GGUF version

#23
by reddiamond - opened

I was wondering if you will be converting GGML versions of LLaMA 2 chat to GGUF in near future?

Same here. Llama cpp did not support back ggml bin version.

Same here. I'm trying to use llama-cpp-python to run Llama-2-7B-Chat-GGML but it is not possible anymore, since since version 0.1.79 requires the model to be GGUF (current version 0.1.83).

reddiamond changed discussion status to closed

Sign up or log in to comment