[`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/layoutlmv2/configuration_layoutlmv2.py

@@ -114,6 +114,7 @@ class LayoutLMv2Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "layoutlmv2"
 
     def __init__(

src/transformers/models/layoutlmv2/processing_layoutlmv2.py

@@ -43,6 +43,7 @@ class LayoutLMv2Processor(ProcessorMixin):
         tokenizer (`LayoutLMv2Tokenizer` or `LayoutLMv2TokenizerFast`, *optional*):
             An instance of [`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "LayoutLMv2ImageProcessor"
     tokenizer_class = ("LayoutLMv2Tokenizer", "LayoutLMv2TokenizerFast")

src/transformers/models/layoutlmv3/configuration_layoutlmv3.py

@@ -119,6 +119,7 @@ class LayoutLMv3Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "layoutlmv3"
 
     def __init__(

src/transformers/models/layoutlmv3/modeling_layoutlmv3.py

@@ -904,8 +904,9 @@ class LayoutLMv3Model(LayoutLMv3PreTrainedModel):
         final_bbox = final_position_ids = None
         patch_height = patch_width = None
         if pixel_values is not None:
-            patch_height, patch_width = int(pixel_values.shape[2] / self.config.patch_size), int(
-                pixel_values.shape[3] / self.config.patch_size
+            patch_height, patch_width = (
+                int(pixel_values.shape[2] / self.config.patch_size),
+                int(pixel_values.shape[3] / self.config.patch_size),
             )
             visual_embeddings = self.forward_image(pixel_values)
             visual_attention_mask = torch.ones(

src/transformers/models/layoutlmv3/processing_layoutlmv3.py

@@ -43,6 +43,7 @@ class LayoutLMv3Processor(ProcessorMixin):
         tokenizer (`LayoutLMv3Tokenizer` or `LayoutLMv3TokenizerFast`, *optional*):
             An instance of [`LayoutLMv3Tokenizer`] or [`LayoutLMv3TokenizerFast`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "LayoutLMv3ImageProcessor"
     tokenizer_class = ("LayoutLMv3Tokenizer", "LayoutLMv3TokenizerFast")

src/transformers/models/layoutlmv3/tokenization_layoutlmv3.py

@@ -268,6 +268,7 @@ class LayoutLMv3Tokenizer(PreTrainedTokenizer):
         only_label_first_subword (`bool`, *optional*, defaults to `True`):
             Whether or not to only label the first subword, in case word labels are provided.
     """
+
     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/led/configuration_led.py

@@ -97,6 +97,7 @@ class LEDConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "led"
     attribute_map = {
         "num_attention_heads": "encoder_attention_heads",

src/transformers/models/levit/configuration_levit.py

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

src/transformers/models/lilt/configuration_lilt.py

@@ -90,6 +90,7 @@ class LiltConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "lilt"
 
     def __init__(

src/transformers/models/llama/configuration_llama.py

@@ -110,6 +110,7 @@ class LlamaConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "llama"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/longformer/configuration_longformer.py

@@ -104,6 +104,7 @@ class LongformerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "longformer"
 
     def __init__(

src/transformers/models/longformer/tokenization_longformer.py

@@ -416,8 +416,8 @@ class LongformerTokenizer(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. Longformer does
-        not make use of token type ids, therefore a list of zeros is returned.
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. Longformer does not
+        make use of token type ids, therefore a list of zeros is returned.
 
         Args:
             token_ids_0 (`List[int]`):

src/transformers/models/longformer/tokenization_longformer_fast.py

@@ -254,8 +254,8 @@ class LongformerTokenizerFast(PreTrainedTokenizerFast):
         `str`: Mask token, to use when training a model with masked-language modeling. Log an error if used while not
         having been set.
 
-        Longformer tokenizer has a special mask token to be usable in the fill-mask pipeline. The mask token will
-        greedily comprise the space before the *<mask>*.
+        Longformer tokenizer has a special mask token to be usable in the fill-mask pipeline. The mask token will greedily
+        comprise the space before the *<mask>*.
         """
         if self._mask_token is None:
             if self.verbose:
@@ -309,8 +309,8 @@ class LongformerTokenizerFast(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. Longformer does
-        not make use of token type ids, therefore a list of zeros is returned.
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. Longformer does not
+        make use of token type ids, therefore a list of zeros is returned.
 
         Args:
             token_ids_0 (`List[int]`):

src/transformers/models/longt5/configuration_longt5.py

@@ -82,6 +82,7 @@ class LongT5Config(PretrainedConfig):
         use_cache (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return the last key/values attentions (not used by all models).
     """
+
     model_type = "longt5"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"hidden_size": "d_model", "num_attention_heads": "num_heads", "num_hidden_layers": "num_layers"}

src/transformers/models/luke/configuration_luke.py

@@ -97,6 +97,7 @@ class LukeConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "luke"
 
     def __init__(

src/transformers/models/lxmert/tokenization_lxmert.py

@@ -254,8 +254,8 @@ class LxmertTokenizer(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 Lxmert
-        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 Lxmert 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/lxmert/tokenization_lxmert_fast.py

@@ -161,8 +161,8 @@ class LxmertTokenizerFast(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 Lxmert
-        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 Lxmert 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/m2m_100/configuration_m2m_100.py

@@ -99,6 +99,7 @@ class M2M100Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "m2m_100"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/marian/configuration_marian.py

@@ -102,6 +102,7 @@ class MarianConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "marian"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/markuplm/configuration_markuplm.py

@@ -97,6 +97,7 @@ class MarkupLMConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "markuplm"
 
     def __init__(