YHK - yet another hacker news clone

Ollaya – Ollama for open-source, Jev-style decision models

32 points Ardakilic 34 minutes ago 16 comments

datadrivenangel 21 minutes ago | parent

Are there many models that are comparable to Jev for generic decision making?

Smarter move if you have an eval set is to just train a classifier and call it a day.

rgbrgb 16 minutes ago | parent

there's this thing with a bunch of similar models https://huggingface.co/spaces/multimodalart/jev-decision-ind...

top open one is trained by perplexity cto for $3k, kinda cool https://x.com/denisyarats/status/2102252088067850507

emmettbt 17 minutes ago | parent

Cool... but this does seem undermined by the fact that Ollama can add support for decision models at any time.

eserozvataf 13 minutes ago | parent

great project for empowering open-source alternatives.

rkovashikawa 2 minutes ago | parent

open-source is the only way for safe AI development. whoever doesn’t share the weights/code will lag behind.

ranyume 12 minutes ago | parent

>Run decision models locally.

>example is a text classification task instead of a decision

cobanov 2 minutes ago | parent

Fair point, that example is basically classification. I'll change it to something that looks more like a real decision.

george_max 12 minutes ago | parent

I am fairly confident if Jev-style decision models are seen as prominent (which, they seem to be), Ollama will support them. Surprised the team hasn't implemented this already.

handfuloflight 12 minutes ago | parent

Sounds good on latency but how is its actual decision quality vs. Jev?

george_max 8 minutes ago | parent

Has anyone actually seen better or the same results with Laya compared to Jev? From my experience, Laya performs significantly worse. It's less confident and often makes wrong decisions with more complex queries.

cobanov 2 minutes ago | parent

Developer here. You're right, Laya is a lot weaker than Jev, especially on harder queries. It's a small model, so it's fast, but that's the trade-off. The open models that get close to Jev are much bigger, and running those is what I'm working on next.

scronkfinkle 2 minutes ago | parent

Yes. JEV generalizes better because they probably have an enormous corpus and trained on it for a long time. Laya's out of the box model is much weaker. However, in the age of LLM's it's incredibly easy and cheap to generate large datasets to fine tune laya for your task, and the training loop is pretty quick and cheap too.

It's so easy that I question why I would ever pay for JEV when eventually I'll have done enough random things that I will also have a large corpus and likely a general model as well.