[`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/x_clip/processing_x_clip.py

@@ -35,6 +35,7 @@ class XCLIPProcessor(ProcessorMixin):
         tokenizer ([`CLIPTokenizerFast`], *optional*):
             The tokenizer is a required input.
     """
+
     attributes = ["image_processor", "tokenizer"]
     image_processor_class = "VideoMAEImageProcessor"
     tokenizer_class = ("CLIPTokenizer", "CLIPTokenizerFast")

src/transformers/models/xglm/configuration_xglm.py

@@ -85,6 +85,7 @@ class XGLMConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "xglm"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/xlm/modeling_tf_xlm.py

@@ -387,9 +387,10 @@ class TFXLMMainLayer(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)
@@ -408,17 +409,19 @@ class TFXLMMainLayer(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/xlm_prophetnet/configuration_xlm_prophetnet.py

@@ -100,6 +100,7 @@ class XLMProphetNetConfig(PretrainedConfig):
         use_cache (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return the last key/values attentions (not used by all models).
     """
+
     model_type = "xlm-prophetnet"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {

src/transformers/models/xlm_prophetnet/modeling_xlm_prophetnet.py

@@ -1469,9 +1469,7 @@ class XLMProphetNetDecoder(XLMProphetNetPreTrainedModel):
         >>> import torch
 
         >>> tokenizer = AutoTokenizer.from_pretrained("patrickvonplaten/xprophetnet-large-uncased-standalone")
-        >>> model = XLMProphetNetDecoder.from_pretrained(
-        ...     "patrickvonplaten/xprophetnet-large-uncased-standalone", add_cross_attention=False
-        ... )
+        >>> model = XLMProphetNetDecoder.from_pretrained("patrickvonplaten/xprophetnet-large-uncased-standalone", add_cross_attention=False)
         >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
         >>> outputs = model(**inputs)
 
@@ -1948,9 +1946,7 @@ class XLMProphetNetForConditionalGeneration(XLMProphetNetPreTrainedModel):
         >>> from transformers import AutoTokenizer, XLMProphetNetForConditionalGeneration
 
         >>> tokenizer = AutoTokenizer.from_pretrained("patrickvonplaten/xprophetnet-large-uncased-standalone")
-        >>> model = XLMProphetNetForConditionalGeneration.from_pretrained(
-        ...     "patrickvonplaten/xprophetnet-large-uncased-standalone"
-        ... )
+        >>> model = XLMProphetNetForConditionalGeneration.from_pretrained("patrickvonplaten/xprophetnet-large-uncased-standalone")
 
         >>> input_ids = tokenizer(
         ...     "Studies have been shown that owning a dog is good for you", return_tensors="pt"

src/transformers/models/xlm_roberta/configuration_xlm_roberta.py

@@ -110,6 +110,7 @@ class XLMRobertaConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "xlm-roberta"
 
     def __init__(

src/transformers/models/xlm_roberta_xl/configuration_xlm_roberta_xl.py

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

src/transformers/models/xmod/configuration_xmod.py

@@ -119,6 +119,7 @@ class XmodConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "xmod"
 
     def __init__(

src/transformers/models/yolos/configuration_yolos.py

@@ -103,6 +103,7 @@ class YolosConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "yolos"
 
     def __init__(

src/transformers/models/yolos/modeling_yolos.py

@@ -904,9 +904,9 @@ def sigmoid_focal_loss(inputs, targets, num_boxes, alpha: float = 0.25, gamma: f
 # Copied from transformers.models.detr.modeling_detr.DetrLoss with Detr->Yolos
 class YolosLoss(nn.Module):
     """
-    This class computes the losses for YolosForObjectDetection/YolosForSegmentation. The process happens in two steps:
-    1) we compute hungarian assignment between ground truth boxes and the outputs of the model 2) we supervise each
-    pair of matched ground-truth / prediction (supervise class and box).
+    This class computes the losses for YolosForObjectDetection/YolosForSegmentation. The process happens in two steps: 1)
+    we compute hungarian assignment between ground truth boxes and the outputs of the model 2) we supervise each pair
+    of matched ground-truth / prediction (supervise class and box).
 
