‹ BackHN Continuity

Thread

Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

575 points · 225 comments · firelex

  1. ijustlovemath · · focus · HN ↗
    Isn't jev just a less nuanced classifier? What am I missing?
    1. neuronexmachina · · focus · HN ↗
      The zero-shot learning is what makes these different from a traditional classifier.
      1. 0x457 · · focus · HN ↗
        Zero-shot just means you give it zero examples. Jev lets you add examples, so it's one-shot/few-shot depending on how many you provide. After playing with it, it seems like once you wonder off their guide examples domains - you have to provide examples to get anything useful from it.

        IMO you going to get better results by doing a small tune of a tiny model. Making training dataset for it with LLMs is easy, serving it is going to be cheaper.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.