Skip to content

fix: use dtype instead of deprecated torch_dtype #978

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
xyf5432 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: use dtype instead of deprecated torch_dtype #978

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion contrib/rlhflow/reward_modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,15 @@
DatasetArguments,
ModelArguments,
)
import transformers
from packaging.version import Version

def _dtype_kwargs(dtype):
"""`dtype` keyword of `from_pretrained` exists since transformers 4.56 (PR #39782);
older versions use `torch_dtype`."""
if Version(transformers.__version__) >= Version("4.56"):
return {"dtype": dtype}
return {"torch_dtype": dtype}

## Prepare training_args
pipeline_name = "finetuner"
Expand All @@ -42,7 +51,7 @@
)
# trust_remote_code=True if you want to use chatglm
model = AutoModelForSequenceClassification.from_pretrained(
model_args.model_name_or_path, num_labels=1, torch_dtype=torch.bfloat16
model_args.model_name_or_path, num_labels=1, **_dtype_kwargs(torch.bfloat16),
)
model_lora = get_peft_model(model, peft_config)
model_lora.print_trainable_parameters()
Expand Down