SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

update examples after ruff being updated (#36972)

Browse Source 
* update

* update

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar
2025-03-25 18:15:47 +01:00
committed by GitHub
parent a41677a68b
commit 121830ab47
20 changed files with 42 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.circleci/config.yml
View File

@@ -154,7 +154,7 @@ jobs:
path: ~/transformers/installed.txt
- run: python -c "from transformers import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
- run: ruff check examples tests src utils
- run: ruff format tests src utils --check
- run: ruff format examples tests src utils --check
- run: python utils/custom_init_isort.py --check_only
- run: python utils/sort_auto_mappings.py --check_only
- run: python utils/check_doc_toc.py

2
examples/flax/language-modeling/run_bert_flax.py
View File

@@ -53,4 +53,4 @@ for _ in range(nbenchmark):
func()
end = time.time()
print(end - start)
print(f"Throughput: {((nbenchmark * BS)/(end-start)):.3f} examples/sec")
print(f"Throughput: {((nbenchmark * BS) / (end - start)):.3f} examples/sec")

6
examples/legacy/seq2seq/finetune_trainer.py
View File

@@ -231,9 +231,9 @@ def main():
# set decoder_start_token_id for MBart
if model.config.decoder_start_token_id is None and isinstance(tokenizer, (MBartTokenizer, MBartTokenizerFast)):
assert (
data_args.tgt_lang is not None and data_args.src_lang is not None
), "mBart requires --tgt_lang and --src_lang"
assert data_args.tgt_lang is not None and data_args.src_lang is not None, (
"mBart requires --tgt_lang and --src_lang"
)
if isinstance(tokenizer, MBartTokenizer):
model.config.decoder_start_token_id = tokenizer.lang_code_to_id[data_args.tgt_lang]
else:

2
examples/legacy/seq2seq/run_eval_search.py
View File

@@ -128,7 +128,7 @@ def run_search():
results_sorted = sorted(results, key=operator.itemgetter(*task_score_names[task]), reverse=True)
print(" | ".join([f"{col:{col_widths[col]}}" for col in col_names]))
print(" | ".join([f"{'-'*col_widths[col]}" for col in col_names]))
print(" | ".join([f"{'-' * col_widths[col]}" for col in col_names]))
for row in results_sorted:
print(" | ".join([f"{row[col]:{col_widths[col]}}" for col in col_names]))

8
examples/legacy/seq2seq/utils.py
View File

@@ -282,9 +282,9 @@ class Seq2SeqDataCollator:
self.tokenizer = tokenizer
self.pad_token_id = tokenizer.pad_token_id
self.decoder_start_token_id = decoder_start_token_id
assert (
self.pad_token_id is not None
), f"pad_token_id is not defined for ({self.tokenizer.__class__.__name__}), it must be defined."
assert self.pad_token_id is not None, (
f"pad_token_id is not defined for ({self.tokenizer.__class__.__name__}), it must be defined."
)
self.data_args = data_args
self.tpu_num_cores = tpu_num_cores
self.dataset_kwargs = {"add_prefix_space": True} if isinstance(tokenizer, BartTokenizer) else {}
@@ -593,7 +593,7 @@ def assert_all_frozen(model):
model_grads: List[bool] = list(grad_status(model))
n_require_grad = sum(lmap(int, model_grads))
npars = len(model_grads)
assert not any(model_grads), f"{n_require_grad/npars:.1%} of {npars} weights require grad"
assert not any(model_grads), f"{n_require_grad / npars:.1%} of {npars} weights require grad"
def assert_not_all_frozen(model):

2
examples/legacy/token-classification/tasks.py
View File

@@ -131,7 +131,7 @@ class POS(TokenClassificationTask):
s_p = preds_list[example_id]
out = ""
for token in sentence:
out += f'{token["form"]} ({token["upos"]}|{s_p.pop(0)}) '
out += f"{token['form']} ({token['upos']}|{s_p.pop(0)}) "
out += "\n"
writer.write(out)
example_id += 1

2
examples/modular-transformers/modeling_multimodal2.py
View File

@@ -534,7 +534,7 @@ class Multimodal2VisionEmbeddings(nn.Module):
batch_size, _, height, width = pixel_values.shape
if not interpolate_pos_encoding and (height != self.image_size or width != self.image_size):
raise ValueError(
f"Input image size ({height}*{width}) doesn't match model" f" ({self.image_size}*{self.image_size})."
f"Input image size ({height}*{width}) doesn't match model ({self.image_size}*{self.image_size})."
)
target_dtype = self.patch_embedding.weight.dtype
patch_embeds = self.patch_embedding(pixel_values.to(dtype=target_dtype)) # shape = [*, width, grid, grid]

