[`Styling`] stylify using ruff (#27144)

* try to stylify using ruff

* might need to remove these changes?

* use ruf format andruff check

* use isinstance instead of type comparision

* use # fmt: skip

* use # fmt: skip

* nits

* soem styling changes

* update ci job

* nits isinstance

* more files update

* nits

* more nits

* small nits

* check and format

* revert wrong changes

* actually use formatter instead of checker

* nits

* well docbuilder is overwriting this commit

* revert notebook changes

* try to nuke docbuilder

* style

* fix feature exrtaction test

* remve `indent-width = 4`

* fixup

* more nits

* update the ruff version that we use

* style

* nuke docbuilder styling

* leve the print for detected changes

* nits

* Remove file I/O
Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>

* style

* nits

* revert notebook changes

* Add # fmt skip when possible

* Add # fmt skip when possible

* Fix

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* NIts

* more fixes

* fix tapas

* Another way to skip

* Recommended way

* Fix two more fiels

* Remove asynch
Remove asynch

---------
Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>

src/transformers/models/clap/processing_clap.py

@@ -33,6 +33,7 @@ class ClapProcessor(ProcessorMixin):
         tokenizer ([`RobertaTokenizerFast`]):
             The tokenizer is a required input.
     """
+
     feature_extractor_class = "ClapFeatureExtractor"
     tokenizer_class = ("RobertaTokenizer", "RobertaTokenizerFast")
 

src/transformers/models/clip/configuration_clip.py

@@ -96,6 +96,7 @@ class CLIPTextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "clip_text_model"
 
     def __init__(

src/transformers/models/clip/modeling_clip.py

@@ -421,9 +421,7 @@ class CLIPPreTrainedModel(PreTrainedModel):
             nn.init.normal_(module.out_proj.weight, std=out_proj_std)
         elif isinstance(module, CLIPMLP):
             factor = self.config.initializer_factor
-            in_proj_std = (
-                (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
-            )
+            in_proj_std = (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
             fc_std = (2 * module.config.hidden_size) ** -0.5 * factor
             nn.init.normal_(module.fc1.weight, std=fc_std)
             nn.init.normal_(module.fc2.weight, std=in_proj_std)

src/transformers/models/clip/processing_clip.py

@@ -35,6 +35,7 @@ class CLIPProcessor(ProcessorMixin):
         tokenizer ([`CLIPTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "CLIPImageProcessor"
     tokenizer_class = ("CLIPTokenizer", "CLIPTokenizerFast")

src/transformers/models/clipseg/configuration_clipseg.py

@@ -86,6 +86,7 @@ class CLIPSegTextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "clipseg_text_model"
 
     def __init__(

src/transformers/models/clipseg/modeling_clipseg.py

@@ -77,8 +77,7 @@ class CLIPSegOutput(ModelOutput):
         text_embeds(`torch.FloatTensor` of shape `(batch_size, output_dim`):
             The text embeddings obtained by applying the projection layer to the pooled output of [`CLIPSegTextModel`].
         image_embeds(`torch.FloatTensor` of shape `(batch_size, output_dim`):
-            The image embeddings obtained by applying the projection layer to the pooled output of
-            [`CLIPSegVisionModel`].
+            The image embeddings obtained by applying the projection layer to the pooled output of [`CLIPSegVisionModel`].
         text_model_output(`BaseModelOutputWithPooling`):
             The output of the [`CLIPSegTextModel`].
         vision_model_output(`BaseModelOutputWithPooling`):
@@ -443,9 +442,7 @@ class CLIPSegPreTrainedModel(PreTrainedModel):
             nn.init.normal_(module.out_proj.weight, std=out_proj_std)
         elif isinstance(module, CLIPSegMLP):
             factor = self.config.initializer_factor
-            in_proj_std = (
-                (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
-            )
+            in_proj_std = (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
             fc_std = (2 * module.config.hidden_size) ** -0.5 * factor
             nn.init.normal_(module.fc1.weight, std=fc_std)
             nn.init.normal_(module.fc2.weight, std=in_proj_std)

src/transformers/models/clipseg/processing_clipseg.py

@@ -35,6 +35,7 @@ class CLIPSegProcessor(ProcessorMixin):
         tokenizer ([`CLIPTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "ViTImageProcessor"
     tokenizer_class = ("CLIPTokenizer", "CLIPTokenizerFast")

