How to use this with llama.cpp

#1
by subbur - opened

Can it be used with llama.cpp server ?

Yes, you would implement the llama.cpp server using OpenAI API completions. Then, you would point the GPT Pilot .env to your server address. https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md

Sign up or log in to comment