(github.com)

1311 points msoad | 2 comments | 31 Mar 23 20:37 UTC | HN request time: 0.408s | source

1. UncleOxidant ◴[31 Mar 23 21:29 UTC] No.35393932[source]▶

What's the difference between llama.cpp and alpaca.cpp?

replies(1): >>35394076 #

2. cubefox ◴[31 Mar 23 21:44 UTC] No.35394076[source]▶

I assume the former is just the foundation model (which only predicts text) while the latter is instruction tuned.

Llama.cpp 30B runs with only 6GB of RAM now