JevForge
an end-to-end stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, local serving, and a preliminary RLCD baseline.
WHAT IT DECIDES
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
The community list's one-line summary does not say which question type this project uses. Read the source to find out — we would rather leave this blank than guess.
MORE IN Calibration & Research
deciderreproduces the System One shape with a Qwen3.5-2B fine-tune that emits typed decisions with calibrated probabilities in one pass.openjevindependent local preview that answers bilingual probability questions from context, questions, and candidate answers, inspired by TypeSafe Jev.Parallel Constrained Decoding (Qwen2.5-1B-RLCD)RLCD-trained Qwen2.5-1B demo exploring open-source parallel constrained decoding as an alternative to Jev.NanoJeva 0.6B parallel decision model that returns full probability distributions with no output-token decoding, shipped with its training pipeline, weights, and dataset.