jev-local
Jev-compatible `POST /v1/systemone` server answering typed `Choice`/`Score`/`Noul` questions with confidence from open weights, verified as an official-SDK drop-in with temperature-fit calibration (set3 n=1316, 0.83 overall).
WHAT IT DECIDES
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
Inferred from this project's own one-line summary in the community list — it reads as a SCORE + NOUL decision. Read the source to confirm.
THE SHAPE OF A SCORE CALL
A generic skeleton for this question type, not this project's actual code.
from typesafe import TypeSafe
ts = TypeSafe()
result = ts.evaluate(
state=candidate,
questions={
"relevance": {
"type": "score",
"levels": ["low", "medium", "high"],
"instructions": "How relevant is this to the query?",
}
},
)
if result["relevance"] >= 0.7:
keep(candidate)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.