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

Implement Additive Attention #4

Closed

8 tasks done

Rishit-dagli opened this issue Aug 30, 2021 · 0 comments · Fixed by #8

Closed

8 tasks done

Implement Additive Attention #4

Rishit-dagli opened this issue Aug 30, 2021 · 0 comments · Fixed by #8

Projects

Fast-Transformer

Milestone

Owner

Rishit-dagli commented Aug 30, 2021 •

edited

Implement Additive Attention as a TensorFlow layer:

Figure out using rotary embeddings
Add masking functionality
Relative Position embeddings
Calculate query attention logits
Calculate Global Query tokens
Calculate key attention logits
Calculate Global Key tokens
Add queries as residuals

Rishit-dagli created this issue from a note in Fast-Transformer (To do)

Rishit-dagli mentioned this issue

Put together a Fast Transformer model #5

Closed

4 tasks

Rishit-dagli added this to the 0.1.0 milestone

Rishit-dagli mentioned this issue

Implement FastAttention layer #8

Merged

Rishit-dagli closed this as completed in #8

Fast-Transformer automation moved this from To do to Done

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment