‹ BackHN Continuity

Thread

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

575 points · 225 comments · firelex

  1. folayii · · focus · HN ↗
    83.1 vs 83.0 on your panel against 70 vs 94 in someone's actual use case is the whole story with zero-shot classification. Any sense of what the 0.8B does on a phone NPU instead of an M4 Max? That's what decides if it's shippable on device.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.