[`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/persimmon/configuration_persimmon.py

@@ -88,6 +88,7 @@ class PersimmonConfig(PretrainedConfig):
     >>> # Initializing a Persimmon persimmon-7b style configuration
     >>> configuration = PersimmonConfig()
     ```"""
+
     model_type = "persimmon"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/phi/configuration_phi.py

@@ -103,6 +103,7 @@ class PhiConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "phi"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/pix2struct/configuration_pix2struct.py

@@ -90,6 +90,7 @@ class Pix2StructTextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "pix2struct_text_model"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/pix2struct/processing_pix2struct.py

@@ -37,6 +37,7 @@ class Pix2StructProcessor(ProcessorMixin):
         tokenizer (Union[`T5TokenizerFast`, `T5Tokenizer`]):
             An instance of ['T5TokenizerFast`] or ['T5Tokenizer`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "Pix2StructImageProcessor"
     tokenizer_class = ("T5Tokenizer", "T5TokenizerFast")

src/transformers/models/plbart/configuration_plbart.py

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

src/transformers/models/poolformer/configuration_poolformer.py

@@ -91,6 +91,7 @@ class PoolFormerConfig(PretrainedConfig):
     >>> configuration = model.config
     ```
     """
+
     model_type = "poolformer"
 
     def __init__(

src/transformers/models/pop2piano/feature_extraction_pop2piano.py

@@ -76,6 +76,7 @@ class Pop2PianoFeatureExtractor(SequenceFeatureExtractor):
         num_bars (`int`, *optional*, defaults to 2):
             Determines interval between each sequence.
     """
+
     model_input_names = ["input_features", "beatsteps", "extrapolated_beatstep"]
 
     def __init__(

src/transformers/models/pop2piano/processing_pop2piano.py

@@ -39,6 +39,7 @@ class Pop2PianoProcessor(ProcessorMixin):
         tokenizer (`Pop2PianoTokenizer`):
             An instance of ['Pop2PianoTokenizer`]. The tokenizer is a required input.
     """
+
     attributes = ["feature_extractor", "tokenizer"]
     feature_extractor_class = "Pop2PianoFeatureExtractor"
     tokenizer_class = "Pop2PianoTokenizer"

src/transformers/models/prophetnet/configuration_prophetnet.py

@@ -98,6 +98,7 @@ class ProphetNetConfig(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 = "prophetnet"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/pvt/configuration_pvt.py

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

src/transformers/models/qdqbert/configuration_qdqbert.py

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

src/transformers/models/rag/modeling_rag.py

@@ -229,6 +229,7 @@ class RagPreTrainedModel(PreTrainedModel):
     generator, the encoder and generator are trainable while the retriever is just an indexed dataset.
 
     """
+
     config_class = RagConfig
     base_model_prefix = "rag"
 

src/transformers/models/rag/modeling_tf_rag.py

@@ -224,6 +224,7 @@ class TFRagPreTrainedModel(TFPreTrainedModel):
     generator, the encoder and generator are trainable while the retriever is just an indexed dataset.
 
     """
+
     config_class = RagConfig
     base_model_prefix = "rag"
     _keys_to_ignore_on_load_missing = [r"position_ids"]

src/transformers/models/realm/configuration_realm.py

@@ -125,6 +125,7 @@ class RealmConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "realm"
 
     def __init__(

src/transformers/models/reformer/configuration_reformer.py

@@ -158,6 +158,7 @@ class ReformerConfig(PretrainedConfig):
     >>> configuration = model.config
     ```
 """
+
     model_type = "reformer"
     keys_to_ignore_at_inference = ["past_buckets_states"]
     attribute_map = {}

src/transformers/models/regnet/configuration_regnet.py

@@ -66,6 +66,7 @@ class RegNetConfig(PretrainedConfig):
     >>> configuration = model.config
     ```
     """
+
     model_type = "regnet"
     layer_types = ["x", "y"]
 

src/transformers/models/regnet/convert_regnet_to_pytorch.py

@@ -192,7 +192,7 @@ def convert_weight_and_push(
     )
 
     from_output = from_model(x)
-    from_output = from_output[-1] if type(from_output) is list else from_output
+    from_output = from_output[-1] if isinstance(from_output, list) else from_output
 
     # now since I don't want to use any config files, vissl seer model doesn't actually have an head, so let's just check the last hidden state
     if "seer" in name and "in1k" in name:

src/transformers/models/rembert/configuration_rembert.py

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

src/transformers/models/resnet/configuration_resnet.py

@@ -84,6 +84,7 @@ class ResNetConfig(BackboneConfigMixin, PretrainedConfig):
     >>> configuration = model.config
     ```
     """
+
     model_type = "resnet"
     layer_types = ["basic", "bottleneck"]
 

src/transformers/models/roberta/configuration_roberta.py

@@ -101,6 +101,7 @@ class RobertaConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "roberta"
 
     def __init__(