[`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/nllb_moe/configuration_nllb_moe.py

@@ -125,6 +125,7 @@ class NllbMoeConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "nllb-moe"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/nougat/processing_nougat.py

@@ -37,6 +37,7 @@ class NougatProcessor(ProcessorMixin):
         tokenizer ([`NougatTokenizerFast`]):
             An instance of [`NougatTokenizerFast`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "AutoImageProcessor"
     tokenizer_class = "AutoTokenizer"

src/transformers/models/nougat/tokenization_nougat_fast.py

@@ -251,7 +251,7 @@ def remove_numbers(lines):
     def _clean(s):
         return re.sub(r"(?:[\d_]|\*\*)", "", s).strip()
 
-    if type(lines) is str:
+    if isinstance(lines, str):
         return _clean(lines)
     out = []
     for l in lines:

src/transformers/models/nystromformer/configuration_nystromformer.py

@@ -89,6 +89,7 @@ class NystromformerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "nystromformer"
 
     def __init__(

src/transformers/models/oneformer/configuration_oneformer.py

@@ -137,6 +137,7 @@ class OneFormerConfig(PretrainedConfig):
     >>> configuration = model.config
     ```
     """
+
     model_type = "oneformer"
     attribute_map = {"hidden_size": "hidden_dim"}
 

src/transformers/models/oneformer/modeling_oneformer.py

@@ -3247,5 +3247,5 @@ class OneFormerForUniversalSegmentation(OneFormerPreTrainedModel):
         if not return_dict:
             output = tuple(v for v in output.values())
             if loss is not None:
-                output = ((loss)) + output
+                output = (loss) + output
         return output

src/transformers/models/oneformer/processing_oneformer.py

@@ -42,6 +42,7 @@ class OneFormerProcessor(ProcessorMixin):
         task_seq_len (`int`, *optional*, defaults to 77):
             Sequence length for input task token.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "OneFormerImageProcessor"
     tokenizer_class = ("CLIPTokenizer", "CLIPTokenizerFast")

src/transformers/models/opt/configuration_opt.py

@@ -93,6 +93,7 @@ class OPTConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "opt"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/owlv2/configuration_owlv2.py

@@ -46,8 +46,8 @@ class Owlv2TextConfig(PretrainedConfig):
 
     Args:
         vocab_size (`int`, *optional*, defaults to 49408):
-            Vocabulary size of the OWLv2 text model. Defines the number of different tokens that can be represented by
-            the `inputs_ids` passed when calling [`Owlv2TextModel`].
+            Vocabulary size of the OWLv2 text model. Defines the number of different tokens that can be represented
+            by the `inputs_ids` passed when calling [`Owlv2TextModel`].
         hidden_size (`int`, *optional*, defaults to 512):
             Dimensionality of the encoder layers and the pooler layer.
         intermediate_size (`int`, *optional*, defaults to 2048):
@@ -92,6 +92,7 @@ class Owlv2TextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "owlv2_text_model"
 
     def __init__(
@@ -148,8 +149,8 @@ class Owlv2TextConfig(PretrainedConfig):
 # Copied from transformers.models.owlvit.configuration_owlvit.OwlViTVisionConfig with OwlViT->Owlv2, owlvit-base-patch32->owlv2-base-patch16, owlvit->owlv2, OWL-ViT->OWLv2, 32->16
 class Owlv2VisionConfig(PretrainedConfig):
     r"""
-    This is the configuration class to store the configuration of an [`Owlv2VisionModel`]. It is used to instantiate an
-    OWLv2 image encoder according to the specified arguments, defining the model architecture. Instantiating a
+    This is the configuration class to store the configuration of an [`Owlv2VisionModel`]. It is used to instantiate
+    an OWLv2 image encoder according to the specified arguments, defining the model architecture. Instantiating a
     configuration with the defaults will yield a similar configuration to that of the OWLv2
     [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) architecture.
 
@@ -255,8 +256,8 @@ class Owlv2VisionConfig(PretrainedConfig):
 class Owlv2Config(PretrainedConfig):
     r"""
     [`Owlv2Config`] is the configuration class to store the configuration of an [`Owlv2Model`]. It is used to
-    instantiate an OWLv2 model according to the specified arguments, defining the text model and vision model configs.
-    Instantiating a configuration with the defaults will yield a similar configuration to that of the OWLv2
+    instantiate an OWLv2 model according to the specified arguments, defining the text model and vision model
+    configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWLv2
     [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
@@ -270,7 +271,8 @@ class Owlv2Config(PretrainedConfig):
         projection_dim (`int`, *optional*, defaults to 512):
             Dimensionality of text and vision projection layers.
         logit_scale_init_value (`float`, *optional*, defaults to 2.6592):
-            The inital value of the *logit_scale* parameter. Default is used as per the original OWLv2 implementation.
+            The inital value of the *logit_scale* parameter. Default is used as per the original OWLv2
+            implementation.
         return_dict (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return a dictionary. If `False`, returns a tuple.
         kwargs (*optional*):
@@ -323,8 +325,8 @@ class Owlv2Config(PretrainedConfig):
     @classmethod
     def from_text_vision_configs(cls, text_config: Dict, vision_config: Dict, **kwargs):
         r"""
-        Instantiate a [`Owlv2Config`] (or a derived class) from owlv2 text model configuration and owlv2 vision model
-        configuration.
+        Instantiate a [`Owlv2Config`] (or a derived class) from owlv2 text model configuration and owlv2 vision
+        model configuration.
 
