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 long does it take to merge three 7B models? #5

Open
tanganke opened this issue Mar 28, 2024 · 0 comments
Open

How long does it take to merge three 7B models? #5

tanganke opened this issue Mar 28, 2024 · 0 comments

Comments

@tanganke
Copy link

How long does it take to merge three 7B models for different methods (PS, DFS, PS+DFS)?

  • Shisa Gamma 7B v1
  • WizardMath 7B v1.1
  • Abel 7B 002

And what are the system requirements to do the merge? Do I need to load 7B models simultaneously and merge them on GPUs or I can merge them lazily on disk like mergekit and load them to GPUs for evolutionary?

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

1 participant