[`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/distilbert/configuration_distilbert.py

@@ -98,6 +98,7 @@ class DistilBertConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "distilbert"
     attribute_map = {
         "hidden_size": "dim",

src/transformers/models/donut/configuration_donut_swin.py

@@ -85,6 +85,7 @@ class DonutSwinConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "donut-swin"
 
     attribute_map = {

src/transformers/models/donut/processing_donut.py

@@ -37,6 +37,7 @@ class DonutProcessor(ProcessorMixin):
         tokenizer ([`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`], *optional*):
             An instance of [`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`]. The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "AutoImageProcessor"
     tokenizer_class = "AutoTokenizer"

src/transformers/models/dpr/configuration_dpr.py

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

src/transformers/models/dpt/configuration_dpt.py

@@ -126,6 +126,7 @@ class DPTConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "dpt"
 
     def __init__(

src/transformers/models/efficientnet/configuration_efficientnet.py

@@ -100,6 +100,7 @@ class EfficientNetConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "efficientnet"
 
     def __init__(

src/transformers/models/electra/configuration_electra.py

@@ -130,6 +130,7 @@ class ElectraConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "electra"
 
     def __init__(

src/transformers/models/electra/modeling_flax_electra.py

@@ -1196,6 +1196,7 @@ class FlaxElectraSequenceSummary(nn.Module):
             - **summary_first_dropout** (`float`) -- Optional dropout probability before the projection and activation.
             - **summary_last_dropout** (`float`)-- Optional dropout probability after the projection and activation.
     """
+
     config: ElectraConfig
     dtype: jnp.dtype = jnp.float32
 

src/transformers/models/electra/tokenization_electra.py

@@ -280,8 +280,8 @@ class ElectraTokenizer(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. A Electra
-        sequence pair mask has the following format:
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A Electra sequence
+        pair mask has the following format:
 
         ```
         0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1

src/transformers/models/electra/tokenization_electra_fast.py

@@ -201,8 +201,8 @@ class ElectraTokenizerFast(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. A ELECTRA
-        sequence pair mask has the following format:
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A ELECTRA sequence
+        pair mask has the following format:
 
         ```
         0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1

src/transformers/models/encodec/configuration_encodec.py

@@ -108,6 +108,7 @@ class EncodecConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "encodec"
 
     def __init__(

src/transformers/models/encoder_decoder/configuration_encoder_decoder.py

@@ -68,6 +68,7 @@ class EncoderDecoderConfig(PretrainedConfig):
     >>> encoder_decoder_config = EncoderDecoderConfig.from_pretrained("my-model")
     >>> model = EncoderDecoderModel.from_pretrained("my-model", config=encoder_decoder_config)
     ```"""
+
     model_type = "encoder-decoder"
     is_composition = True
 

src/transformers/models/encoder_decoder/modeling_encoder_decoder.py

@@ -174,6 +174,7 @@ class EncoderDecoderModel(PreTrainedModel):
     :meth*~transformers.AutoModel.from_pretrained* class method for the encoder and
     :meth*~transformers.AutoModelForCausalLM.from_pretrained* class method for the decoder.
     """
+
     config_class = EncoderDecoderConfig
     base_model_prefix = "encoder_decoder"
     main_input_name = "input_ids"

src/transformers/models/encoder_decoder/modeling_flax_encoder_decoder.py

@@ -306,6 +306,7 @@ class FlaxEncoderDecoderModel(FlaxPreTrainedModel):
     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 = EncoderDecoderConfig
     base_model_prefix = "encoder_decoder"
     module_class = FlaxEncoderDecoderModule

src/transformers/models/encoder_decoder/modeling_tf_encoder_decoder.py

@@ -197,6 +197,7 @@ class TFEncoderDecoderModel(TFPreTrainedModel, TFCausalLanguageModelingLoss):
     [`~TFAutoModel.from_pretrained`] class method for the encoder and [`~TFAutoModelForCausalLM.from_pretrained`] class
     method for the decoder.
     """
+
     config_class = EncoderDecoderConfig
     base_model_prefix = "encoder_decoder"
     load_weight_prefix = "tf_encoder_decoder_model"

src/transformers/models/ernie/configuration_ernie.py

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

src/transformers/models/ernie_m/configuration_ernie_m.py

@@ -78,6 +78,7 @@ class ErnieMConfig(PretrainedConfig):
     A normal_initializer initializes weight matrices as normal distributions. See
     `ErnieMPretrainedModel._init_weights()` for how weights are initialized in `ErnieMModel`.
     """
+
     model_type = "ernie_m"
     attribute_map: Dict[str, str] = {"dropout": "classifier_dropout", "num_classes": "num_labels"}
 

src/transformers/models/esm/configuration_esm.py

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

src/transformers/models/esm/modeling_esmfold.py

@@ -229,7 +229,7 @@ def dict_multimap(fn, dicts):
     new_dict = {}
     for k, v in first.items():
         all_v = [d[k] for d in dicts]
-        if type(v) is dict:
+        if isinstance(v, dict):
             new_dict[k] = dict_multimap(fn, all_v)
         else:
             new_dict[k] = fn(all_v)
@@ -1060,7 +1060,7 @@ class EsmFoldDropout(nn.Module):
         super().__init__()
 
         self.r = r
-        if type(batch_dim) == int:
+        if isinstance(batch_dim, int):
             batch_dim = [batch_dim]
         self.batch_dim = batch_dim
         self.dropout = nn.Dropout(self.r)
@@ -2254,7 +2254,7 @@ class EsmForProteinFolding(EsmPreTrainedModel):
         seqs: Union[str, List[str]],
         position_ids=None,
     ):
-        if type(seqs) is str:
+        if isinstance(seqs, str):
             lst = [seqs]
         else:
             lst = seqs
@@ -2312,7 +2312,7 @@ class EsmForProteinFolding(EsmPreTrainedModel):
 
     def infer_pdb(self, seqs, *args, **kwargs) -> str:
         """Returns the pdb (file) string from the model given an input sequence."""
-        assert type(seqs) is str
+        assert isinstance(seqs, str)
         output = self.infer(seqs, *args, **kwargs)
         return self.output_to_pdb(output)[0]
 

src/transformers/models/falcon/configuration_falcon.py

@@ -104,6 +104,7 @@ class FalconConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "falcon"
     keys_to_ignore_at_inference = ["past_key_values"]