全部项目

open-jev-typed-decision-engine

intikhab49/open-jev-typed-decision-engine

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

Python
星标
50
派生
4

收录依据

这是一个独立的 1.5 亿参数状态型问题编码器,README 报告了它与 TypeSafe Jev 的自有基准对比。

相关项目

  • sysone-bench

    First independent head-to-head benchmark of System One decision models (Laya vs Jev) on byte-identical inputs

    共同主题: calibration, decision-model

  • jev-acento

    ¿Jev entiende tu acento? Pre-registered audit of TypeSafe AI's Jev on Spanish — accuracy, calibration and token cost — plus a CLI to run the same comparison on your own labelled data.

    共同主题: calibration, expected-calibration-error

  • jevoss

    Evaluation tools for Jev-compatible decision models, covering accuracy, calibration, hidden instructions, padding and consistency.

    共同主题: calibration, decision-model