src/transformers/models/clvp/modeling_clvp.py

@@ -684,9 +684,7 @@ class ClvpPreTrainedModel(PreTrainedModel):
                 module.bias.data.zero_()
         elif isinstance(module, ClvpEncoderMLP):
             factor = self.config.initializer_factor
-            in_proj_std = (
-                (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
-            )
+            in_proj_std = (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
             fc_std = (2 * module.config.hidden_size) ** -0.5 * factor
             nn.init.normal_(module.fc1.proj.weight if getattr(module.fc1, "proj") else module.fc1.weight, std=fc_std)
             nn.init.normal_(module.fc2.weight, std=in_proj_std)

src/transformers/models/clvp/processing_clvp.py

@@ -34,6 +34,7 @@ class ClvpProcessor(ProcessorMixin):
         tokenizer (`ClvpTokenizer`):
             An instance of [`ClvpTokenizer`]. The tokenizer is a required input.
     """
+
     feature_extractor_class = "ClvpFeatureExtractor"
     tokenizer_class = "ClvpTokenizer"
     model_input_names = [
@@ -76,15 +77,15 @@ class ClvpProcessor(ProcessorMixin):
     # Copied from transformers.models.whisper.processing_whisper.WhisperProcessor.batch_decode with Whisper->Clvp
     def batch_decode(self, *args, **kwargs):
         """
-        This method forwards all its arguments to ClvpTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer
-        to the docstring of this method for more information.
+        This method forwards all its arguments to ClvpTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please
+        refer to the docstring of this method for more information.
         """
         return self.tokenizer.batch_decode(*args, **kwargs)
 
     # Copied from transformers.models.whisper.processing_whisper.WhisperProcessor.decode with Whisper->Clvp
     def decode(self, *args, **kwargs):
         """
-        This method forwards all its arguments to ClvpTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the
-        docstring of this method for more information.
+        This method forwards all its arguments to ClvpTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to
+        the docstring of this method for more information.
         """
         return self.tokenizer.decode(*args, **kwargs)

src/transformers/models/codegen/configuration_codegen.py

@@ -105,6 +105,7 @@ class CodeGenConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "codegen"
     attribute_map = {
         "max_position_embeddings": "n_positions",

src/transformers/models/conditional_detr/configuration_conditional_detr.py

@@ -134,6 +134,7 @@ class ConditionalDetrConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "conditional_detr"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/conditional_detr/image_processing_conditional_detr.py

@@ -478,8 +478,7 @@ def post_process_panoptic_sample(
     threshold=0.85,
 ) -> Dict:
     """
-    Converts the output of [`ConditionalDetrForSegmentation`] into panoptic segmentation predictions for a single
-    sample.
+    Converts the output of [`ConditionalDetrForSegmentation`] into panoptic segmentation predictions for a single sample.
 
     Args:
         out_logits (`torch.Tensor`):
@@ -1454,8 +1453,7 @@ class ConditionalDetrImageProcessor(BaseImageProcessor):
     # Copied from transformers.models.detr.image_processing_detr.DetrImageProcessor.post_process_semantic_segmentation with Detr->ConditionalDetr
     def post_process_semantic_segmentation(self, outputs, target_sizes: List[Tuple[int, int]] = None):
         """
-        Converts the output of [`ConditionalDetrForSegmentation`] into semantic segmentation maps. Only supports
-        PyTorch.
+        Converts the output of [`ConditionalDetrForSegmentation`] into semantic segmentation maps. Only supports PyTorch.
 
         Args:
             outputs ([`ConditionalDetrForSegmentation`]):
@@ -1511,8 +1509,7 @@ class ConditionalDetrImageProcessor(BaseImageProcessor):
         return_coco_annotation: Optional[bool] = False,
     ) -> List[Dict]:
         """
-        Converts the output of [`ConditionalDetrForSegmentation`] into instance segmentation predictions. Only supports
-        PyTorch.
+        Converts the output of [`ConditionalDetrForSegmentation`] into instance segmentation predictions. Only supports PyTorch.
 
         Args:
             outputs ([`ConditionalDetrForSegmentation`]):
@@ -1596,8 +1593,8 @@ class ConditionalDetrImageProcessor(BaseImageProcessor):
         target_sizes: Optional[List[Tuple[int, int]]] = None,
     ) -> List[Dict]:
         """
-        Converts the output of [`ConditionalDetrForSegmentation`] into image panoptic segmentation predictions. Only
-        supports PyTorch.
+        Converts the output of [`ConditionalDetrForSegmentation`] into image panoptic segmentation predictions. Only supports
+        PyTorch.
 
