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.

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

how to avoid information leakage in the convolution #1

Open
0-KaiKai-0 opened this issue Jul 19, 2024 · 1 comment
Open

how to avoid information leakage in the convolution #1

0-KaiKai-0 opened this issue Jul 19, 2024 · 1 comment

Comments

@0-KaiKai-0
Copy link

I sincerely appreciate your work! Wish to see your complete repo!

I have a question here. Does the convolution work on the sequence length? If so, there maybe information leakage for decoder-only models. My understanding may not be correct.

@cairuisi
Copy link
Collaborator

cairuisi commented Sep 9, 2024

Thank you for your interest in our work. The convolution indeed operates over the sequence length but is applied only to the previous KV Cache, excluding any unseen tokens. As a result, there is no risk of information leakage.

Please let me know if you have other questions. Thanks.

Best,
Ruisi

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants