Update quality tooling for formatting (#21480)

* Result of black 23.1

* Update target to Python 3.7

* Switch flake8 to ruff

* Configure isort

* Configure isort

* Apply isort with line limit

* Put the right black version

* adapt black in check copies

* Fix copies

examples/research_projects/deebert/src/modeling_highway_bert.py

@@ -229,7 +229,10 @@ class DeeBertModel(BertPreTrainedModel):
         sequence_output = encoder_outputs[0]
         pooled_output = self.pooler(sequence_output)
 
-        outputs = (sequence_output, pooled_output,) + encoder_outputs[
+        outputs = (
+            sequence_output,
+            pooled_output,
+        ) + encoder_outputs[
             1:
         ]  # add hidden_states and attentions if they are here
         return outputs  # sequence_output, pooled_output, (hidden_states), (attentions), highway exits

examples/research_projects/deebert/src/modeling_highway_roberta.py

@@ -19,7 +19,6 @@ from .modeling_highway_bert import BertPreTrainedModel, DeeBertModel, HighwayExc
     ROBERTA_START_DOCSTRING,
 )
 class DeeRobertaModel(DeeBertModel):
-
     config_class = RobertaConfig
     base_model_prefix = "roberta"
 
@@ -36,7 +35,6 @@ class DeeRobertaModel(DeeBertModel):
     ROBERTA_START_DOCSTRING,
 )
 class DeeRobertaForSequenceClassification(BertPreTrainedModel):
-
     config_class = RobertaConfig
     base_model_prefix = "roberta"
 

examples/research_projects/deebert/test_glue_deebert.py

@@ -4,6 +4,7 @@ import sys
 from unittest.mock import patch
 
 import run_glue_deebert
+
 from transformers.testing_utils import TestCasePlus, get_gpu_count, require_torch_non_multi_gpu, slow
 
 
@@ -45,7 +46,6 @@ class DeeBertTests(TestCasePlus):
     @slow
     @require_torch_non_multi_gpu
     def test_glue_deebert_train(self):
-
         train_args = """
             --model_type roberta
             --model_name_or_path roberta-base