JevForge
End-to-end Jev-style structured-decision stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, preliminary RLCD, local serving, and interactive replay.
An open training and inference stack for Jev-style decision models. Train models to score dynamic candidate branches from a shared prefix, with support for high-cardinality choice, calibration, and fast batched inference.
How it uses Jev
An end-to-end toolkit for synthesizing decision data, training calibrated candidate scorers, evaluating them, and serving Jev-compatible inference for interactive web decisions.
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.