[`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/blenderbot_small/configuration_blenderbot_small.py

@@ -104,6 +104,7 @@ class BlenderbotSmallConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "blenderbot-small"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/blenderbot_small/modeling_blenderbot_small.py

@@ -1478,9 +1478,7 @@ class BlenderbotSmallForCausalLM(BlenderbotSmallPreTrainedModel):
         >>> from transformers import AutoTokenizer, BlenderbotSmallForCausalLM
 
         >>> tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot_small-90M")
-        >>> model = BlenderbotSmallForCausalLM.from_pretrained(
-        ...     "facebook/blenderbot_small-90M", add_cross_attention=False
-        ... )
+        >>> model = BlenderbotSmallForCausalLM.from_pretrained("facebook/blenderbot_small-90M", add_cross_attention=False)
         >>> assert model.config.is_decoder, f"{model.__class__} has to be configured as a decoder."
         >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
         >>> outputs = model(**inputs)

src/transformers/models/blip/configuration_blip.py

@@ -109,6 +109,7 @@ class BlipTextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "blip_text_model"
 
     def __init__(

src/transformers/models/blip/modeling_blip_text.py

@@ -742,13 +742,13 @@ class BlipTextModel(BlipTextPreTrainedModel):
         # If a 2D or 3D attention mask is provided for the cross-attention
         # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
         if encoder_hidden_states is not None:
-            if type(encoder_hidden_states) == list:
+            if isinstance(encoder_hidden_states, list):
                 encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states[0].size()
             else:
                 encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
             encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
 
-            if type(encoder_attention_mask) == list:
+            if isinstance(encoder_attention_mask, list):
                 encoder_extended_attention_mask = [self.invert_attention_mask(mask) for mask in encoder_attention_mask]
             elif encoder_attention_mask is None:
                 encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)

src/transformers/models/blip/modeling_tf_blip_text.py

@@ -741,13 +741,13 @@ class TFBlipTextModel(TFBlipTextPreTrainedModel):
         # If a 2D or 3D attention mask is provided for the cross-attention
         # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
         if encoder_hidden_states is not None:
-            if type(encoder_hidden_states) == list:
+            if isinstance(encoder_hidden_states, list):
                 encoder_batch_size, encoder_sequence_length, _ = shape_list(encoder_hidden_states[0])
             else:
                 encoder_batch_size, encoder_sequence_length, _ = shape_list(encoder_hidden_states)
             encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
 
-            if type(encoder_attention_mask) == list:
+            if isinstance(encoder_attention_mask, list):
                 encoder_extended_attention_mask = [invert_attention_mask(mask) for mask in encoder_attention_mask]
             elif encoder_attention_mask is None:
                 encoder_attention_mask = tf.ones(encoder_hidden_shape)

src/transformers/models/blip/processing_blip.py

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

src/transformers/models/blip_2/configuration_blip_2.py

@@ -190,6 +190,7 @@ class Blip2QFormerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "blip_2_qformer"
 
     def __init__(

src/transformers/models/blip_2/modeling_blip_2.py

@@ -1123,13 +1123,13 @@ class Blip2QFormerModel(Blip2PreTrainedModel):
         # If a 2D or 3D attention mask is provided for the cross-attention
         # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
         if encoder_hidden_states is not None:
-            if type(encoder_hidden_states) == list:
+            if isinstance(encoder_hidden_states, list):
                 encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states[0].size()
             else:
                 encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
             encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
 
-            if type(encoder_attention_mask) == list:
+            if isinstance(encoder_attention_mask, list):
                 encoder_extended_attention_mask = [self.invert_attention_mask(mask) for mask in encoder_attention_mask]
             elif encoder_attention_mask is None:
                 encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)

