minojev
Independent Jev-style replica with head training: a frozen Qwen3-1.7B backbone plus a small trained decision head returns calibrated Choice/Boolean/Score distributions in one forward pass, with committed datasets and a same-backbone generation benchmark.
Decisions, not tokens: minojev reads calibrated, typed probability distributions straight from hidden states in one forward pass — zero output tokens, fully reproducible on a laptop CPU.
How it uses Jev
Most "Jev-style" projects either call a hosted API or fine-tune a whole model. minojev's core is smaller than both:
Getting started
Build the general dataset and run head training with live observability:
- Languages
- Python 56% · HTML 42% · Shell 1%
- License
- MIT
- Last activity
- Sep 2026
- Added
- 2026-09-21
- Stars at snapshot
- 0
- 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.