GitHub · by Zefan Cai

Open-Jev-27B-v1.1

Typed probabilities from an open 27B model, with no generated JSON.

Zefan Cai's Open-Jev repository now ships Open-Jev-27B-v1.1. You supply a context, questions and candidates and get typed probabilities directly, without autoregressive answer generation and without parsing generated JSON. The repository links a 32-second demo and an interactive replay.

Zefan-Cai/Open-Jev on GitHub

Stars: 396
Forks: 55
Language: Python
Last push: Oct 4, 2026

Repository created Sep 20, 2026. Counts read from the GitHub API on Oct 8, 2026, and they move daily — quote them with the date.

Open the source

CUA-S1-FORMS

Parameters: 706k
Form fill: one 50 ms pass

Vincent Wang-Maścianica

@vinnylarouge

I reverse-engineered a jev-like architecture given its type. You can find the repo here to train your own jevlikes: github.com/vinnylarouge/j…

GitHubOpen source

jevlike

Eric Zhang

@ekzhang1

Inspired by @typesafeai , here is a Jev-compatible public API to play with It runs a comparable open model (Qwen3.6-35B-A3B), and just uses SGLang radix cache to preserve the prefill reuse / really fast parallel systemone generation - 64 tasks in <1s. github.com/ekzhang/openje…