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

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):