jevlike
build a small model that chooses among a changing list of text options and returns one probability per option in a single pass - the base CUA-S1-FORMS was built on.
何を判断するか
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 CHOICE decision. Read the source to confirm.
CHOICE 呼び出しの形
この質問型の一般的な骨格であって、このプロジェクトの実際のコードではない。
from typesafe import TypeSafe
ts = TypeSafe() # reads TYPESAFE_API_KEY
result = ts.evaluate(
state=page_state,
questions={
"next_action": {
"type": "choice",
"options": ["click", "scroll", "type", "done"],
"instructions": "What should the agent do next?",
}
},
)
action = result["next_action"] # the chosen option
confidence = result["next_action_confidence"]較正と研究の他のプロジェクト
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.