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.
OWNER
vinnylarouge
INDUSTRY
Training library
CATEGORY
Calibration & Research
KIND
REPO
HOST
github.com
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 CHOICE decision. Read the source to confirm.
THE SHAPE OF A CHOICE CALL
A generic skeleton for this question type, not this project's actual code.
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"]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.