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

Possibility of using Mamba SSM #390

Closed
RookieIndieDev opened this issue Mar 2, 2024 · 3 comments
Closed

Possibility of using Mamba SSM #390

RookieIndieDev opened this issue Mar 2, 2024 · 3 comments
Labels
enhancement New feature or request help wanted Extra attention is needed local Issue related to local generation

Comments

@RookieIndieDev
Copy link

RookieIndieDev commented Mar 2, 2024 •
edited
Loading

Mamba SSM architecture has some improvements over the standard transformer based LLMs it seems. Mamba Paper. There are people working on implementations with llama.cpp, mentioned in this GitHub thread towards the end
@danemadsen
Copy link
Member

Will be added once its in llama cpp

@danemadsen danemadsen added enhancement New feature or request help wanted Extra attention is needed local Issue related to local generation labels Mar 4, 2024
@RookieIndieDev
Copy link
Author

Looks like Mamba support has been merged master branch of llama.cpp PR Link

@danemadsen
Copy link
Member

updated llama cpp and merged

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request help wanted Extra attention is needed local Issue related to local generation
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@RookieIndieDev @danemadsen