News for hackers. Stuff that matters.

A comment on Refact LLM: New 1.6B code model reaches 32% HumanEval and is SOTA for the size. Parent comment

Re:Refact LLM: New 1.6B code model reaches 32% HumanEval and... by naillo on Monday September 04, 2023 @03:23PM (#37383967)
7b runs on my 4gb vram machine (8gb memory). I.e. quantization helps a lot too
[ Parent | on HN ]

There are no comments on this comment yet.