AnyJev
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)
How it uses Jev
LocalLLaMA/typed-decisions, 20 questions × 300 labels, 2,000 held-out decisions. Pooled ECE 0.03–0.05. Jev 0.727 and fine-tuned Laya 0.768 on the same set, as published by their authors · every cell
- Languages
- Python 100% · Shell 1%
- License
- Apache-2.0
- Latest release
- v0.0.2
- Last activity
- Sep 2026
- Added
- 2026-09-23
- Stars at snapshot
- 440
- Status
- Community listing
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.