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/codeparrot/scripts/bpe_training.py

@@ -1,7 +1,7 @@
+from arguments import TokenizerTrainingArguments
 from datasets import load_dataset
 from tqdm import tqdm
 
-from arguments import TokenizerTrainingArguments
 from transformers import AutoTokenizer, HfArgumentParser
 from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
 

examples/research_projects/codeparrot/scripts/codeparrot_training.py

@@ -6,16 +6,16 @@ from pathlib import Path
 
 import datasets
 import torch
+from accelerate import Accelerator, DistributedType
+from arguments import TrainingArguments
 from datasets import load_dataset
+from huggingface_hub import Repository
 from torch.optim import AdamW
 from torch.utils.data import IterableDataset
 from torch.utils.data.dataloader import DataLoader
 from torch.utils.data.datapipes.iter.combinatorics import ShufflerIterDataPipe
 
 import transformers
-from accelerate import Accelerator, DistributedType
-from arguments import TrainingArguments
-from huggingface_hub import Repository
 from transformers import AutoModelForCausalLM, AutoTokenizer, HfArgumentParser, get_scheduler, set_seed
 
 

examples/research_projects/codeparrot/scripts/human_eval.py

@@ -5,15 +5,15 @@ import re
 from collections import defaultdict
 
 import torch
+from accelerate import Accelerator
+from accelerate.utils import set_seed
+from arguments import HumanEvalArguments
 from datasets import load_dataset, load_metric
 from torch.utils.data import IterableDataset
 from torch.utils.data.dataloader import DataLoader
 from tqdm import tqdm
 
 import transformers
-from accelerate import Accelerator
-from accelerate.utils import set_seed
-from arguments import HumanEvalArguments
 from transformers import AutoModelForCausalLM, AutoTokenizer, HfArgumentParser, StoppingCriteria, StoppingCriteriaList
 
 

examples/research_projects/codeparrot/scripts/initialize_model.py

@@ -1,4 +1,5 @@
 from arguments import InitializationArguments
+
 from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, HfArgumentParser
 
 

examples/research_projects/codeparrot/scripts/minhash_deduplication.py

@@ -6,10 +6,9 @@ from functools import partial
 from typing import Dict, List, Optional, Set, Tuple, Type
 
 from datasets import Dataset
-from tqdm import tqdm
-
 from datasketch import MinHash, MinHashLSH
 from dpu_utils.utils.iterators import ThreadedIterator
+from tqdm import tqdm
 
 
 NON_ALPHA = re.compile("[^A-Za-z_0-9]")

examples/research_projects/codeparrot/scripts/preprocessing.py

@@ -9,10 +9,10 @@ import time
 from pathlib import Path
 
 import numpy as np
-from datasets import load_dataset
-
 from arguments import PreprocessingArguments
+from datasets import load_dataset
 from minhash_deduplication import deduplicate_dataset
+
 from transformers import AutoTokenizer, HfArgumentParser
 
 

examples/research_projects/codeparrot/scripts/pretokenizing.py

@@ -1,9 +1,9 @@
 import multiprocessing
 import time
 
+from arguments import PretokenizationArguments
 from datasets import load_dataset
 
-from arguments import PretokenizationArguments
 from transformers import AutoTokenizer, HfArgumentParser
 
 

examples/research_projects/codeparrot/scripts/tests/test_deduplicate.py

@@ -1,7 +1,6 @@
 from unittest import TestCase
 
 from datasets import Dataset
-
 from minhash_deduplication import deduplicate_dataset, make_duplicate_clusters
 
 

examples/research_projects/codeparrot/scripts/validation_loss.py

@@ -1,12 +1,12 @@
 import logging
 
 import torch
+from accelerate import Accelerator
+from arguments import EvaluationArguments
 from datasets import load_dataset
 from torch.utils.data import IterableDataset
 from torch.utils.data.dataloader import DataLoader
 
-from accelerate import Accelerator
-from arguments import EvaluationArguments
 from transformers import AutoModelForCausalLM, AutoTokenizer, HfArgumentParser, set_seed