Thread

1. alex7o · 1790367128 · focus · HN ↗

   Guys I have a real q, what is the difference between an instruct based re-ranker and laya/jev I just don't see it.

   Edit: One is that jev/laya are tuned to have better probabilities, but a reranker can be fine tuned to do that as well. And jev/laya use RLCD?

   1. avereveard · 1790368261 · focus · HN ↗

      Calibrated probability across multi task with zero shot I guess. A reranker is single task and tuning it make it even more narrow. And I guess some piping to make multiclass efficient since you cannot mask logprob for independent questions in the same output space without throwing calibration away.

      1. alex7o · 1790407428 · focus · HN ↗

         If you mean that I can compare the probilities between different tasks fair. This is a thing you can not do with a reranker. This sounds cool but not the amount of hype we got cool

Unofficial Hacker News client; not affiliated with Y Combinator.