[`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/markuplm/feature_extraction_markuplm.py

@@ -67,7 +67,7 @@ class MarkupLMFeatureExtractor(FeatureExtractionMixin):
         string2xsubs_seq = []
 
         for element in html_code.descendants:
-            if type(element) == bs4.element.NavigableString:
+            if isinstance(element, bs4.element.NavigableString):
                 if type(element.parent) != bs4.element.Tag:
                     continue
 

src/transformers/models/markuplm/processing_markuplm.py

@@ -41,6 +41,7 @@ class MarkupLMProcessor(ProcessorMixin):
         parse_html (`bool`, *optional*, defaults to `True`):
             Whether or not to use `MarkupLMFeatureExtractor` to parse HTML strings into nodes and corresponding xpaths.
     """
+
     feature_extractor_class = "MarkupLMFeatureExtractor"
     tokenizer_class = ("MarkupLMTokenizer", "MarkupLMTokenizerFast")
     parse_html = True

src/transformers/models/mask2former/configuration_mask2former.py

@@ -119,6 +119,7 @@ class Mask2FormerConfig(PretrainedConfig):
     ```
 
     """
+
     model_type = "mask2former"
     backbones_supported = ["swin"]
     attribute_map = {"hidden_size": "hidden_dim"}

src/transformers/models/mask2former/modeling_mask2former.py

@@ -2537,5 +2537,5 @@ class Mask2FormerForUniversalSegmentation(Mask2FormerPreTrainedModel):
         if not return_dict:
             output = tuple(v for v in output.values() if v is not None)
             if loss is not None:
-                output = ((loss)) + output
+                output = (loss) + output
         return output

src/transformers/models/maskformer/configuration_maskformer.py

@@ -94,6 +94,7 @@ class MaskFormerConfig(PretrainedConfig):
     ```
 
     """
+
     model_type = "maskformer"
     attribute_map = {"hidden_size": "mask_feature_size"}
     backbones_supported = ["resnet", "swin"]

src/transformers/models/maskformer/configuration_maskformer_swin.py

@@ -90,6 +90,7 @@ class MaskFormerSwinConfig(BackboneConfigMixin, PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "maskformer-swin"
 
     attribute_map = {

src/transformers/models/mbart/configuration_mbart.py

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

src/transformers/models/mbart/tokenization_mbart.py

@@ -45,9 +45,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     "facebook/mbart-large-cc25": 1024,
 }
 
-# fmt: off
-FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]
-# fmt: on
+FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]  # fmt: skip
 
 
 class MBartTokenizer(PreTrainedTokenizer):

src/transformers/models/mbart/tokenization_mbart_fast.py

@@ -55,9 +55,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     "facebook/mbart-large-cc25": 1024,
 }
 
-# fmt: off
-FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]
-# fmt: on
+FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]  # fmt: skip
 
 
 class MBartTokenizerFast(PreTrainedTokenizerFast):

src/transformers/models/mbart50/tokenization_mbart50.py

@@ -41,9 +41,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     "facebook/mbart-large-50-one-to-many-mmt": 1024,
 }
 
-# fmt: off
-FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]
-# fmt: on
+FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]  # fmt: skip
 
 
 class MBart50Tokenizer(PreTrainedTokenizer):

src/transformers/models/mbart50/tokenization_mbart50_fast.py

@@ -51,9 +51,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     "facebook/mbart-large-50-one-to-many-mmt": 1024,
 }
 
-# fmt: off
-FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]
-# fmt: on
+FAIRSEQ_LANGUAGE_CODES = ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]  # fmt: skip
 
 
 class MBart50TokenizerFast(PreTrainedTokenizerFast):

src/transformers/models/mega/configuration_mega.py

@@ -145,6 +145,7 @@ class MegaConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mega"
 
     def __init__(

src/transformers/models/mega/modeling_mega.py

@@ -539,9 +539,7 @@ class MegaGatedCrossAttention(nn.Module):
         self.config = config
         self.activation = ACT2FN[self.config.activation]
         self.attention_activation = self.config.attention_activation
-        self.scaling = (
-            self.config.shared_representation_size**-0.5 if self.attention_activation == "softmax" else None
-        )
+        self.scaling = self.config.shared_representation_size**-0.5 if self.attention_activation == "softmax" else None
 
         self.dropout = MegaDropout(self.config.dropout_prob, is_featurewise=self.config.use_feature_dropout)
         self.hidden_dropout = MegaDropout(

src/transformers/models/megatron_bert/configuration_megatron_bert.py

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

src/transformers/models/mgp_str/configuration_mgp_str.py

@@ -89,6 +89,7 @@ class MgpstrConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mgp-str"
 
     def __init__(

src/transformers/models/mgp_str/processing_mgp_str.py

@@ -49,6 +49,7 @@ class MgpstrProcessor(ProcessorMixin):
         tokenizer ([`MgpstrTokenizer`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "char_tokenizer"]
     image_processor_class = "ViTImageProcessor"
     char_tokenizer_class = "MgpstrTokenizer"

src/transformers/models/mobilebert/configuration_mobilebert.py

@@ -108,6 +108,7 @@ class MobileBertConfig(PretrainedConfig):
     Attributes: pretrained_config_archive_map (Dict[str, str]): A dictionary containing all the available pre-trained
     checkpoints.
     """
+
     pretrained_config_archive_map = MOBILEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
     model_type = "mobilebert"
 

src/transformers/models/mobilebert/tokenization_mobilebert.py

@@ -252,8 +252,8 @@ class MobileBertTokenizer(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 MobileBERT
-        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 MobileBERT 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/mobilebert/tokenization_mobilebert_fast.py

@@ -159,8 +159,8 @@ class MobileBertTokenizerFast(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 MobileBERT
-        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 MobileBERT 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/mobilenet_v1/configuration_mobilenet_v1.py

@@ -78,6 +78,7 @@ class MobileNetV1Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mobilenet_v1"
 
     def __init__(