Skip to content
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

Jump to bottom

Is it possible to apply GeDi to encoder-decoder models? #2

Open
20174376 opened this issue Aug 26, 2022 · 1 comment
Open

Is it possible to apply GeDi to encoder-decoder models? #2

20174376 opened this issue Aug 26, 2022 · 1 comment

Comments

@20174376
Copy link

Is it possible to apply GeDi to encoder-decoder models? Like T5 or BART?
@xxbidiao
Copy link
Owner

Sorry for the late reply!
If these models get their next token by softmax-ing over a distribution of candidate tokens (which I believe they do), you should be able to apply GeDi and plug-and-blend to them.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@xxbidiao @20174376