src/transformers/models/blip_2/processing_blip_2.py

@@ -37,6 +37,7 @@ class Blip2Processor(ProcessorMixin):
         tokenizer (`AutoTokenizer`):
             An instance of ['PreTrainedTokenizer`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "BlipImageProcessor"
     tokenizer_class = "AutoTokenizer"
@@ -141,8 +142,8 @@ class Blip2Processor(ProcessorMixin):
     # Copied from transformers.models.blip.processing_blip.BlipProcessor.decode with BertTokenizerFast->PreTrainedTokenizer
     def decode(self, *args, **kwargs):
         """
-        This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer
-        to the docstring of this method for more information.
+        This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to
+        the docstring of this method for more information.
         """
         return self.tokenizer.decode(*args, **kwargs)
 

src/transformers/models/bridgetower/configuration_bridgetower.py

@@ -73,6 +73,7 @@ class BridgeTowerVisionConfig(PretrainedConfig):
     >>> # Accessing the configuration
     >>> configuration
     ```"""
+
     model_type = "bridgetower_vision_model"
 
     def __init__(
@@ -179,6 +180,7 @@ class BridgeTowerTextConfig(PretrainedConfig):
     >>> # Accessing the configuration
     >>> configuration
     ```"""
+
     model_type = "bridgetower_text_model"
 
     def __init__(
@@ -291,6 +293,7 @@ class BridgeTowerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "bridgetower"
 
     def __init__(

src/transformers/models/bridgetower/modeling_bridgetower.py

@@ -46,7 +46,7 @@ _TOKENIZER_FOR_DOC = "RobertaTokenizer"
 
 BRIDGETOWER_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "BridgeTower/bridgetower-base",
-    "BridgeTower/bridgetower-base-itm-mlm"
+    "BridgeTower/bridgetower-base-itm-mlm",
     # See all bridgetower models at https://huggingface.co/BridgeTower
 ]
 

src/transformers/models/bridgetower/processing_bridgetower.py

@@ -38,6 +38,7 @@ class BridgeTowerProcessor(ProcessorMixin):
         tokenizer (`RobertaTokenizerFast`):
             An instance of ['RobertaTokenizerFast`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "BridgeTowerImageProcessor"
     tokenizer_class = ("RobertaTokenizer", "RobertaTokenizerFast")

src/transformers/models/bros/configuration_bros.py

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

src/transformers/models/bros/processing_bros.py

@@ -34,6 +34,7 @@ class BrosProcessor(ProcessorMixin):
         tokenizer (`BertTokenizerFast`, *optional*):
             An instance of ['BertTokenizerFast`]. The tokenizer is a required input.
     """
+
     attributes = ["tokenizer"]
     tokenizer_class = ("BertTokenizer", "BertTokenizerFast")
 

src/transformers/models/canine/configuration_canine.py

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

src/transformers/models/canine/modeling_canine.py

@@ -54,7 +54,7 @@ _CONFIG_FOR_DOC = "CanineConfig"
 
 CANINE_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "google/canine-s",
-    "google/canine-r"
+    "google/canine-r",
     # See all CANINE models at https://huggingface.co/models?filter=canine
 ]
 

src/transformers/models/chinese_clip/configuration_chinese_clip.py

@@ -106,6 +106,7 @@ class ChineseCLIPTextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "chinese_clip_text_model"
 
     def __init__(

src/transformers/models/chinese_clip/modeling_chinese_clip.py

@@ -718,9 +718,7 @@ class ChineseCLIPPreTrainedModel(PreTrainedModel):
             nn.init.normal_(module.out_proj.weight, std=out_proj_std)
         elif isinstance(module, ChineseCLIPVisionMLP):
             factor = self.config.initializer_factor
-            in_proj_std = (
-                (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
-            )
+            in_proj_std = (module.config.hidden_size**-0.5) * ((2 * module.config.num_hidden_layers) ** -0.5) * factor
             fc_std = (2 * module.config.hidden_size) ** -0.5 * factor
             nn.init.normal_(module.fc1.weight, std=fc_std)
             nn.init.normal_(module.fc2.weight, std=in_proj_std)

src/transformers/models/chinese_clip/processing_chinese_clip.py

@@ -36,6 +36,7 @@ class ChineseCLIPProcessor(ProcessorMixin):
         tokenizer ([`BertTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "ChineseCLIPImageProcessor"
     tokenizer_class = ("BertTokenizer", "BertTokenizerFast")

src/transformers/models/clap/configuration_clap.py

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