[`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/speech_to_text/processing_speech_to_text.py

@@ -36,6 +36,7 @@ class Speech2TextProcessor(ProcessorMixin):
         tokenizer (`Speech2TextTokenizer`):
             An instance of [`Speech2TextTokenizer`]. The tokenizer is a required input.
     """
+
     feature_extractor_class = "Speech2TextFeatureExtractor"
     tokenizer_class = "Speech2TextTokenizer"
 

src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py

@@ -86,6 +86,7 @@ class Speech2Text2Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "speech_to_text_2"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "decoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/speech_to_text_2/processing_speech_to_text_2.py

@@ -35,6 +35,7 @@ class Speech2Text2Processor(ProcessorMixin):
         tokenizer (`Speech2Text2Tokenizer`):
             An instance of [`Speech2Text2Tokenizer`]. The tokenizer is a required input.
     """
+
     feature_extractor_class = "AutoFeatureExtractor"
     tokenizer_class = "Speech2Text2Tokenizer"
 

src/transformers/models/speecht5/configuration_speecht5.py

@@ -194,6 +194,7 @@ class SpeechT5Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "speecht5"
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "num_hidden_layers": "encoder_layers"}
 
@@ -398,6 +399,7 @@ class SpeechT5HifiGanConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "hifigan"
 
     def __init__(

src/transformers/models/speecht5/processing_speecht5.py

@@ -30,6 +30,7 @@ class SpeechT5Processor(ProcessorMixin):
         tokenizer (`SpeechT5Tokenizer`):
             An instance of [`SpeechT5Tokenizer`]. The tokenizer is a required input.
     """
+
     feature_extractor_class = "SpeechT5FeatureExtractor"
     tokenizer_class = "SpeechT5Tokenizer"
 

src/transformers/models/splinter/configuration_splinter.py

@@ -88,6 +88,7 @@ class SplinterConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "splinter"
 
     def __init__(

src/transformers/models/squeezebert/configuration_squeezebert.py

@@ -109,6 +109,7 @@ class SqueezeBertConfig(PretrainedConfig):
     Attributes: pretrained_config_archive_map (Dict[str, str]): A dictionary containing all the available pre-trained
     checkpoints.
     """
+
     pretrained_config_archive_map = SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
     model_type = "squeezebert"
 

src/transformers/models/squeezebert/tokenization_squeezebert.py

@@ -266,8 +266,8 @@ class SqueezeBertTokenizer(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 SqueezeBERT
-        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 SqueezeBERT 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/squeezebert/tokenization_squeezebert_fast.py

@@ -182,8 +182,8 @@ class SqueezeBertTokenizerFast(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 SqueezeBERT
-        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 SqueezeBERT 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/swiftformer/configuration_swiftformer.py

@@ -85,6 +85,7 @@ class SwiftFormerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "swiftformer"
 
     def __init__(

src/transformers/models/swin/configuration_swin.py

@@ -105,6 +105,7 @@ class SwinConfig(BackboneConfigMixin, PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "swin"
 
     attribute_map = {

src/transformers/models/swin2sr/configuration_swin2sr.py

@@ -97,6 +97,7 @@ class Swin2SRConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "swin2sr"
 
     attribute_map = {

src/transformers/models/swinv2/configuration_swinv2.py

@@ -89,6 +89,7 @@ class Swinv2Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "swinv2"
 
     attribute_map = {

src/transformers/models/switch_transformers/configuration_switch_transformers.py

@@ -94,6 +94,7 @@ class SwitchTransformersConfig(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 = "switch_transformers"
     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/t5/configuration_t5.py

@@ -77,6 +77,7 @@ class T5Config(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 = "t5"
     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/table_transformer/configuration_table_transformer.py

@@ -132,6 +132,7 @@ class TableTransformerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "table-transformer"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/table_transformer/modeling_table_transformer.py

@@ -65,10 +65,9 @@ TABLE_TRANSFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [
 # Copied from transformers.models.detr.modeling_detr.DetrDecoderOutput with DETR->TABLE_TRANSFORMER,Detr->TableTransformer
 class TableTransformerDecoderOutput(BaseModelOutputWithCrossAttentions):
     """
-    Base class for outputs of the TABLE_TRANSFORMER decoder. This class adds one attribute to
-    BaseModelOutputWithCrossAttentions, namely an optional stack of intermediate decoder activations, i.e. the output
-    of each decoder layer, each of them gone through a layernorm. This is useful when training the model with auxiliary
-    decoding losses.
+    Base class for outputs of the TABLE_TRANSFORMER decoder. This class adds one attribute to BaseModelOutputWithCrossAttentions,
+    namely an optional stack of intermediate decoder activations, i.e. the output of each decoder layer, each of them
+    gone through a layernorm. This is useful when training the model with auxiliary decoding losses.
 
