May need reconversion

#1
by concedo - opened

The convert-hf-to-gguf.py script was recently updated to support llama 3 pretokenization, that fixed some incorrect regex merges. I believe that may require a reconversion and requantization of all llama 3 models.

https://github.com/ggerganov/llama.cpp/pull/6920

I've updated the model card with instructions on how to get the correct pretokenization.

Sign up or log in to comment