,8 +69,10 @@ class XLMProphetNetDecoder(ProphetNetDecoder):
     >>> from transformers import XLMProphetNetTokenizer, XLMProphetNetDecoder
     >>> import torch
 
-    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
-    >>> model = XLMProphetNetDecoder.from_pretrained('patrickvonplaten/xprophetnet-large-uncased-standalone', add_cross_attention=False)
+    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
+    >>> model = XLMProphetNetDecoder.from_pretrained(
+    ...     "patrickvonplaten/xprophetnet-large-uncased-standalone", add_cross_attention=False
+    ... )
     >>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder."
     >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
     >>> outputs = model(**inputs)
@@ -91,10 +93,12 @@ class XLMProphetNetModel(ProphetNetModel):
     ```python
     >>> from transformers import XLMProphetNetTokenizer, XLMProphetNetModel
 
-    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
-    >>> model = XLMProphetNetModel.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
+    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
+    >>> model = XLMProphetNetModel.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
 
-    >>> input_ids = tokenizer("Studies have been shown that owning a dog is good for you", return_tensors="pt").input_ids  # Batch size 1
+    >>> input_ids = tokenizer(
+    ...     "Studies have been shown that owning a dog is good for you", return_tensors="pt"
+    >>> ).input_ids  # Batch size 1
     >>> decoder_input_ids = tokenizer("Studies show that", return_tensors="pt").input_ids  # Batch size 1
     >>> outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)
 
@@ -115,10 +119,12 @@ class XLMProphetNetForConditionalGeneration(ProphetNetForConditionalGeneration):
     ```python
     >>> from transformers import XLMProphetNetTokenizer, XLMProphetNetForConditionalGeneration
 
-    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
-    >>> model =  XLMProphetNetForConditionalGeneration.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
+    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
+    >>> model = XLMProphetNetForConditionalGeneration.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
 
-    >>> input_ids = tokenizer("Studies have been shown that owning a dog is good for you", return_tensors="pt").input_ids  # Batch size 1
+    >>> input_ids = tokenizer(
+    ...     "Studies have been shown that owning a dog is good for you", return_tensors="pt"
+    >>> ).input_ids  # Batch size 1
     >>> decoder_input_ids = tokenizer("Studies show that", return_tensors="pt").input_ids  # Batch size 1
     >>> outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)
 
@@ -140,8 +146,8 @@ class XLMProphetNetForCausalLM(ProphetNetForCausalLM):
     >>> from transformers import XLMProphetNetTokenizer, XLMProphetNetForCausalLM
     >>> import torch
 
-    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
-    >>> model = XLMProphetNetForCausalLM.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
+    >>> tokenizer = XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
+    >>> model = XLMProphetNetForCausalLM.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
     >>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder."
     >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
     >>> outputs = model(**inputs)
@@ -152,14 +158,16 @@ class XLMProphetNetForCausalLM(ProphetNetForCausalLM):
     >>> from transformers import EncoderDecoderModel, XLMProphetNetTokenizer, XLMRobertaTokenizer
     >>> import torch
 
-    >>> tokenizer_enc = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large')
-    >>> tokenizer_dec = XLMProphetNetTokenizer.from_pretrained('microsoft/xprophetnet-large-wiki100-cased')
-    >>> model = EncoderDecoderModel.from_encoder_decoder_pretrained("xlm-roberta-large", 'microsoft/xprophetnet-large-wiki100-cased')
+    >>> tokenizer_enc = XLMRobertaTokenizer.from_pretrained("xlm-roberta-large")
+    >>> tokenizer_dec = XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
+    >>> model = EncoderDecoderModel.from_encoder_decoder_pretrained(
+    ...     "xlm-roberta-large", "microsoft/xprophetnet-large-wiki100-cased"
+    ... )
 
