すべてのプロジェクト

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
スター
50
フォーク
4

掲載理由

独立した1.5億パラメーターの状態・型付き質問エンコーダーで、READMEはTypeSafe Jevとの独自ベンチマーク比較を報告している。

関連プロジェクト

  • sysone-bench

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

    共通トピック: 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.

    共通トピック: calibration, expected-calibration-error

  • jevoss

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

    共通トピック: calibration, decision-model