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

I-JEPA - contributing to lib #1260

Closed
Natyren opened this issue May 29, 2023 · 4 comments
Closed

I-JEPA - contributing to lib #1260

Natyren opened this issue May 29, 2023 · 4 comments

Comments

@Natyren
Copy link
Contributor

Natyren commented May 29, 2023

In this issue, I have initiated the beginning of a PR to implement I-JEPA. If there are any concerns or suggestions regarding potential issues or best practices, please kindly share them.
@guarin guarin mentioned this issue May 30, 2023
Open
6 tasks
@Natyren
Copy link
Contributor Author

Natyren commented Jun 2, 2023

@guarin Hello! Can I implement additional module with Attention and Causal Attention (like in x-formers) for usage in this model (Causal Attention for Predictors).

@Natyren
Copy link
Contributor Author

Natyren commented Jun 2, 2023 •
edited
Loading

Sorry for interruption, looks like figured out how to do it with attention mask in mha in PyTorch. So there is no need to add module

@Natyren
Copy link
Contributor Author

Natyren commented Jun 7, 2023

#1273 Is starting point to this issue

@Natyren
Copy link
Contributor Author

Natyren commented Jul 14, 2023

Completed with experimental #1273

@Natyren Natyren closed this as completed Jul 14, 2023
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
1 participant
@Natyren