2
examples/pytorch/language-modeling/run_clm.py
View File

@@ -438,7 +438,7 @@ def main():
else:
model = AutoModelForCausalLM.from_config(config, trust_remote_code=model_args.trust_remote_code)
n_params = sum({p.data_ptr(): p.numel() for p in model.parameters()}.values())
logger.info(f"Training new model from scratch - Total size={n_params/2**20:.2f}M params")
logger.info(f"Training new model from scratch - Total size={n_params / 2**20:.2f}M params")
# We resize the embeddings only when necessary to avoid index errors. If you are creating a model from scratch
# on a small vocab and want a smaller embedding size, remove this test.

5
examples/pytorch/language-modeling/run_fim.py
View File

@@ -265,8 +265,7 @@ class DataTrainingArguments:
default="<fim_pad>",
metadata={
"help": (
"Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True. "
"Defaults to '<fim_pad>'."
"Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True. Defaults to '<fim_pad>'."
)
},
)
@@ -514,7 +513,7 @@ def main():
attn_implementation=model_args.attn_implementation,
)
n_params = sum({p.data_ptr(): p.numel() for p in model.parameters()}.values())
logger.info(f"Training new model from scratch - Total size={n_params/2**20:.2f}M params")
logger.info(f"Training new model from scratch - Total size={n_params / 2**20:.2f}M params")
# Add the new FIM tokens to the tokenizer and resize model's vocab embeddings
special_tokens = [data_args.fim_prefix_token, data_args.fim_middle_token, data_args.fim_suffix_token]

4
examples/pytorch/language-modeling/run_fim_no_trainer.py
View File

@@ -234,9 +234,7 @@ def parse_args():
"--fim_pad_token",
type=str,
default="<fim_pad>",
help=(
"Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True." " Defaults to '<fim_pad>'."
),
help=("Fill-in-Middle Pad token. Used only when 'truncate_or_pad' is set to True. Defaults to '<fim_pad>'."),
)
parser.add_argument(
"--preprocessing_num_workers",

2
examples/pytorch/speech-recognition/run_speech_recognition_ctc.py
View File

@@ -491,7 +491,7 @@ def main():
# E.g. characters, such as `,` and `.` do not really have an acoustic characteristic
# that could be easily picked up by the model
chars_to_ignore_regex = (
f'[{"".join(data_args.chars_to_ignore)}]' if data_args.chars_to_ignore is not None else None
f"[{''.join(data_args.chars_to_ignore)}]" if data_args.chars_to_ignore is not None else None
)
text_column_name = data_args.text_column_name

2
examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py
View File

@@ -471,7 +471,7 @@ def main():
# E.g. characters, such as `,` and `.` do not really have an acoustic characteristic
# that could be easily picked up by the model
chars_to_ignore_regex = (
f'[{"".join(data_args.chars_to_ignore)}]' if data_args.chars_to_ignore is not None else None
f"[{''.join(data_args.chars_to_ignore)}]" if data_args.chars_to_ignore is not None else None
)
text_column_name = data_args.text_column_name

6
examples/pytorch/summarization/run_summarization.py
View File

@@ -505,9 +505,9 @@ def main():
return
if isinstance(tokenizer, tuple(MULTILINGUAL_TOKENIZERS)):
assert (
data_args.lang is not None
), f"{tokenizer.__class__.__name__} is a multilingual tokenizer which requires --lang argument"
assert data_args.lang is not None, (
f"{tokenizer.__class__.__name__} is a multilingual tokenizer which requires --lang argument"
)
tokenizer.src_lang = data_args.lang
tokenizer.tgt_lang = data_args.lang

12
examples/pytorch/text-classification/run_classification.py
View File

@@ -199,9 +199,9 @@ class DataTrainingArguments:
train_extension = self.train_file.split(".")[-1]
assert train_extension in ["csv", "json"], "`train_file` should be a csv or a json file."
validation_extension = self.validation_file.split(".")[-1]
assert (
validation_extension == train_extension
), "`validation_file` should have the same extension (csv or json) as `train_file`."
assert validation_extension == train_extension, (
"`validation_file` should have the same extension (csv or json) as `train_file`."
)
@dataclass
@@ -357,9 +357,9 @@ def main():
if data_args.test_file is not None:
train_extension = data_args.train_file.split(".")[-1]
test_extension = data_args.test_file.split(".")[-1]
assert (
test_extension == train_extension
), "`test_file` should have the same extension (csv or json) as `train_file`."
assert test_extension == train_extension, (
"`test_file` should have the same extension (csv or json) as `train_file`."
)
data_files["test"] = data_args.test_file
else:
raise ValueError("Need either a dataset name or a test file for `do_predict`.")

