Community questions distinguish decision models from existing re-rankers
5 Sep 25 4:12 PM · 2d ago · 2 comments · 1 source · development 5 of 9
Developers debate whether decision models are genuinely novel or simply re-branded re-rankers with better probability calibration, with questions raised about what differentiates them architecturally.
TypeSafe Creator of Jev decision modelOllaya maintainers Open-source implementation leadsTinyJev maintainers Open-source implementation leadsValen authors Multimodal extension developers
The whole story postscomments the bright band is this development · numbered dots are the others · click one to jump
What people said 2 voices · verbatim
-
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?
-
It would be really cool to have LLMs and System One in a single tool - in this case, if Ollama implemented it.
All 9 developments of Open-source Jev clones proliferate weeks after TypeSafe's… →
Hacker NewsMastodonNewswiresLobsters