[`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/altclip/modeling_altclip.py

@@ -174,8 +174,7 @@ class AltCLIPOutput(ModelOutput):
         text_embeds(`torch.FloatTensor` of shape `(batch_size, output_dim`):
             The text embeddings obtained by applying the projection layer to the pooled output of [`AltCLIPTextModel`].
         image_embeds(`torch.FloatTensor` of shape `(batch_size, output_dim`):
-            The image embeddings obtained by applying the projection layer to the pooled output of
-            [`AltCLIPVisionModel`].
+            The image embeddings obtained by applying the projection layer to the pooled output of [`AltCLIPVisionModel`].
         text_model_output(`BaseModelOutputWithPooling`):
             The output of the [`AltCLIPTextModel`].
         vision_model_output(`BaseModelOutputWithPooling`):
@@ -1049,9 +1048,7 @@ class AltCLIPPreTrainedModel(PreTrainedModel):
             nn.init.normal_(module.out_proj.weight, std=out_proj_std)
         elif isinstance(module, AltCLIPMLP):
             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/altclip/processing_altclip.py

@@ -35,6 +35,7 @@ class AltCLIPProcessor(ProcessorMixin):
         tokenizer ([`XLMRobertaTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "CLIPImageProcessor"
     tokenizer_class = ("XLMRobertaTokenizer", "XLMRobertaTokenizerFast")

src/transformers/models/audio_spectrogram_transformer/configuration_audio_spectrogram_transformer.py

@@ -86,6 +86,7 @@ class ASTConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "audio-spectrogram-transformer"
 
     def __init__(

src/transformers/models/autoformer/configuration_autoformer.py

@@ -131,6 +131,7 @@ class AutoformerConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "autoformer"
     attribute_map = {
         "hidden_size": "d_model",

src/transformers/models/bark/processing_bark.py

@@ -46,6 +46,7 @@ class BarkProcessor(ProcessorMixin):
             a list of `voice_preset_names`.
 
     """
+
     tokenizer_class = "AutoTokenizer"
     attributes = ["tokenizer"]
 

src/transformers/models/bart/configuration_bart.py

@@ -107,6 +107,7 @@ class BartConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "bart"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/bart/tokenization_bart_fast.py

@@ -147,6 +147,7 @@ class BartTokenizerFast(PreTrainedTokenizerFast):
         trim_offsets (`bool`, *optional*, defaults to `True`):
             Whether the post processing step should trim offsets to avoid including whitespaces.
     """
+
     vocab_files_names = VOCAB_FILES_NAMES
     pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
     max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES

src/transformers/models/beit/configuration_beit.py

@@ -115,6 +115,7 @@ class BeitConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "beit"
 
     def __init__(

src/transformers/models/bert/configuration_bert.py

@@ -136,6 +136,7 @@ class BertConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "bert"
 
     def __init__(

src/transformers/models/bert_generation/configuration_bert_generation.py

@@ -84,6 +84,7 @@ class BertGenerationConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "bert-generation"
 
     def __init__(

src/transformers/models/big_bird/configuration_big_bird.py

@@ -104,6 +104,7 @@ class BigBirdConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "big_bird"
 
     def __init__(

src/transformers/models/big_bird/modeling_big_bird.py

@@ -896,15 +896,11 @@ class BigBirdBlockSparseAttention(nn.Module):
             # global keys (corresponding to 1st key block)
             attention_probs[:, :, 2 * from_block_size : -2 * from_block_size, :to_block_size] = attn_weights[
                 :, :, :, :, :to_block_size
-            ].view(
-                bsz, n_heads, -1, to_block_size
-            )  # first_band_product
+            ].view(bsz, n_heads, -1, to_block_size)  # first_band_product
             # global keys (corresponding to last key block)
             attention_probs[:, :, 2 * from_block_size : -2 * from_block_size, -to_block_size:] = attn_weights[
                 :, :, :, :, -to_block_size:
-            ].view(
-                bsz, n_heads, -1, to_block_size
-            )  # last_band_product
+            ].view(bsz, n_heads, -1, to_block_size)  # last_band_product
             # random keys
             for p1, i1, w1 in zip(range(bsz), rand_attn, attn_weights):
                 # p1, i1, w1 corresponds to batch_dim i.e. following operation is done for each sequence in batch

src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py

@@ -120,6 +120,7 @@ class BigBirdPegasusConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "bigbird_pegasus"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py

