[`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/flaubert/modeling_tf_flaubert.py

@@ -518,9 +518,10 @@ class TFFlaubertMainLayer(tf.keras.layers.Layer):
 
         # check inputs
         # assert shape_list(lengths)[0] == bs
-        tf.debugging.assert_equal(
-            shape_list(lengths)[0], bs
-        ), f"Expected batch size {shape_list(lengths)[0]} and received batch size {bs} mismatched"
+        (
+            tf.debugging.assert_equal(shape_list(lengths)[0], bs),
+            f"Expected batch size {shape_list(lengths)[0]} and received batch size {bs} mismatched",
+        )
         # assert lengths.max().item() <= slen
         # input_ids = input_ids.transpose(0, 1)  # batch size as dimension 0
         # assert (src_enc is None) == (src_len is None)
@@ -539,17 +540,19 @@ class TFFlaubertMainLayer(tf.keras.layers.Layer):
             position_ids = tf.tile(position_ids, (bs, 1))
 
         # assert shape_list(position_ids) == [bs, slen]  # (slen, bs)
-        tf.debugging.assert_equal(
-            shape_list(position_ids), [bs, slen]
-        ), f"Position id shape {shape_list(position_ids)} and input shape {[bs, slen]} mismatched"
+        (
+            tf.debugging.assert_equal(shape_list(position_ids), [bs, slen]),
+            f"Position id shape {shape_list(position_ids)} and input shape {[bs, slen]} mismatched",
+        )
         # position_ids = position_ids.transpose(0, 1)
 
         # langs
         if langs is not None:
             # assert shape_list(langs) == [bs, slen]  # (slen, bs)
-            tf.debugging.assert_equal(
-                shape_list(langs), [bs, slen]
-            ), f"Lang shape {shape_list(langs)} and input shape {[bs, slen]} mismatched"
+            (
+                tf.debugging.assert_equal(shape_list(langs), [bs, slen]),
+                f"Lang shape {shape_list(langs)} and input shape {[bs, slen]} mismatched",
+            )
             # langs = langs.transpose(0, 1)
 
         # Prepare head mask if needed

src/transformers/models/flava/configuration_flava.py

@@ -218,6 +218,7 @@ class FlavaTextConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "flava_text_model"
 
     def __init__(

src/transformers/models/flava/modeling_flava.py

@@ -1254,9 +1254,7 @@ class FlavaModel(FlavaPreTrainedModel):
         ...     text=["a photo of a cat", "a photo of a dog"], max_length=77, padding="max_length", return_tensors="pt"
         ... )
         >>> text_features = model.get_text_features(**inputs)
-        ```""".format(
-            _CHECKPOINT_FOR_DOC
-        )
+        ```""".format(_CHECKPOINT_FOR_DOC)
         text_outputs = self.text_model(
             input_ids=input_ids,
             attention_mask=attention_mask,
@@ -1305,9 +1303,7 @@ class FlavaModel(FlavaPreTrainedModel):
         >>> inputs = processor(images=image, return_tensors="pt")
 
         >>> image_features = model.get_image_features(**inputs)
-        ```""".format(
-            _CHECKPOINT_FOR_DOC
-        )
+        ```""".format(_CHECKPOINT_FOR_DOC)
         image_outputs = self.image_model(
             pixel_values=pixel_values,
             bool_masked_pos=bool_masked_pos,
@@ -1583,9 +1579,7 @@ class FlavaImageCodebook(FlavaPreTrainedModel):
 
         >>> outputs = model.get_codebook_indices(**inputs)
         ```
-        """.format(
-            _CHECKPOINT_FOR_CODEBOOK_DOC
-        )
+        """.format(_CHECKPOINT_FOR_CODEBOOK_DOC)
         z_logits = self.blocks(pixel_values)
         return torch.argmax(z_logits, axis=1)
 
@@ -1620,9 +1614,7 @@ class FlavaImageCodebook(FlavaPreTrainedModel):
         >>> print(outputs.shape)
         (1, 196)
         ```
-        """.format(
-            _CHECKPOINT_FOR_CODEBOOK_DOC
-        )
+        """.format(_CHECKPOINT_FOR_CODEBOOK_DOC)
         if len(pixel_values.shape) != 4:
             raise ValueError(f"input shape {pixel_values.shape} is not 4d")
         if pixel_values.shape[1] != self.input_channels:

src/transformers/models/flava/processing_flava.py

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

src/transformers/models/fnet/configuration_fnet.py

@@ -22,7 +22,7 @@ logger = logging.get_logger(__name__)
 
 FNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
     "google/fnet-base": "https://huggingface.co/google/fnet-base/resolve/main/config.json",
-    "google/fnet-large": "https://huggingface.co/google/fnet-large/resolve/main/config.json"
+    "google/fnet-large": "https://huggingface.co/google/fnet-large/resolve/main/config.json",
     # See all FNet models at https://huggingface.co/models?filter=fnet
 }
 
@@ -84,6 +84,7 @@ class FNetConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "fnet"
 
     def __init__(

src/transformers/models/fnet/modeling_fnet.py

@@ -61,7 +61,7 @@ _CONFIG_FOR_DOC = "FNetConfig"
 
