News for hackers. Stuff that matters.

A comment on Falcon LLM – A 40B Model. Parent comment

Re:Falcon LLM – A 40B Model by logicchains on Sunday June 18, 2023 @12:01AM (#36377196)
llama.cpp just got Falcon support (not yet merged), so you could run it on just RAM. Not too fast though.
[ Parent | on HN ]
Re:Falcon LLM – A 40B Model by gardnr on Sunday June 18, 2023 @02:03AM (#36377719)
In case anyone wants to follow along: https://github.com/ggerganov/llama.cpp/issues/1602
[ Parent | on HN ]