     >>> ARTICLE = (
-    ... "the us state department said wednesday it had received no "
-    ... "formal word from bolivia that it was expelling the us ambassador there "
-    ... "but said the charges made against him are `` baseless ."
+    ...     "the us state department said wednesday it had received no "
+    ...     "formal word from bolivia that it was expelling the us ambassador there "
+    ...     "but said the charges made against him are `` baseless ."
     ... )
     >>> input_ids = tokenizer_enc(ARTICLE, return_tensors="pt").input_ids
     >>> labels = tokenizer_dec("us rejects charges against its ambassador in bolivia", return_tensors="pt").input_ids

src/transformers/models/xlnet/modeling_tf_xlnet.py

@@ -1321,21 +1321,33 @@ class TFXLNetLMHeadModel(TFXLNetPreTrainedModel, TFCausalLanguageModelingLoss):
         >>> import numpy as np
         >>> from transformers import XLNetTokenizer, TFXLNetLMHeadModel
 
-        >>> tokenizer = XLNetTokenizer.from_pretrained('xlnet-large-cased')
-        >>> model = TFXLNetLMHeadModel.from_pretrained('xlnet-large-cased')
+        >>> tokenizer = XLNetTokenizer.from_pretrained("xlnet-large-cased")
+        >>> model = TFXLNetLMHeadModel.from_pretrained("xlnet-large-cased")
 
         >>> # We show how to setup inputs to predict a next token using a bi-directional context.
-        >>> input_ids = tf.constant(tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=True))[None, :]  # We will predict the masked token
+        >>> input_ids = tf.constant(tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=True))[
+        ...     None, :
+        >>> ]  # We will predict the masked token
 
         >>> perm_mask = np.zeros((1, input_ids.shape[1], input_ids.shape[1]))
         >>> perm_mask[:, :, -1] = 1.0  # Previous tokens don't see last token
 
-        >>> target_mapping = np.zeros((1, 1, input_ids.shape[1]))  # Shape [1, 1, seq_length] => let's predict one token
-        >>> target_mapping[0, 0, -1] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)
-
-        >>> outputs = model(input_ids, perm_mask=tf.constant(perm_mask, dtype=tf.float32), target_mapping=tf.constant(target_mapping, dtype=tf.float32))
-
-        >>> next_token_logits = outputs[0]  # Output has shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]
+        >>> target_mapping = np.zeros(
+        ...     (1, 1, input_ids.shape[1])
+        >>> )  # Shape [1, 1, seq_length] => let's predict one token
+        >>> target_mapping[
+        ...     0, 0, -1
+        >>> ] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)
+
+        >>> outputs = model(
+        ...     input_ids,
+        ...     perm_mask=tf.constant(perm_mask, dtype=tf.float32),
+        ...     target_mapping=tf.constant(target_mapping, dtype=tf.float32),
+        ... )
+
+        >>> next_token_logits = outputs[
+        ...     0
+        >>> ]  # Output has shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]
         ```"""
         inputs = input_processing(
             func=self.call,

src/transformers/models/xlnet/modeling_xlnet.py

@@ -1400,31 +1400,53 @@ class XLNetLMHeadModel(XLNetPreTrainedModel):
         >>> from transformers import XLNetTokenizer, XLNetLMHeadModel
         >>> import torch
 
-        >>> tokenizer = XLNetTokenizer.from_pretrained('xlnet-large-cased')
-        >>> model = XLNetLMHeadModel.from_pretrained('xlnet-large-cased')
+        >>> tokenizer = XLNetTokenizer.from_pretrained("xlnet-large-cased")
+        >>> model = XLNetLMHeadModel.from_pretrained("xlnet-large-cased")
 