     A note on the `num_classes` argument (copied from original repo in detr.py): "the naming of the `num_classes`
     parameter of the criterion is somewhat misleading. It indeed corresponds to `max_obj_id` + 1, where `max_obj_id` is

src/transformers/models/yoso/configuration_yoso.py

@@ -94,6 +94,7 @@ class YosoConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "yoso"
 
     def __init__(

src/transformers/models/yoso/modeling_yoso.py

@@ -88,7 +88,7 @@ def to_contiguous(input_tensors):
 
 
 def normalize(input_tensors):
-    if type(input_tensors) is list:
+    if isinstance(input_tensors, list):
         out = []
         for tensor in input_tensors:
             out.append(nn.functional.normalize(tensor, p=2, dim=-1))

src/transformers/tokenization_utils_base.py

@@ -1593,9 +1593,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin, PushToHubMixin):
         # By default, do not split special tokens for both fast and slow tokenizers
         self.split_special_tokens = kwargs.pop("split_special_tokens", False)
 
-        self.deprecation_warnings = (
-            {}
-        )  # Use to store when we have already noticed a deprecation warning (avoid overlogging).
+        self.deprecation_warnings = {}  # Use to store when we have already noticed a deprecation warning (avoid overlogging).
         self._in_target_context_manager = False
 
         # Stores a Jinja template that formats chat histories into tokenizable strings

src/transformers/trainer_pt_utils.py

@@ -896,7 +896,7 @@ def metrics_format(self, metrics: Dict[str, float]) -> Dict[str, float]:
             metrics_copy[k] = _secs2timedelta(v)
         elif k == "total_flos":
             metrics_copy[k] = f"{ int(v) >> 30 }GF"
-        elif type(metrics_copy[k]) == float:
+        elif isinstance(metrics_copy[k], float):
             metrics_copy[k] = round(v, 4)
 
     return metrics_copy

src/transformers/utils/fx.py

@@ -174,7 +174,7 @@ _SPECIAL_SUPPORTED_MODELS = [
     "Speech2Text2Decoder",
     "TrOCRDecoder",
     "PeftModelForCausalLM",
-    "PeftModelForSeq2SeqLM"
+    "PeftModelForSeq2SeqLM",
     # TODO: add support for them as it should be quite easy to do so (small blocking issues).
     # XLNetForQuestionAnswering,
 ]

src/transformers/utils/sentencepiece_model_pb2.py

@@ -1445,7 +1445,7 @@ TrainerSpec = _reflection.GeneratedProtocolMessageType(
     (_message.Message,),
     {
         "DESCRIPTOR": _TRAINERSPEC,
-        "__module__": "sentencepiece_model_pb2"
+        "__module__": "sentencepiece_model_pb2",
         # @@protoc_insertion_point(class_scope:sentencepiece.TrainerSpec)
     },
 )
@@ -1456,7 +1456,7 @@ NormalizerSpec = _reflection.GeneratedProtocolMessageType(
     (_message.Message,),
     {
         "DESCRIPTOR": _NORMALIZERSPEC,
-        "__module__": "sentencepiece_model_pb2"
+        "__module__": "sentencepiece_model_pb2",
         # @@protoc_insertion_point(class_scope:sentencepiece.NormalizerSpec)
     },
 )
@@ -1471,12 +1471,12 @@ SelfTestData = _reflection.GeneratedProtocolMessageType(
             (_message.Message,),
             {
                 "DESCRIPTOR": _SELFTESTDATA_SAMPLE,
-                "__module__": "sentencepiece_model_pb2"
+                "__module__": "sentencepiece_model_pb2",
                 # @@protoc_insertion_point(class_scope:sentencepiece.SelfTestData.Sample)
             },
         ),
         "DESCRIPTOR": _SELFTESTDATA,
-        "__module__": "sentencepiece_model_pb2"
+        "__module__": "sentencepiece_model_pb2",
         # @@protoc_insertion_point(class_scope:sentencepiece.SelfTestData)
     },
 )
@@ -1492,12 +1492,12 @@ ModelProto = _reflection.GeneratedProtocolMessageType(
             (_message.Message,),
             {
                 "DESCRIPTOR": _MODELPROTO_SENTENCEPIECE,
-                "__module__": "sentencepiece_model_pb2"
+                "__module__": "sentencepiece_model_pb2",
                 # @@protoc_insertion_point(class_scope:sentencepiece.ModelProto.SentencePiece)
             },
         ),
         "DESCRIPTOR": _MODELPROTO,
-        "__module__": "sentencepiece_model_pb2"
+        "__module__": "sentencepiece_model_pb2",
         # @@protoc_insertion_point(class_scope:sentencepiece.ModelProto)
     },
 )

templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/configuration_{{cookiecutter.lowercase_modelname}}.py

@@ -238,4 +238,3 @@ class {{cookiecutter.camelcase_modelname}}Config(PretrainedConfig):
             **kwargs
         )
 
-    
\ No newline at end of file