Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Llama2.c: inference llama 2 in one file of pure C. Parent comment
I like the sound of that!
I don't know the answer but I might experiment with it. Probably a researcher has tried it.
You would need N times the compute per token generate of course.
You could either pick to N, or sample N (with temperature adjustment to logits if needed)
There are no comments on this comment yet.
I like the sound of that!
I don't know the answer but I might experiment with it. Probably a researcher has tried it.
You would need N times the compute per token generate of course.
You could either pick to N, or sample N (with temperature adjustment to logits if needed)