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
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",