Skip to content

Make beam_constraints.Constraint.advance() docstring more accurate #32674

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
gante merged 2 commits into from
Aug 16, 2024
Merged

Make beam_constraints.Constraint.advance() docstring more accurate #32674

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9d7fbf6
Fix beam_constraints.Constraint.advance() docstring
alex-calderwood Aug 14, 2024
8176c7d
Update src/transformers/generation/beam_constraints.py
gante Aug 16, 2024
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: 5 additions & 2 deletions src/transformers/generation/beam_constraints.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,10 +48,13 @@ def test(self):
@abstractmethod
def advance(self):
"""
When called, returns the token that would take this constraint one step closer to being fulfilled.
When called, returns the token(s) that would take this constraint one step closer to being fulfilled.

Return:
token_ids(`torch.tensor`): Must be a tensor of a list of indexable tokens, not some integer.
token_ids (Union[int, List[int], None]):
- A single token ID (int) that advances the constraint, or
- A list of token IDs that could advance the constraint
- None if the constraint is completed or cannot be advanced
"""
raise NotImplementedError(
f"{self.__class__} is an abstract class. Only classes inheriting this class can be called."
Expand Down