Skip to the experiment

JevMade hello@JevMade.com

← Back to experiments

Benchmarks & research

qwen-rlcd

By shamazharikh

qwen-rlcd trains Qwen3.5-0.8B to make Jev-style choices, scores, and binary judgments with calibrated confidence.

Source screenshot of qwen-rlcd — SOURCE SCREENSHOT · source ↗ · captured 2026-09-21Full screenshot ↗

GitHub repository ↗

Primitives: choice, score, noul
Platform: Python
Added: Sep 17, 2026
Project created: Sep 16, 2026
GitHub stars: 1 · snapshot 2026-09-18T22:58:45Z

Source checked 2026-09-19 — opened the GitHub repository directly.