News for hackers. Stuff that matters.

A comment on Could you train a ChatGPT-beating model for $85,000 and run it in a browser?.

Re:Could you train a ChatGPT-beating model for $85,000 and r... by JasonZ2 on Friday March 31, 2023 @02:43PM (#35391451)
Does anyone know how the results from a 7B parameter model with bloomz.cpp (https://github.com/NouamaneTazi/bloomz.cpp) compares to the 7B parameter Alpaca model with llama.cpp (https://github.com/ggerganov/llama.cpp)?

I have the latter working on a M1 Macbook Air with very good results for what it is. Curious if bloomz.cpp is significantly better or just about the same.

[ Parent | on HN ]

There are no comments on this comment yet.