[`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/roberta_prelayernorm/configuration_roberta_prelayernorm.py

@@ -34,10 +34,9 @@ ROBERTA_PRELAYERNORM_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 # Copied from transformers.models.roberta.configuration_roberta.RobertaConfig with roberta-base->andreasmadsen/efficient_mlm_m0.40,RoBERTa->RoBERTa-PreLayerNorm,Roberta->RobertaPreLayerNorm,roberta->roberta-prelayernorm
 class RobertaPreLayerNormConfig(PretrainedConfig):
     r"""
-    This is the configuration class to store the configuration of a [`RobertaPreLayerNormModel`] or a
-    [`TFRobertaPreLayerNormModel`]. It is used to instantiate a RoBERTa-PreLayerNorm model according to the specified
-    arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar
-    configuration to that of the RoBERTa-PreLayerNorm
+    This is the configuration class to store the configuration of a [`RobertaPreLayerNormModel`] or a [`TFRobertaPreLayerNormModel`]. It is
+    used to instantiate a RoBERTa-PreLayerNorm model according to the specified arguments, defining the model architecture.
+    Instantiating a configuration with the defaults will yield a similar configuration to that of the RoBERTa-PreLayerNorm
     [andreasmadsen/efficient_mlm_m0.40](https://huggingface.co/andreasmadsen/efficient_mlm_m0.40) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
@@ -46,9 +45,8 @@ class RobertaPreLayerNormConfig(PretrainedConfig):
 
     Args:
         vocab_size (`int`, *optional*, defaults to 50265):
-            Vocabulary size of the RoBERTa-PreLayerNorm model. Defines the number of different tokens that can be
-            represented by the `inputs_ids` passed when calling [`RobertaPreLayerNormModel`] or
-            [`TFRobertaPreLayerNormModel`].
+            Vocabulary size of the RoBERTa-PreLayerNorm model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`RobertaPreLayerNormModel`] or [`TFRobertaPreLayerNormModel`].
         hidden_size (`int`, *optional*, defaults to 768):
             Dimensionality of the encoder layers and the pooler layer.
         num_hidden_layers (`int`, *optional*, defaults to 12):
@@ -68,8 +66,7 @@ class RobertaPreLayerNormConfig(PretrainedConfig):
             The maximum sequence length that this model might ever be used with. Typically set this to something large
             just in case (e.g., 512 or 1024 or 2048).
         type_vocab_size (`int`, *optional*, defaults to 2):
-            The vocabulary size of the `token_type_ids` passed when calling [`RobertaPreLayerNormModel`] or
-            [`TFRobertaPreLayerNormModel`].
+            The vocabulary size of the `token_type_ids` passed when calling [`RobertaPreLayerNormModel`] or [`TFRobertaPreLayerNormModel`].
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         layer_norm_eps (`float`, *optional*, defaults to 1e-12):
@@ -102,6 +99,7 @@ class RobertaPreLayerNormConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "roberta-prelayernorm"
 
     def __init__(

src/transformers/models/roc_bert/configuration_roc_bert.py

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

src/transformers/models/roc_bert/modeling_roc_bert.py

@@ -56,9 +56,7 @@ _EXPECTED_OUTPUT_SHAPE = [1, 8, 768]
 
 # Token Classification output
 _CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "ArthurZ/dummy-rocbert-ner"
-# fmt: off
-_TOKEN_CLASS_EXPECTED_OUTPUT = ["S-EVENT", "S-FAC", "I-ORDINAL", "I-ORDINAL", "E-ORG", "E-LANGUAGE", "E-ORG", "E-ORG", "E-ORG", "E-ORG", "I-EVENT", "S-TIME", "S-TIME", "E-LANGUAGE", "S-TIME", "E-DATE", "I-ORDINAL", "E-QUANTITY", "E-LANGUAGE", "S-TIME", "B-ORDINAL", "S-PRODUCT", "E-LANGUAGE", "E-LANGUAGE", "E-ORG", "E-LOC", "S-TIME", "I-ORDINAL", "S-FAC", "O", "S-GPE", "I-EVENT", "S-GPE", "E-LANGUAGE", "E-ORG", "S-EVENT", "S-FAC", "S-FAC", "S-FAC", "E-ORG", "S-FAC", "E-ORG", "S-GPE"]
-# fmt: on
+_TOKEN_CLASS_EXPECTED_OUTPUT = ["S-EVENT", "S-FAC", "I-ORDINAL", "I-ORDINAL", "E-ORG", "E-LANGUAGE", "E-ORG", "E-ORG", "E-ORG", "E-ORG", "I-EVENT", "S-TIME", "S-TIME", "E-LANGUAGE", "S-TIME", "E-DATE", "I-ORDINAL", "E-QUANTITY", "E-LANGUAGE", "S-TIME", "B-ORDINAL", "S-PRODUCT", "E-LANGUAGE", "E-LANGUAGE", "E-ORG", "E-LOC", "S-TIME", "I-ORDINAL", "S-FAC", "O", "S-GPE", "I-EVENT", "S-GPE", "E-LANGUAGE", "E-ORG", "S-EVENT", "S-FAC", "S-FAC", "S-FAC", "E-ORG", "S-FAC", "E-ORG", "S-GPE"]  # fmt: skip
 _TOKEN_CLASS_EXPECTED_LOSS = 3.62
 
