A 151M-parameter decision engine based on ModernBERT that outperforms TypeSafe Jev and Laya on LocalLLaMA/typed-decisions with 77.10% accuracy and 0.0636 Brier score, and includes a WebGPU in-browser demo.
该仓库构建并评测了一个基于 ModernBERT 的非自回归决策引擎，在 LocalLLaMA/typed-decisions 基准上与 TypeSafe Jev 1.13.0 对比，受 Jev 架构启发，并提供 WebGPU 可运行 demo，属于对 TypeSafe Jev 模型的深入研究。
JevalsJevals/jevals-dataIndependent benchmark data comparing TypeSafe AI's Jev (System One model) against LLMs on decision score, accuracy, calibration, cost, and latency for typed tasks.
NearCaiNearCai/JevLightA CityFlow-based traffic signal control framework that evaluates TypeSafe Jev and OpenAI-compatible LLM controllers alongside rule-based and reinforcement-learning baselines through the same simulation pipeline.
choxoschoxos/jev-reviewerUses TypeSafe AI's Jev/System One model (jev-1.13.0) to locate verbatim evidence in trial reports and supplements, supporting RoB 2, ROBINS-I, QUADAS-2 templates; files are processed locally in the browser.