         Args:
             outputs ([`ConditionalDetrForSegmentation`]):

src/transformers/models/conditional_detr/modeling_conditional_detr.py

@@ -153,8 +153,8 @@ class ConditionalDetrObjectDetectionOutput(ModelOutput):
         pred_boxes (`torch.FloatTensor` of shape `(batch_size, num_queries, 4)`):
             Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These
             values are normalized in [0, 1], relative to the size of each individual image in the batch (disregarding
-            possible padding). You can use [`~ConditionalDetrImageProcessor.post_process_object_detection`] to retrieve
-            the unnormalized bounding boxes.
+            possible padding). You can use [`~ConditionalDetrImageProcessor.post_process_object_detection`] to retrieve the
+            unnormalized bounding boxes.
         auxiliary_outputs (`list[Dict]`, *optional*):
             Optional, only returned when auxilary losses are activated (i.e. `config.auxiliary_loss` is set to `True`)
             and labels are provided. It is a list of dictionaries containing the two above keys (`logits` and
@@ -217,14 +217,14 @@ class ConditionalDetrSegmentationOutput(ModelOutput):
         pred_boxes (`torch.FloatTensor` of shape `(batch_size, num_queries, 4)`):
             Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These
             values are normalized in [0, 1], relative to the size of each individual image in the batch (disregarding
-            possible padding). You can use [`~ConditionalDetrImageProcessor.post_process_object_detection`] to retrieve
-            the unnormalized bounding boxes.
+            possible padding). You can use [`~ConditionalDetrImageProcessor.post_process_object_detection`] to retrieve the
+            unnormalized bounding boxes.
         pred_masks (`torch.FloatTensor` of shape `(batch_size, num_queries, height/4, width/4)`):
             Segmentation masks logits for all queries. See also
             [`~ConditionalDetrImageProcessor.post_process_semantic_segmentation`] or
             [`~ConditionalDetrImageProcessor.post_process_instance_segmentation`]
-            [`~ConditionalDetrImageProcessor.post_process_panoptic_segmentation`] to evaluate semantic, instance and
-            panoptic segmentation masks respectively.
+            [`~ConditionalDetrImageProcessor.post_process_panoptic_segmentation`] to evaluate semantic, instance and panoptic
+            segmentation masks respectively.
         auxiliary_outputs (`list[Dict]`, *optional*):
             Optional, only returned when auxiliary losses are activated (i.e. `config.auxiliary_loss` is set to `True`)
             and labels are provided. It is a list of dictionaries containing the two above keys (`logits` and

src/transformers/models/convbert/configuration_convbert.py

@@ -96,6 +96,7 @@ class ConvBertConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "convbert"
 
     def __init__(

src/transformers/models/convbert/tokenization_convbert.py

@@ -263,8 +263,8 @@ class ConvBertTokenizer(PreTrainedTokenizer):
         self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
     ) -> List[int]:
         """
-        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A ConvBERT
-        sequence pair mask has the following format:
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A ConvBERT sequence
+        pair mask has the following format:
 
         ```
         0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1

src/transformers/models/convbert/tokenization_convbert_fast.py

@@ -168,8 +168,8 @@ class ConvBertTokenizerFast(PreTrainedTokenizerFast):
         self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
     ) -> List[int]:
         """
-        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A ConvBERT
-        sequence pair mask has the following format:
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A ConvBERT sequence
+        pair mask has the following format:
 
         ```
         0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1

src/transformers/models/convnext/configuration_convnext.py

@@ -87,6 +87,7 @@ class ConvNextConfig(BackboneConfigMixin, PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "convnext"
 
     def __init__(

src/transformers/models/convnextv2/configuration_convnextv2.py

@@ -79,6 +79,7 @@ class ConvNextV2Config(BackboneConfigMixin, PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "convnextv2"
 
     def __init__(

src/transformers/models/cpmant/configuration_cpmant.py

@@ -84,6 +84,7 @@ class CpmAntConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "cpmant"
 
     def __init__(

src/transformers/models/cvt/configuration_cvt.py

@@ -96,6 +96,7 @@ class CvtConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "cvt"
 
     def __init__(