 # SequenceClassification docstring

src/transformers/models/roformer/configuration_roformer.py

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

src/transformers/models/roformer/modeling_flax_roformer.py

@@ -49,7 +49,7 @@ FLAX_ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "junnyu/roformer_chinese_char_small",
     "junnyu/roformer_chinese_char_base",
     "junnyu/roformer_small_discriminator",
-    "junnyu/roformer_small_generator"
+    "junnyu/roformer_small_generator",
     # See all RoFormer models at https://huggingface.co/models?filter=roformer
 ]
 

src/transformers/models/roformer/modeling_roformer.py

@@ -58,7 +58,7 @@ ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "junnyu/roformer_chinese_char_small",
     "junnyu/roformer_chinese_char_base",
     "junnyu/roformer_small_discriminator",
-    "junnyu/roformer_small_generator"
+    "junnyu/roformer_small_generator",
     # See all RoFormer models at https://huggingface.co/models?filter=roformer
 ]
 

src/transformers/models/roformer/modeling_tf_roformer.py

@@ -69,7 +69,7 @@ TF_ROFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "junnyu/roformer_chinese_char_small",
     "junnyu/roformer_chinese_char_base",
     "junnyu/roformer_small_discriminator",
-    "junnyu/roformer_small_generator"
+    "junnyu/roformer_small_generator",
     # See all RoFormer models at https://huggingface.co/models?filter=roformer
 ]
 

src/transformers/models/roformer/tokenization_roformer.py

@@ -358,6 +358,7 @@ class RoFormerTokenizer(PreTrainedTokenizer):
     >>> tokenizer.tokenize("今天天气非常好。")
     ['今', '天', '天', '气', '非常', '好', '。']
     ```"""
+
     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/sam/processing_sam.py

@@ -44,6 +44,7 @@ class SamProcessor(ProcessorMixin):
         image_processor (`SamImageProcessor`):
             An instance of [`SamImageProcessor`]. The image processor is a required input.
     """
+
     attributes = ["image_processor"]
     image_processor_class = "SamImageProcessor"
 

src/transformers/models/seamless_m4t/configuration_seamless_m4t.py

@@ -239,6 +239,7 @@ class SeamlessM4TConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "seamless_m4t"
 
     def __init__(

src/transformers/models/seamless_m4t/convert_fairseq2_to_hf.py

@@ -33,23 +33,10 @@ from transformers import (
 from transformers.utils import logging
 
