⬢github Python · 1.3K ★ +2 since we first saw it · pushed 10 d ago · MIT
vinnylarouge/jevlike
Jevlike is a Python project that trains small models that pick one option from a variable-length list of text options in a single forward pass, instead of generating answers token by token. It independently reproduces the input/output shape of TypeSafe's commercial Jev model, providing training, evaluation, and prediction tools, plus demo checkpoints that score game-controller options (Doom buttons, chess keys) from image patches.
Why now: It's trending on GitHub's most-starred new repos, riding interest in TypeSafe's recently announced 'System One' Jev models whose design was never published, so this open starter implementation fills that gap.
Who it is for: ML engineers and researchers who want an open, trainable model for discrete option selection over text (or game inputs) without autoregressive generation.
Stars over our 15 snapshots: 1.3K to 1.3K, since 1 h ago.
Where people talked about it
- ⬢github new repos, most starred 7 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/vinnylarouge/jevlike