SamSuka
GET GOING FAST
GET GOING FAST

patreon


Installing and Using LLama.CPP with LLMs

In this video we go ahead and get our command prompt LLM inference working. This becomes an important task as we want to build applications for people to use. Is a lightweight and heavily functional software that can be ran on multiple hardware configurations.

The repository is here: https://github.com/ggerganov/llama.cpp


More Creators