 
-# fmt: off
-UNIT_SUPPORTED_LANGUAGES = ["__arb__", "__ben__", "__cat__", "__ces__", "__cmn__", "__cym__", "__dan__", "__deu__", "__eng__", "__est__", "__fin__", "__fra__", "__hin__", "__ind__", "__ita__", "__jpn__", "__kan__", "__kor__", "__mlt__", "__nld__", "__pes__", "__pol__", "__por__", "__ron__", "__rus__", "__slk__", "__spa__", "__swe__", "__swh__", "__tam__", "__tel__", "__tgl__", "__tha__", "__tur__", "__ukr__", "__urd__", "__uzn__", "__vie__", ]
-# fmt: on
-
-# fmt: off
-VOCODER_SUPPORTED_LANGUAGES = ["__arb__", "__ben__", "__cat__", "__ces__", "__cmn__", "__cym__", "__dan__", "__deu__", "__eng__", "__est__", "__fin__", "__fra__", "__hin__", "__ind__", "__ita__", "__jpn__", "__kor__", "__mlt__", "__nld__", "__pes__", "__pol__", "__por__", "__ron__", "__rus__", "__slk__", "__spa__", "__swe__", "__swh__", "__tel__", "__tgl__", "__tha__", "__tur__", "__ukr__", "__urd__", "__uzn__", "__vie__",]
-# fmt: on
-
-
-# fmt: off
-MEDIUM_SUPPORTED_LANGUAGES = ["ace","ace_Latn","acm","acq","aeb","afr","ajp","aka","amh","apc","arb","ars","ary","arz","asm","ast","awa","ayr","azb","azj","bak","bam","ban","bel","bem","ben","bho","bjn","bjn_Latn","bod","bos","bug","bul","cat","ceb","ces","cjk","ckb","crh","cym","dan","deu","dik","dyu","dzo","ell","eng","epo","est","eus","ewe","fao","pes","fij","fin","fon","fra","fur","fuv","gla","gle","glg","grn","guj","hat","hau","heb","hin","hne","hrv","hun","hye","ibo","ilo","ind","isl","ita","jav","jpn","kab","kac","kam","kan","kas","kas_Deva","kat","knc","knc_Latn","kaz","kbp","kea","khm","kik","kin","kir","kmb","kon","kor","kmr","lao","lvs","lij","lim","lin","lit","lmo","ltg","ltz","lua","lug","luo","lus","mag","mai","mal","mar","min","mkd","plt","mlt","mni","khk","mos","mri","zsm","mya","nld","nno","nob","npi","nso","nus","nya","oci","gaz","ory","pag","pan","pap","pol","por","prs","pbt","quy","ron","run","rus","sag","san","sat","scn","shn","sin","slk","slv","smo","sna","snd","som","sot","spa","als","srd","srp","ssw","sun","swe","swh","szl","tam","tat","tel","tgk","tgl","tha","tir","taq","taq_Tfng","tpi","tsn","tso","tuk","tum","tur","twi","tzm","uig","ukr","umb","urd","uzn","vec","vie","war","wol","xho","ydd","yor","yue","cmn","cmn_Hant","zul",]
-# fmt: on
-
-
-# fmt: off
-LARGE_SUPPORTED_LANGUAGES = ["afr","amh","arb","ary","arz","asm","azj","bel","ben","bos","bul","cat","ceb","ces","ckb","cmn","cmn_Hant","cym","dan","deu","ell","eng","est","eus","fin","fra","fuv","gaz","gle","glg","guj","heb","hin","hrv","hun","hye","ibo","ind","isl","ita","jav","jpn","kan","kat","kaz","khk","khm","kir","kor","lao","lit","lug","luo","lvs","mai","mal","mar","mkd","mlt","mni","mya","nld","nno","nob","npi","nya","ory","pan","pbt","pes","pol","por","ron","rus","sat","slk","slv","sna","snd","som","spa","srp","swe","swh","tam","tel","tgk","tgl","tha","tur","ukr","urd","uzn","vie","yor","yue","zlm","zul",]
-# fmt: on
+UNIT_SUPPORTED_LANGUAGES = ["__arb__", "__ben__", "__cat__", "__ces__", "__cmn__", "__cym__", "__dan__", "__deu__", "__eng__", "__est__", "__fin__", "__fra__", "__hin__", "__ind__", "__ita__", "__jpn__", "__kan__", "__kor__", "__mlt__", "__nld__", "__pes__", "__pol__", "__por__", "__ron__", "__rus__", "__slk__", "__spa__", "__swe__", "__swh__", "__tam__", "__tel__", "__tgl__", "__tha__", "__tur__", "__ukr__", "__urd__", "__uzn__", "__vie__", ]  # fmt: skip
+VOCODER_SUPPORTED_LANGUAGES = ["__arb__", "__ben__", "__cat__", "__ces__", "__cmn__", "__cym__", "__dan__", "__deu__", "__eng__", "__est__", "__fin__", "__fra__", "__hin__", "__ind__", "__ita__", "__jpn__", "__kor__", "__mlt__", "__nld__", "__pes__", "__pol__", "__por__", "__ron__", "__rus__", "__slk__", "__spa__", "__swe__", "__swh__", "__tel__", "__tgl__", "__tha__", "__tur__", "__ukr__", "__urd__", "__uzn__", "__vie__",]  # fmt: skip
+MEDIUM_SUPPORTED_LANGUAGES = ["ace","ace_Latn","acm","acq","aeb","afr","ajp","aka","amh","apc","arb","ars","ary","arz","asm","ast","awa","ayr","azb","azj","bak","bam","ban","bel","bem","ben","bho","bjn","bjn_Latn","bod","bos","bug","bul","cat","ceb","ces","cjk","ckb","crh","cym","dan","deu","dik","dyu","dzo","ell","eng","epo","est","eus","ewe","fao","pes","fij","fin","fon","fra","fur","fuv","gla","gle","glg","grn","guj","hat","hau","heb","hin","hne","hrv","hun","hye","ibo","ilo","ind","isl","ita","jav","jpn","kab","kac","kam","kan","kas","kas_Deva","kat","knc","knc_Latn","kaz","kbp","kea","khm","kik","kin","kir","kmb","kon","kor","kmr","lao","lvs","lij","lim","lin","lit","lmo","ltg","ltz","lua","lug","luo","lus","mag","mai","mal","mar","min","mkd","plt","mlt","mni","khk","mos","mri","zsm","mya","nld","nno","nob","npi","nso","nus","nya","oci","gaz","ory","pag","pan","pap","pol","por","prs","pbt","quy","ron","run","rus","sag","san","sat","scn","shn","sin","slk","slv","smo","sna","snd","som","sot","spa","als","srd","srp","ssw","sun","swe","swh","szl","tam","tat","tel","tgk","tgl","tha","tir","taq","taq_Tfng","tpi","tsn","tso","tuk","tum","tur","twi","tzm","uig","ukr","umb","urd","uzn","vec","vie","war","wol","xho","ydd","yor","yue","cmn","cmn_Hant","zul",]  # fmt: skip
+LARGE_SUPPORTED_LANGUAGES = ["afr","amh","arb","ary","arz","asm","azj","bel","ben","bos","bul","cat","ceb","ces","ckb","cmn","cmn_Hant","cym","dan","deu","ell","eng","est","eus","fin","fra","fuv","gaz","gle","glg","guj","heb","hin","hrv","hun","hye","ibo","ind","isl","ita","jav","jpn","kan","kat","kaz","khk","khm","kir","kor","lao","lit","lug","luo","lvs","mai","mal","mar","mkd","mlt","mni","mya","nld","nno","nob","npi","nya","ory","pan","pbt","pes","pol","por","ron","rus","sat","slk","slv","sna","snd","som","spa","srp","swe","swh","tam","tel","tgk","tgl","tha","tur","ukr","urd","uzn","vie","yor","yue","zlm","zul",]  # fmt: skip
 
