[`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/data2vec/configuration_data2vec_audio.py

@@ -168,6 +168,7 @@ class Data2VecAudioConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "data2vec-audio"
 
     def __init__(

src/transformers/models/data2vec/configuration_data2vec_text.py

@@ -95,6 +95,7 @@ class Data2VecTextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "data2vec-text"
 
     def __init__(

src/transformers/models/data2vec/configuration_data2vec_vision.py

@@ -111,6 +111,7 @@ class Data2VecVisionConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "data2vec-vision"
 
     def __init__(

src/transformers/models/data2vec/modeling_data2vec_vision.py

@@ -289,8 +289,8 @@ class Data2VecVisionSelfAttention(nn.Module):
 # Copied from transformers.models.beit.modeling_beit.BeitSelfOutput with Beit->Data2VecVision
 class Data2VecVisionSelfOutput(nn.Module):
     """
-    The residual connection is defined in Data2VecVisionLayer instead of here (as is the case with other models), due
-    to the layernorm applied before each block.
+    The residual connection is defined in Data2VecVisionLayer instead of here (as is the case with other models), due to the
+    layernorm applied before each block.
     """
 
     def __init__(self, config: Data2VecVisionConfig) -> None:

src/transformers/models/deberta/configuration_deberta.py

@@ -105,6 +105,7 @@ class DebertaConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "deberta"
 
     def __init__(
@@ -148,7 +149,7 @@ class DebertaConfig(PretrainedConfig):
         self.position_biased_input = position_biased_input
 
         # Backwards compatibility
-        if type(pos_att_type) == str:
+        if isinstance(pos_att_type, str):
             pos_att_type = [x.strip() for x in pos_att_type.lower().split("|")]
 
         self.pos_att_type = pos_att_type

src/transformers/models/deberta_v2/configuration_deberta_v2.py

@@ -107,6 +107,7 @@ class DebertaV2Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "deberta-v2"
 
     def __init__(
@@ -150,7 +151,7 @@ class DebertaV2Config(PretrainedConfig):
         self.position_biased_input = position_biased_input
 
         # Backwards compatibility
-        if type(pos_att_type) == str:
+        if isinstance(pos_att_type, str):
             pos_att_type = [x.strip() for x in pos_att_type.lower().split("|")]
 
         self.pos_att_type = pos_att_type

src/transformers/models/deberta_v2/modeling_deberta_v2.py

@@ -780,15 +780,11 @@ class DisentangledSelfAttention(nn.Module):
             if "c2p" in self.pos_att_type:
                 pos_key_layer = self.transpose_for_scores(
                     self.pos_key_proj(rel_embeddings), self.num_attention_heads
-                ).repeat(
-                    query_layer.size(0) // self.num_attention_heads, 1, 1
-                )  # .split(self.all_head_size, dim=-1)
+                ).repeat(query_layer.size(0) // self.num_attention_heads, 1, 1)  # .split(self.all_head_size, dim=-1)
             if "p2c" in self.pos_att_type:
                 pos_query_layer = self.transpose_for_scores(
                     self.pos_query_proj(rel_embeddings), self.num_attention_heads
-                ).repeat(
-                    query_layer.size(0) // self.num_attention_heads, 1, 1
-                )  # .split(self.all_head_size, dim=-1)
+                ).repeat(query_layer.size(0) // self.num_attention_heads, 1, 1)  # .split(self.all_head_size, dim=-1)
 
         score = 0
         # content->position

src/transformers/models/deformable_detr/configuration_deformable_detr.py

@@ -143,6 +143,7 @@ class DeformableDetrConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "deformable_detr"
     attribute_map = {
         "hidden_size": "d_model",

src/transformers/models/deit/configuration_deit.py

@@ -91,6 +91,7 @@ class DeiTConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "deit"
 
     def __init__(

src/transformers/models/deprecated/mctct/configuration_mctct.py

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

src/transformers/models/deprecated/mctct/processing_mctct.py

@@ -34,6 +34,7 @@ class MCTCTProcessor(ProcessorMixin):
         tokenizer (`AutoTokenizer`):
             An instance of [`AutoTokenizer`]. The tokenizer is a required input.
     """
+
     feature_extractor_class = "MCTCTFeatureExtractor"
     tokenizer_class = "AutoTokenizer"
 

src/transformers/models/deprecated/open_llama/configuration_open_llama.py

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

src/transformers/models/deprecated/retribert/configuration_retribert.py

@@ -72,6 +72,7 @@ class RetriBertConfig(PretrainedConfig):
         projection_dim (`int`, *optional*, defaults to 128):
             Final dimension of the query and document representation after projection
     """
+
     model_type = "retribert"
 
     def __init__(

src/transformers/models/deprecated/trajectory_transformer/configuration_trajectory_transformer.py

@@ -100,6 +100,7 @@ class TrajectoryTransformerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "trajectory_transformer"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/deprecated/van/configuration_van.py

@@ -77,6 +77,7 @@ class VanConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "van"
 
     def __init__(

src/transformers/models/deta/configuration_deta.py

@@ -124,6 +124,7 @@ class DetaConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "deta"
     attribute_map = {
         "hidden_size": "d_model",

src/transformers/models/deta/modeling_deta.py

@@ -70,8 +70,8 @@ DETA_PRETRAINED_MODEL_ARCHIVE_LIST = [
 # Copied from transformers.models.deformable_detr.modeling_deformable_detr.DeformableDetrDecoderOutput with DeformableDetr->Deta
 class DetaDecoderOutput(ModelOutput):
     """
-    Base class for outputs of the DetaDecoder. This class adds two attributes to BaseModelOutputWithCrossAttentions,
-    namely:
+    Base class for outputs of the DetaDecoder. This class adds two attributes to
+    BaseModelOutputWithCrossAttentions, namely:
     - a stacked tensor of intermediate decoder hidden states (i.e. the output of each decoder layer)
     - a stacked tensor of intermediate reference points.
 

src/transformers/models/detr/configuration_detr.py

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

src/transformers/models/dinat/configuration_dinat.py

@@ -94,6 +94,7 @@ class DinatConfig(BackboneConfigMixin, PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "dinat"
 
     attribute_map = {

src/transformers/models/dinov2/configuration_dinov2.py

@@ -105,6 +105,7 @@ class Dinov2Config(BackboneConfigMixin, PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "dinov2"
 
     def __init__(