Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
docs(common): name the k<2 floor confidence_from_probs returns 1.0 at
Aashish099e2589cf07
diff --git a/laya/common.py b/laya/common.pyindex ebf46666..465c5626 100644--- a/laya/common.py+++ b/laya/common.py@@ -804,6 +804,17 @@ def confidence_from_probs(p: np.ndarray, k: int) -> float:How concentrated the whole distribution is. Useful, but not calibrated: it is not whattemperature scaling fits and not what the reported ECE measures. See `answer_confidence`.++ The formula is reported only for ``k >= 2``: ``log(1)`` and ``log(0)`` are zero, so a+ distribution over fewer than two options has no entropy scale to divide by. Those inputs+ return ``1.0``, the *maximum* score this function can produce, whatever ``p`` holds -- an+ empty or single-option question reads as perfectly concentrated, and a caller comparing the+ reported `confidence` against any threshold sees a pass. That is not the same as the+ abstention gate passing it: `laya.confidence` gates on `answer_confidence` first and reaches+ this number only when that field is absent. The gate does pass a real one-option answer, for+ a different reason -- a softmax over one logit is exactly ``[1.0]``, so both numbers are+ ``1.0``. `laya.structured` builds such an answer from ``{"enum": ["solo"]}``, and the option+ count is bounded only above (`MAX_OPTIONS`)."""if k < 2:return 1.0