TheBloke

/

Llama-2-7B-GGML

like 214

Hello everyone,
I'm running the llama.cpp from https://github.com/ggerganov/llama.cpp
and I'm stuck with the model thing.
Can someone explain it like I'm 5 on what to do with this models and the repository?

I'm trying to run the docker version of it.

Thanks!