         >>> # We show how to setup inputs to predict a next token using a bi-directional context.
-        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=False)).unsqueeze(0)  # We will predict the masked token
+        >>> input_ids = torch.tensor(
+        ...     tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=False)
+        >>> ).unsqueeze(
+        ...     0
+        >>> )  # We will predict the masked token
         >>> perm_mask = torch.zeros((1, input_ids.shape[1], input_ids.shape[1]), dtype=torch.float)
         >>> perm_mask[:, :, -1] = 1.0  # Previous tokens don't see last token
-        >>> target_mapping = torch.zeros((1, 1, input_ids.shape[1]), dtype=torch.float)  # Shape [1, 1, seq_length] => let's predict one token
-        >>> target_mapping[0, 0, -1] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)
+        >>> target_mapping = torch.zeros(
+        ...     (1, 1, input_ids.shape[1]), dtype=torch.float
+        >>> )  # Shape [1, 1, seq_length] => let's predict one token
+        >>> target_mapping[
+        ...     0, 0, -1
+        >>> ] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)
 
         >>> outputs = model(input_ids, perm_mask=perm_mask, target_mapping=target_mapping)
-        >>> next_token_logits = outputs[0]  # Output has shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]
+        >>> next_token_logits = outputs[
+        ...     0
+        >>> ]  # Output has shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]
 
         >>> # The same way can the XLNetLMHeadModel be used to be trained by standard auto-regressive language modeling.
-        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=False)).unsqueeze(0)  # We will predict the masked token
+        >>> input_ids = torch.tensor(
+        ...     tokenizer.encode("Hello, my dog is very <mask>", add_special_tokens=False)
+        >>> ).unsqueeze(
+        ...     0
+        >>> )  # We will predict the masked token
         >>> labels = torch.tensor(tokenizer.encode("cute", add_special_tokens=False)).unsqueeze(0)
-        >>> assert labels.shape[0] == 1, 'only one word will be predicted'
+        >>> assert labels.shape[0] == 1, "only one word will be predicted"
         >>> perm_mask = torch.zeros((1, input_ids.shape[1], input_ids.shape[1]), dtype=torch.float)
-        >>> perm_mask[:, :, -1] = 1.0  # Previous tokens don't see last token as is done in standard auto-regressive lm training
-        >>> target_mapping = torch.zeros((1, 1, input_ids.shape[1]), dtype=torch.float)  # Shape [1, 1, seq_length] => let's predict one token
-        >>> target_mapping[0, 0, -1] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)
+        >>> perm_mask[
+        ...     :, :, -1
+        >>> ] = 1.0  # Previous tokens don't see last token as is done in standard auto-regressive lm training
+        >>> target_mapping = torch.zeros(
+        ...     (1, 1, input_ids.shape[1]), dtype=torch.float
+        >>> )  # Shape [1, 1, seq_length] => let's predict one token
+        >>> target_mapping[
+        ...     0, 0, -1
+        >>> ] = 1.0  # Our first (and only) prediction will be the last token of the sequence (the masked token)
 
         >>> outputs = model(input_ids, perm_mask=perm_mask, target_mapping=target_mapping, labels=labels)
         >>> loss = outputs.loss
-        >>> next_token_logits = outputs.logits  # Logits have shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]
+        >>> next_token_logits = (
+        ...     outputs.logits
+        >>> )  # Logits have shape [target_mapping.size(0), target_mapping.size(1), config.vocab_size]
         ```"""
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
@@ -1968,10 +1990,12 @@ class XLNetForQuestionAnswering(XLNetPreTrainedModel):
         >>> from transformers import XLNetTokenizer, XLNetForQuestionAnswering
         >>> import torch
 
-        >>> tokenizer =  XLNetTokenizer.from_pretrained('xlnet-base-cased')
-        >>> model = XLNetForQuestionAnswering.from_pretrained('xlnet-base-cased')
+        >>> tokenizer = XLNetTokenizer.from_pretrained("xlnet-base-cased")
+        >>> model = XLNetForQuestionAnswering.from_pretrained("xlnet-base-cased")
 
-        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
+        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(
+        ...     0
+        >>> )  # Batch size 1
         >>> start_positions = torch.tensor([1])
         >>> end_positions = torch.tensor([3])
         >>> outputs = model(input_ids, start_positions=start_positions, end_positions=end_positions)