@@ -683,15 +683,11 @@ class BigBirdPegasusBlockSparseAttention(nn.Module):
             # global keys (corresponding to 1st key block)
             attention_probs[:, :, 2 * from_block_size : -2 * from_block_size, :to_block_size] = attn_weights[
                 :, :, :, :, :to_block_size
-            ].view(
-                bsz, n_heads, -1, to_block_size
-            )  # first_band_product
+            ].view(bsz, n_heads, -1, to_block_size)  # first_band_product
             # global keys (corresponding to last key block)
             attention_probs[:, :, 2 * from_block_size : -2 * from_block_size, -to_block_size:] = attn_weights[
                 :, :, :, :, -to_block_size:
-            ].view(
-                bsz, n_heads, -1, to_block_size
-            )  # last_band_product
+            ].view(bsz, n_heads, -1, to_block_size)  # last_band_product
             # random keys
             for p1, i1, w1 in zip(range(bsz), rand_attn, attn_weights):
                 # p1, i1, w1 corresponds to batch_dim i.e. following operation is done for each sequence in batch

src/transformers/models/biogpt/configuration_biogpt.py

@@ -93,6 +93,7 @@ class BioGptConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "biogpt"
 
     def __init__(

src/transformers/models/bit/configuration_bit.py

@@ -85,6 +85,7 @@ class BitConfig(BackboneConfigMixin, PretrainedConfig):
     >>> configuration = model.config
     ```
     """
+
     model_type = "bit"
     layer_types = ["preactivation", "bottleneck"]
     supported_padding = ["SAME", "VALID"]

src/transformers/models/blenderbot/configuration_blenderbot.py

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

src/transformers/models/blenderbot/modeling_blenderbot.py

@@ -1511,9 +1511,7 @@ class BlenderbotForCausalLM(BlenderbotPreTrainedModel):
         >>> from transformers import AutoTokenizer, BlenderbotForCausalLM
 
         >>> tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill")
-        >>> model = BlenderbotForCausalLM.from_pretrained(
-        ...     "facebook/blenderbot-400M-distill", add_cross_attention=False
-        ... )
+        >>> model = BlenderbotForCausalLM.from_pretrained("facebook/blenderbot-400M-distill", 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/blenderbot/tokenization_blenderbot.py

@@ -376,8 +376,8 @@ class BlenderbotTokenizer(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. Blenderbot does
-        not make use of token type ids, therefore a list of zeros is returned.
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. Blenderbot does not
+        make use of token type ids, therefore a list of zeros is returned.
 
         Args:
             token_ids_0 (`List[int]`):

src/transformers/models/blenderbot/tokenization_blenderbot_fast.py

@@ -212,8 +212,8 @@ class BlenderbotTokenizerFast(PreTrainedTokenizerFast):
         `str`: Mask token, to use when training a model with masked-language modeling. Log an error if used while not
         having been set.
 
-        Blenderbot tokenizer has a special mask token to be usable in the fill-mask pipeline. The mask token will
-        greedily comprise the space before the *<mask>*.
+        Blenderbot tokenizer has a special mask token to be usable in the fill-mask pipeline. The mask token will greedily
+        comprise the space before the *<mask>*.
         """
         if self._mask_token is None:
             if self.verbose:
@@ -264,8 +264,8 @@ class BlenderbotTokenizerFast(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. Blenderbot does
-        not make use of token type ids, therefore a list of zeros is returned.
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. Blenderbot does not
+        make use of token type ids, therefore a list of zeros is returned.
 
         Args:
             token_ids_0 (`List[int]`):