Hacker News Reader

The llama source code in the original repo has been updated for llama 2: https://github.com/facebookresearch/llama

do you know if llama.cpp will work out of the box or do we need to wait for the code to be updated?

Likely needs to be updated

Edit: Only the case for the 34B and 70B models. 7B and 13B run as-is.

You can download the GGML model already