         Returns:
             [`Owlv2Config`]: An instance of a configuration object

src/transformers/models/owlv2/modeling_owlv2.py

@@ -245,11 +245,11 @@ class Owlv2ImageGuidedObjectDetectionOutput(ModelOutput):
             (disregarding possible padding). You can use [`~Owlv2ImageProcessor.post_process_object_detection`] to
             retrieve the unnormalized bounding boxes.
         image_embeds (`torch.FloatTensor` of shape `(batch_size, patch_size, patch_size, output_dim`):
-            Pooled output of [`Owlv2VisionModel`]. OWLv2 represents images as a set of image patches and computes image
-            embeddings for each patch.
+            Pooled output of [`Owlv2VisionModel`]. OWLv2 represents images as a set of image patches and computes
+            image embeddings for each patch.
         query_image_embeds (`torch.FloatTensor` of shape `(batch_size, patch_size, patch_size, output_dim`):
-            Pooled output of [`Owlv2VisionModel`]. OWLv2 represents images as a set of image patches and computes image
-            embeddings for each patch.
+            Pooled output of [`Owlv2VisionModel`]. OWLv2 represents images as a set of image patches and computes
+            image embeddings for each patch.
         class_embeds (`torch.FloatTensor` of shape `(batch_size, num_patches, hidden_size)`):
             Class embeddings of all image patches. OWLv2 represents images as a set of image patches where the total
             number of patches is (image_size / patch_size)**2.
@@ -548,9 +548,7 @@ class Owlv2PreTrainedModel(PreTrainedModel):
             nn.init.normal_(module.out_proj.weight, std=out_proj_std)
         elif isinstance(module, Owlv2MLP):
             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/owlv2/processing_owlv2.py

@@ -37,6 +37,7 @@ class Owlv2Processor(ProcessorMixin):
         tokenizer ([`CLIPTokenizer`, `CLIPTokenizerFast`]):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "Owlv2ImageProcessor"
     tokenizer_class = ("CLIPTokenizer", "CLIPTokenizerFast")

src/transformers/models/owlvit/configuration_owlvit.py

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

src/transformers/models/owlvit/image_processing_owlvit.py

@@ -124,6 +124,7 @@ class OwlViTImageProcessor(BaseImageProcessor):
         image_std (`List[int]`, *optional*, defaults to `[0.26862954, 0.26130258, 0.27577711]`):
             The sequence of standard deviations for each channel, to be used when normalizing images.
     """
+
     model_input_names = ["pixel_values"]
 
     def __init__(

src/transformers/models/owlvit/modeling_owlvit.py

@@ -540,9 +540,7 @@ class OwlViTPreTrainedModel(PreTrainedModel):
             nn.init.normal_(module.out_proj.weight, std=out_proj_std)
         elif isinstance(module, OwlViTMLP):
             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/owlvit/processing_owlvit.py

@@ -38,6 +38,7 @@ class OwlViTProcessor(ProcessorMixin):
         tokenizer ([`CLIPTokenizer`, `CLIPTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "OwlViTImageProcessor"
     tokenizer_class = ("CLIPTokenizer", "CLIPTokenizerFast")

src/transformers/models/pegasus/configuration_pegasus.py

@@ -97,6 +97,7 @@ class PegasusConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "pegasus"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/pegasus/tokenization_pegasus.py

@@ -96,6 +96,7 @@ class PegasusTokenizer(PreTrainedTokenizer):
             - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
               BPE-dropout.
     """
+
     vocab_files_names = VOCAB_FILES_NAMES
     pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
     max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES

src/transformers/models/pegasus/tokenization_pegasus_fast.py

@@ -91,6 +91,7 @@ class PegasusTokenizerFast(PreTrainedTokenizerFast):
             tokenizer](https://github.com/google-research/pegasus/blob/939830367bcf411193d2b5eca2f2f90f3f9260ca/pegasus/ops/pretrain_parsing_ops.cc#L66)
             that uses the tokens 2 - 104 only for pretraining
     """
+
     vocab_files_names = VOCAB_FILES_NAMES
     pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
     max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES

src/transformers/models/pegasus_x/configuration_pegasus_x.py

@@ -103,6 +103,7 @@ class PegasusXConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "pegasus_x"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/perceiver/configuration_perceiver.py

@@ -117,6 +117,7 @@ class PerceiverConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "perceiver"
 
     def __init__(