     Args:
         last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
@@ -97,10 +96,9 @@ class TableTransformerDecoderOutput(BaseModelOutputWithCrossAttentions):
 # Copied from transformers.models.detr.modeling_detr.DetrModelOutput with DETR->TABLE_TRANSFORMER,Detr->TableTransformer
 class TableTransformerModelOutput(Seq2SeqModelOutput):
     """
-    Base class for outputs of the TABLE_TRANSFORMER encoder-decoder model. This class adds one attribute to
-    Seq2SeqModelOutput, namely an optional stack of intermediate decoder activations, i.e. the output of each decoder
-    layer, each of them gone through a layernorm. This is useful when training the model with auxiliary decoding
-    losses.
+    Base class for outputs of the TABLE_TRANSFORMER encoder-decoder model. This class adds one attribute to Seq2SeqModelOutput,
+    namely an optional stack of intermediate decoder activations, i.e. the output of each decoder layer, each of them
+    gone through a layernorm. This is useful when training the model with auxiliary decoding losses.
 
     Args:
         last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
@@ -153,8 +151,8 @@ class TableTransformerObjectDetectionOutput(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 [`~TableTransformerImageProcessor.post_process_object_detection`] to
-            retrieve the unnormalized bounding boxes.
+            possible padding). You can use [`~TableTransformerImageProcessor.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
@@ -1583,15 +1581,15 @@ def sigmoid_focal_loss(inputs, targets, num_boxes, alpha: float = 0.25, gamma: f
 # Copied from transformers.models.detr.modeling_detr.DetrLoss with Detr->TableTransformer,detr->table_transformer
 class TableTransformerLoss(nn.Module):
     """
-    This class computes the losses for TableTransformerForObjectDetection/TableTransformerForSegmentation. The process
-    happens in two steps: 1) we compute hungarian assignment between ground truth boxes and the outputs of the model 2)
-    we supervise each pair of matched ground-truth / prediction (supervise class and box).
-
-    A note on the `num_classes` argument (copied from original repo in table_transformer.py): "the naming of the
-    `num_classes` parameter of the criterion is somewhat misleading. It indeed corresponds to `max_obj_id` + 1, where
-    `max_obj_id` is the maximum id for a class in your dataset. For example, COCO has a `max_obj_id` of 90, so we pass
-    `num_classes` to be 91. As another example, for a dataset that has a single class with `id` 1, you should pass
-    `num_classes` to be 2 (`max_obj_id` + 1). For more details on this, check the following discussion
+    This class computes the losses for TableTransformerForObjectDetection/TableTransformerForSegmentation. The process happens in two steps: 1)
+    we compute hungarian assignment between ground truth boxes and the outputs of the model 2) we supervise each pair
+    of matched ground-truth / prediction (supervise class and box).
+
+    A note on the `num_classes` argument (copied from original repo in table_transformer.py): "the naming of the `num_classes`
+    parameter of the criterion is somewhat misleading. It indeed corresponds to `max_obj_id` + 1, where `max_obj_id` is
+    the maximum id for a class in your dataset. For example, COCO has a `max_obj_id` of 90, so we pass `num_classes` to
+    be 91. As another example, for a dataset that has a single class with `id` 1, you should pass `num_classes` to be 2
+    (`max_obj_id` + 1). For more details on this, check the following discussion
     https://github.com/facebookresearch/table_transformer/issues/108#issuecomment-650269223"
 
 

src/transformers/models/time_series_transformer/configuration_time_series_transformer.py

@@ -127,6 +127,7 @@ class TimeSeriesTransformerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "time_series_transformer"
     attribute_map = {
         "hidden_size": "d_model",

src/transformers/models/timesformer/configuration_timesformer.py

@@ -85,6 +85,7 @@ class TimesformerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "timesformer"
 
     def __init__(

src/transformers/models/timm_backbone/configuration_timm_backbone.py

@@ -60,6 +60,7 @@ class TimmBackboneConfig(PretrainedConfig):
     >>> configuration = model.config
     ```
     """
+
     model_type = "timm_backbone"
 
     def __init__(