| ▲ | Der_Einzige 15 hours ago | |
We got an oral at ICLR for calling out how shit samplers like top_p and top_k are. Use min_p! | ||
| ▲ | moffkalast 10 hours ago | parent [-] | |
True yep, I wish more people benchmarked models with more representative sampler settings and then took the average of 5 or 10 responses. | ||