 
 def assert_param_count(model_1, model_2):

src/transformers/models/seamless_m4t/processing_seamless_m4t.py

@@ -34,6 +34,7 @@ class SeamlessM4TProcessor(ProcessorMixin):
         tokenizer ([`SeamlessM4TTokenizerFast`]):
             The tokenizer is a required input.
     """
+
     feature_extractor_class = "SeamlessM4TFeatureExtractor"
     tokenizer_class = ("SeamlessM4TTokenizer", "SeamlessM4TTokenizerFast")
 

src/transformers/models/segformer/configuration_segformer.py

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

src/transformers/models/segformer/image_processing_segformer.py

@@ -440,8 +440,7 @@ class SegformerImageProcessor(BaseImageProcessor):
     # Copied from transformers.models.beit.image_processing_beit.BeitImageProcessor.post_process_semantic_segmentation with Beit->Segformer
     def post_process_semantic_segmentation(self, outputs, target_sizes: List[Tuple] = None):
         """
-        Converts the output of [`SegformerForSemanticSegmentation`] into semantic segmentation maps. Only supports
-        PyTorch.
+        Converts the output of [`SegformerForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch.
 
         Args:
             outputs ([`SegformerForSemanticSegmentation`]):

src/transformers/models/sew/configuration_sew.py

@@ -154,6 +154,7 @@ class SEWConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "sew"
 
     def __init__(

src/transformers/models/sew_d/configuration_sew_d.py

@@ -169,6 +169,7 @@ class SEWDConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "sew-d"
 
     def __init__(

src/transformers/models/sew_d/modeling_sew_d.py

@@ -847,15 +847,11 @@ 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/speech_encoder_decoder/configuration_speech_encoder_decoder.py

@@ -69,6 +69,7 @@ class SpeechEncoderDecoderConfig(PretrainedConfig):
     >>> encoder_decoder_config = SpeechEncoderDecoderConfig.from_pretrained("my-model")
     >>> model = SpeechEncoderDecoderModel.from_pretrained("my-model", config=encoder_decoder_config)
     ```"""
+
     model_type = "speech-encoder-decoder"
     is_composition = True
 

src/transformers/models/speech_encoder_decoder/modeling_speech_encoder_decoder.py

@@ -177,6 +177,7 @@ class SpeechEncoderDecoderModel(PreTrainedModel):
     :meth*~transformers.AutoModel.from_pretrained* class method for the encoder and
     :meth*~transformers.AutoModelForCausalLM.from_pretrained* class method for the decoder.
     """
+
     config_class = SpeechEncoderDecoderConfig
     base_model_prefix = "speech_encoder_decoder"
     main_input_name = "inputs"

src/transformers/models/speech_to_text/configuration_speech_to_text.py

@@ -121,6 +121,7 @@ class Speech2TextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "speech_to_text"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}