Can't find a way to make it work with llama.cpp

#102
by ZeroWw - opened

I'm trying to use gemma-7b with llama.cpp
I converted the model to gguf.
As I start the server and try to chat, the model answers correctly the first time (but very shortly) then starts talking to itself :(
Any idea?

Thank you for asking queries
Could you let us know about the variant of gemma 7b model as well as the steps you performed?

ZeroWw changed discussion status to closed

Sign up or log in to comment