[`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/transfo_xl/tokenization_transfo_xl.py

@@ -212,7 +212,7 @@ class TransfoXLTokenizer(PreTrainedTokenizer):
                 # Loading a torch-saved transfo-xl vocab dict with pickle results in an integer
                 # Entering this if statement means that we tried to load a torch-saved file with pickle, and we failed.
                 # We therefore load it with torch, if it's available.
-                if type(vocab_dict) == int:
+                if isinstance(vocab_dict, int):
                     if not is_torch_available():
                         raise ImportError(
                             "Not trying to load dict with PyTorch as you need to install pytorch to load "

src/transformers/models/trocr/configuration_trocr.py

@@ -91,6 +91,7 @@ class TrOCRConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "trocr"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/trocr/processing_trocr.py

@@ -35,6 +35,7 @@ class TrOCRProcessor(ProcessorMixin):
         tokenizer ([`RobertaTokenizer`/`XLMRobertaTokenizer`], *optional*):
             An instance of [`RobertaTokenizer`/`XLMRobertaTokenizer`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "AutoImageProcessor"
     tokenizer_class = "AutoTokenizer"

src/transformers/models/tvlt/configuration_tvlt.py

@@ -110,6 +110,7 @@ class TvltConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "tvlt"
 
     def __init__(

src/transformers/models/tvlt/processing_tvlt.py

@@ -32,6 +32,7 @@ class TvltProcessor(ProcessorMixin):
         feature_extractor (`TvltFeatureExtractor`):
             An instance of [`TvltFeatureExtractor`]. The feature extractor is a required input.
     """
+
     attributes = ["image_processor", "feature_extractor"]
     image_processor_class = "TvltImageProcessor"
     feature_extractor_class = "TvltFeatureExtractor"

src/transformers/models/umt5/configuration_umt5.py

@@ -73,6 +73,7 @@ class UMT5Config(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 = "umt5"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/umt5/modeling_umt5.py

@@ -940,6 +940,7 @@ class UMT5Model(UMT5PreTrainedModel):
     >>> outputs = model(input_ids=inputs["input_ids"], decoder_input_ids=labels["input_ids"])
     >>> hidden_states = outputs.last_hidden_state
     ```"""
+
     model_type = "uumt5"
     config_class = UMT5Config
     _tied_weights_keys = ["encoder.embed_tokens.weight", "decoder.embed_tokens.weight"]

src/transformers/models/unispeech/configuration_unispeech.py

@@ -187,6 +187,7 @@ class UniSpeechConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "unispeech"
 
     def __init__(

src/transformers/models/unispeech_sat/configuration_unispeech_sat.py

@@ -197,6 +197,7 @@ class UniSpeechSatConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "unispeech-sat"
 
     def __init__(

src/transformers/models/upernet/configuration_upernet.py

@@ -69,6 +69,7 @@ class UperNetConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "upernet"
 
     def __init__(

src/transformers/models/videomae/configuration_videomae.py

@@ -94,6 +94,7 @@ class VideoMAEConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "videomae"
 
     def __init__(

src/transformers/models/vilt/configuration_vilt.py

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

src/transformers/models/vilt/processing_vilt.py

@@ -37,6 +37,7 @@ class ViltProcessor(ProcessorMixin):
         tokenizer (`BertTokenizerFast`, *optional*):
             An instance of ['BertTokenizerFast`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "ViltImageProcessor"
     tokenizer_class = ("BertTokenizer", "BertTokenizerFast")

src/transformers/models/vision_encoder_decoder/configuration_vision_encoder_decoder.py

@@ -76,6 +76,7 @@ class VisionEncoderDecoderConfig(PretrainedConfig):
     >>> 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

@@ -272,6 +272,7 @@ class FlaxVisionEncoderDecoderModel(FlaxPreTrainedModel):
     another one as decoder module when created with the :meth*~transformers.FlaxAutoModel.from_pretrained* class method
     for the encoder and :meth*~transformers.FlaxAutoModelForCausalLM.from_pretrained* class method for the decoder.
     """
+
     config_class = VisionEncoderDecoderConfig
     base_model_prefix = "vision_encoder_decoder"
     main_input_name = "pixel_values"

src/transformers/models/vision_encoder_decoder/modeling_tf_vision_encoder_decoder.py

@@ -180,6 +180,7 @@ class TFVisionEncoderDecoderModel(TFPreTrainedModel, TFCausalLanguageModelingLos
     decoder when created with the [`~TFAutoModel.from_pretrained`] class method for the encoder and
     [`~TFAutoModelForCausalLM.from_pretrained`] class method for the decoder.
     """
+
     config_class = VisionEncoderDecoderConfig
     base_model_prefix = "vision_encoder_decoder"
     load_weight_prefix = "tf_vision_encoder_decoder_model"

src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py

@@ -155,6 +155,7 @@ class VisionEncoderDecoderModel(PreTrainedModel):
     :meth*~transformers.AutoModel.from_pretrained* class method for the encoder and
     :meth*~transformers.AutoModelForCausalLM.from_pretrained* class method for the decoder.
     """
+
     config_class = VisionEncoderDecoderConfig
     base_model_prefix = "vision_encoder_decoder"
     main_input_name = "pixel_values"

src/transformers/models/vision_text_dual_encoder/processing_vision_text_dual_encoder.py

@@ -37,6 +37,7 @@ class VisionTextDualEncoderProcessor(ProcessorMixin):
         tokenizer ([`PreTrainedTokenizer`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "AutoImageProcessor"
     tokenizer_class = "AutoTokenizer"

src/transformers/models/visual_bert/configuration_visual_bert.py

@@ -35,7 +35,7 @@ VISUAL_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
     "uclanlp/visualbert-nlvr2-pre": "https://huggingface.co/uclanlp/visualbert-nlvr2-pre/resolve/main/config.json",
     "uclanlp/visualbert-nlvr2-coco-pre": (
         "https://huggingface.co/uclanlp/visualbert-nlvr2-coco-pre/resolve/main/config.json"
-    )
+    ),
     # See all VisualBERT models at https://huggingface.co/models?filter=visual_bert
 }
 

src/transformers/models/visual_bert/modeling_visual_bert.py

@@ -57,7 +57,7 @@ VISUAL_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "uclanlp/visualbert-vcr-coco-pre",
     "uclanlp/visualbert-nlvr2",
     "uclanlp/visualbert-nlvr2-pre",
-    "uclanlp/visualbert-nlvr2-coco-pre"
+    "uclanlp/visualbert-nlvr2-coco-pre",
     # See all VisualBERT models at https://huggingface.co/models?filter=visual_bert
 ]