CalibratedDecisions.

Repo · Benchmarks & research

jevalt

Open Jev-API–compatible Choice/Score/Noul models (EN/TR/DE) for CPU (~4 GB RAM); independent of hosted Jev.

Open github.com ↗

From the repository

Three small 4B language models for local decisions in English, Turkish and German. Jev-compatible API, per-option probabilities and CPU GGUF builds.

calibrationdecision-modelgermanggufjevllama-cpplocal-llmmultilingualopen-weightsprompt-injectionpythonsmall-language-modeltext-classificationturkishuncertainty-quantification

How builders describe it

Open alternative to Jev, Kev and Laya: three 4B decision models (English, Turkish, German) that answer typed questions with calibrated probabilities. Jev API compatible, runs on a CPU in about 3 GB of RAM.

The decision Jev makes

Benchmark questions with known answers, to check accuracy and confidence.

Where it fits

Head-to-head tests, calibration studies and independent research into how well Jev decides, how fast, and at what cost. All 682 benchmarks & research projects →

Related projects