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

Llama2 13B chat config and code improvements #3

Closed
wants to merge 2 commits into from

Conversation

agrogov
Copy link

@agrogov agrogov commented Jul 26, 2023

  • Added Dev Container for quick start in fresh env
  • Added Llama2 13B chat config
  • Moved merge to separate script due to memory issues after training
  • Made some code improvements

@georgesung
Copy link
Owner

Thanks a lot for your PR! There were some helpful changes to the code organization for sure. However, since this repo is still a personal tinkering space for me, I don't want to hard-code the device map to 2 GPUs for example (e.g. I'm running on a single GPU for now, maybe a 4-GPU machine in the future, or 8-GPU, etc.). Also I haven't set up a Docker container to run this so I can't test the Dockerfiles, but it's a great idea!

You can make a fork of this repo for your use cases though. Again, thanks for the PR, there were some very good ideas here I may incorporate in the future.

@agrogov
Copy link
Author

agrogov commented Jul 28, 2023

No problem! :)

@agrogov agrogov closed this Jul 28, 2023
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

Successfully merging this pull request may close these issues.

None yet

2 participants