Skip to content

Conversation

@pculliton
Copy link
Collaborator

No description provided.

Also implement support for some model variations:

- Local attention.
- Add support for biases.
- Use RoPE only on half vectors.
- Support different order of QKV weights.

Co-authored-by: Andrey Mikhaylov <[email protected]>
Co-authored-by: Martin Bruse <[email protected]>
Co-authored-by: Zoltan Szabadka <[email protected]>
@pculliton pculliton added the copybara-import Trigger Copybara for merging pull requests label Apr 9, 2024
@pculliton pculliton closed this Apr 9, 2024
@pculliton pculliton reopened this Apr 9, 2024
@pculliton pculliton changed the base branch from main to dev April 9, 2024 04:10
@copybara-service copybara-service bot merged commit 83dd08a into google:dev Apr 9, 2024
@jan-wassenberg
Copy link
Member

Refs #135

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

Labels

copybara-import Trigger Copybara for merging pull requests

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants