Skip to content

use eos_token_id if there is no pad_token_id to avoid sending None #541

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

Merged
merged 1 commit into from
Nov 9, 2025
Merged

use eos_token_id if there is no pad_token_id to avoid sending None #541

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
7 changes: 6 additions & 1 deletion apps/grpo/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,7 +266,12 @@ async def sample(self) -> dict[str, str] | None:

@endpoint
async def pad_token(self):
return self._tokenizer.pad_token_id
# Use pad_token_id if available, otherwise use eos_token_id
# Llama models don't have a pad token by default
if self._tokenizer.pad_token_id is not None:
return self._tokenizer.pad_token_id
else:
return self._tokenizer.eos_token_id


async def drop_weights(version: int):
Expand Down
Loading