Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Using mmap to make LLaMA load faster. Parent comment
So you get the LLaMA weights (somewhere), then apply the Vicuna deltas to them to end up with the Vicuna model.
There are no comments on this comment yet.
So you get the LLaMA weights (somewhere), then apply the Vicuna deltas to them to end up with the Vicuna model.