Y
Hacker News
new
|
ask
|
show
|
jobs
by
Der_Einzige
415 days ago
We got an oral at ICLR for calling out how shit samplers like top_p and top_k are. Use min_p!
1 comments
moffkalast
415 days ago
True yep, I wish more people benchmarked models with more representative sampler settings and then took the average of 5 or 10 responses.
link