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

Make notebooks out of the LLaMA C++ examples #8

Open

2 of 4 tasks

davidrpugh opened this issue Oct 3, 2024 · 1 comment

Assignees

Member

davidrpugh commented Oct 3, 2024 •

edited

Loading

LLaMA C++ repository has lots of great examples but I think its best to focus on four for now.

Once these four tutorials are finished, then I can make a tutorial on how to take a new model and add support for LLaMA C++.

davidrpugh self-assigned this

Member Author

davidrpugh commented Oct 15, 2024

Working through the main example from LLaMA C++ and encountered the following issues.

Need to specify the cache directory so that LLaMA C++ caches models inside the project directory (and not some arbitrary place in the user's home directory. Maybe this requires setting some environment variable?
Need to modify the build from source scripts to make sure that LLaMA C++ is built with curl support to enable to nice to have functionality of downloading models from HF using the --model-url command line option.

davidrpugh mentioned this issue

Add tutorials covering the contents of the main LLaMA C++ example #19

Merged

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