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
build(dotnet): require Python 3.12 to record the confidence probe
kevin-gatimu783d69ca4932
diff --git a/laya-dotnet/tools/dump_routing_golden.py b/laya-dotnet/tools/dump_routing_golden.pyindex d1340f57..9d559377 100644--- a/laya-dotnet/tools/dump_routing_golden.py+++ b/laya-dotnet/tools/dump_routing_golden.py@@ -252,6 +252,10 @@ def _gate(answers, threshold):def build_confidence_probe():+ # jev_confidence sums floats; CPython 3.12 made sum() compensated, and the SDKs reproduce that.+ if sys.version_info < (3, 12):+ sys.exit("confidence_probe.json must be recorded with Python 3.12 or later "+ "(sum() of floats is compensated from 3.12 on), got %d.%d" % sys.version_info[:2])scalars = [dict(value=v, **_checked(confidence.check_min_confidence, v)) for v in cc.SCALAR_THRESHOLDS]maps = []