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

questions about coca_roberta-ViT-B-32.json #445

Open
ae86208 opened this issue Feb 22, 2023 · 0 comments · May be fixed by #447
Open

questions about coca_roberta-ViT-B-32.json #445

ae86208 opened this issue Feb 22, 2023 · 0 comments · May be fixed by #447

Comments

@ae86208
Copy link

ae86208 commented Feb 22, 2023

With the default config, hugging face text encoder does not add casual mask, which may lead to information leakage in the decoder side. If using text transformers in open_clip, the problem does not exist since casual mask was added.
@gpucce gpucce linked a pull request Feb 22, 2023 that will close this issue
Draft
4 tasks
@sandeepmukh sandeepmukh mentioned this issue Apr 18, 2024
Closed
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

Successfully merging a pull request may close this issue.

Make coca and HF work together gpucce/open_clip
1 participant
@ae86208