News for hackers. Stuff that matters.
Re:LLaMA: A foundational, 65B-parameter large language model by brucethemoose2 on Friday February 24, 2023 @04:58PM (#34930713)
Requirements could be reduced with something like DeepSpeed or ColossalAI (or even just simple hacks to move bits to RAM more aggressively)

There are no comments on this comment yet.