 FNET_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "google/fnet-base",
-    "google/fnet-large"
+    "google/fnet-large",
     # See all FNet models at https://huggingface.co/models?filter=fnet
 ]
 

src/transformers/models/focalnet/configuration_focalnet.py

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

src/transformers/models/fsmt/configuration_fsmt.py

@@ -28,6 +28,7 @@ class DecoderConfig(PretrainedConfig):
     r"""
     Configuration class for FSMT's decoder specific things. note: this is a private helper class
     """
+
     model_type = "fsmt_decoder"
 
     def __init__(self, vocab_size=0, bos_token_id=0):
@@ -132,6 +133,7 @@ class FSMTConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "fsmt"
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}
 

src/transformers/models/fsmt/modeling_fsmt.py

@@ -472,9 +472,7 @@ class FSMTEncoder(nn.Module):
         self.embed_positions = SinusoidalPositionalEmbedding(
             config.max_position_embeddings + self.padding_idx + 1, embed_dim, self.padding_idx
         )
-        self.layers = nn.ModuleList(
-            [EncoderLayer(config) for _ in range(config.encoder_layers)]
-        )  # type: List[EncoderLayer]
+        self.layers = nn.ModuleList([EncoderLayer(config) for _ in range(config.encoder_layers)])  # type: List[EncoderLayer]
 
     def forward(
         self,
@@ -682,9 +680,7 @@ class FSMTDecoder(nn.Module):
         self.embed_positions = SinusoidalPositionalEmbedding(
             config.max_position_embeddings + self.padding_idx + 1, embed_dim, self.padding_idx
         )
-        self.layers = nn.ModuleList(
-            [DecoderLayer(config) for _ in range(config.decoder_layers)]
-        )  # type: List[DecoderLayer]
+        self.layers = nn.ModuleList([DecoderLayer(config) for _ in range(config.decoder_layers)])  # type: List[DecoderLayer]
 
         if is_deepspeed_zero3_enabled():
             import deepspeed

src/transformers/models/funnel/configuration_funnel.py

@@ -96,6 +96,7 @@ class FunnelConfig(PretrainedConfig):
         pool_q_only (`bool`, *optional*, defaults to `True`):
             Whether or not to apply the pooling only to the query or to query, key and values for the attention layers.
     """
+
     model_type = "funnel"
     attribute_map = {
         "hidden_size": "d_model",

src/transformers/models/fuyu/configuration_fuyu.py

@@ -102,6 +102,7 @@ class FuyuConfig(PretrainedConfig):
     >>> # Initializing a Fuyu fuyu-7b style configuration
     >>> configuration = FuyuConfig()
     ```"""
+
     model_type = "fuyu"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/fuyu/processing_fuyu.py

@@ -319,6 +319,7 @@ class FuyuProcessor(ProcessorMixin):
         tokenizer ([`LlamaTokenizerFast`]):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "FuyuImageProcessor"
     tokenizer_class = "AutoTokenizer"

src/transformers/models/git/configuration_git.py

@@ -188,6 +188,7 @@ class GitConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "git"
 
     def __init__(

src/transformers/models/git/processing_git.py

@@ -33,6 +33,7 @@ class GitProcessor(ProcessorMixin):
         tokenizer ([`AutoTokenizer`]):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "AutoImageProcessor"
     tokenizer_class = "AutoTokenizer"

src/transformers/models/glpn/configuration_glpn.py

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

src/transformers/models/gpt2/modeling_gpt2.py

@@ -1534,7 +1534,20 @@ class GPT2ForTokenClassification(GPT2PreTrainedModel):
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
         expected_loss=0.25,
-        expected_output=["Lead", "Lead", "Lead", "Position", "Lead", "Lead", "Lead", "Lead", "Lead", "Lead", "Lead", "Lead"],
+        expected_output=[
+            "Lead",
+            "Lead",
+            "Lead",
+            "Position",
+            "Lead",
+            "Lead",
+            "Lead",
+            "Lead",
+            "Lead",
+            "Lead",
+            "Lead",
+            "Lead",
+        ],
     )
     # fmt: on
     def forward(

src/transformers/models/gpt_neo/configuration_gpt_neo.py

@@ -102,6 +102,7 @@ class GPTNeoConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "gpt_neo"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "num_heads", "num_hidden_layers": "num_layers"}

src/transformers/models/gpt_neox/configuration_gpt_neox.py

@@ -101,6 +101,7 @@ class GPTNeoXConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config  # doctest: +SKIP
     ```"""
+
     model_type = "gpt_neox"
 
     def __init__(

src/transformers/models/gpt_neox_japanese/configuration_gpt_neox_japanese.py

@@ -81,6 +81,7 @@ class GPTNeoXJapaneseConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "gpt_neox_japanese"
 
     def __init__(

src/transformers/models/gptj/configuration_gptj.py

@@ -85,6 +85,7 @@ class GPTJConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "gptj"
     attribute_map = {
         "max_position_embeddings": "n_positions",