12
examples/pytorch/text-classification/run_glue.py
View File

@@ -156,9 +156,9 @@ class DataTrainingArguments:
train_extension = self.train_file.split(".")[-1]
assert train_extension in ["csv", "json"], "`train_file` should be a csv or a json file."
validation_extension = self.validation_file.split(".")[-1]
assert (
validation_extension == train_extension
), "`validation_file` should have the same extension (csv or json) as `train_file`."
assert validation_extension == train_extension, (
"`validation_file` should have the same extension (csv or json) as `train_file`."
)
@dataclass
@@ -313,9 +313,9 @@ def main():
if data_args.test_file is not None:
train_extension = data_args.train_file.split(".")[-1]
test_extension = data_args.test_file.split(".")[-1]
assert (
test_extension == train_extension
), "`test_file` should have the same extension (csv or json) as `train_file`."
assert test_extension == train_extension, (
"`test_file` should have the same extension (csv or json) as `train_file`."
)
data_files["test"] = data_args.test_file
else:
raise ValueError("Need either a GLUE task or a test file for `do_predict`.")

2
examples/pytorch/text-generation/run_generation.py
View File

@@ -322,7 +322,7 @@ def main():
parser.add_argument(
"--use_cpu",
action="store_true",
help="Whether or not to use cpu. If set to False, " "we will use gpu/npu or mps device if available",
help="Whether or not to use cpu. If set to False, we will use gpu/npu or mps device if available",
)
parser.add_argument("--num_return_sequences", type=int, default=1, help="The number of samples to generate.")
parser.add_argument(

2
examples/pytorch/text-generation/run_generation_contrastive_search.py
View File

@@ -68,7 +68,7 @@ def main():
parser.add_argument(
"--use_cpu",
action="store_true",
help="Whether or not to use cpu. If set to False, " "we will use gpu/npu or mps device if available",
help="Whether or not to use cpu. If set to False, we will use gpu/npu or mps device if available",
)
parser.add_argument(
"--fp16",

6
examples/pytorch/translation/run_translation_no_trainer.py
View File

@@ -436,9 +436,9 @@ def main():
# Set decoder_start_token_id
if model.config.decoder_start_token_id is None and isinstance(tokenizer, (MBartTokenizer, MBartTokenizerFast)):
assert (
args.target_lang is not None and args.source_lang is not None
), "mBart requires --target_lang and --source_lang"
assert args.target_lang is not None and args.source_lang is not None, (
"mBart requires --target_lang and --source_lang"
)
if isinstance(tokenizer, MBartTokenizer):
model.config.decoder_start_token_id = tokenizer.lang_code_to_id[args.target_lang]
else:

2
examples/run_on_remote.py
View File

@@ -56,7 +56,7 @@ if __name__ == "__main__":
cluster.run(["pip install torch --upgrade --extra-index-url https://download.pytorch.org/whl/cu117"])
# Run example. You can bypass the CLI wrapper and paste your own code here.
cluster.run([f'python transformers/examples/{args.example} {" ".join(shlex.quote(arg) for arg in unknown)}'])
cluster.run([f"python transformers/examples/{args.example} {' '.join(shlex.quote(arg) for arg in unknown)}"])
# Alternatively, we can just import and run a training function (especially if there's no wrapper CLI):
# from my_script... import train

6
examples/tensorflow/translation/run_translation.py
View File

@@ -501,9 +501,9 @@ def main():
# region Set decoder_start_token_id
if model.config.decoder_start_token_id is None and isinstance(tokenizer, (MBartTokenizer, MBartTokenizerFast)):
assert (
data_args.target_lang is not None and data_args.source_lang is not None
), "mBart requires --target_lang and --source_lang"
assert data_args.target_lang is not None and data_args.source_lang is not None, (
"mBart requires --target_lang and --source_lang"
)
if isinstance(tokenizer, MBartTokenizer):
model.config.decoder_start_token_id = tokenizer.lang_code_to_id[data_args.target_lang]
else: