‹ BackHN Continuity

Thread

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

575 points · 225 comments · firelex

  1. m11a · · focus · HN ↗
    It sounds like Jev is not a generative model. If true, I don’t understand these clones which fine-tune a generative model, which appears to not be what Jev is doing.
    1. petesergeant · · focus · HN ↗
      > It sounds like Jev is not a generative model

      Why does it sound like that to you?

    2. blueblazin · · focus · HN ↗
      I think you may be confusing autoregressive and generative. But that can just mean it's a BERT-like encoder model that outputs a single vector for the given input tokens. To make it sound even more "novel" you can say it's a bidirectional encoder-only transformer model which modern LLMs are not and sell that as something revolutionary.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.