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
test(dotnet): regenerate binning wide-int probe rows after #1440
Nandakishord3b04653aba4
diff --git a/laya-dotnet/tests/Laya.Tests/golden/routing/calibration_probe.json b/laya-dotnet/tests/Laya.Tests/golden/routing/calibration_probe.jsonindex 66d31e0d..cd377468 100644--- a/laya-dotnet/tests/Laya.Tests/golden/routing/calibration_probe.json+++ b/laya-dotnet/tests/Laya.Tests/golden/routing/calibration_probe.json@@ -4324,8 +4324,8 @@}}},- "error_type": "OverflowError",- "error_message": "int too large to convert to float",+ "error_type": "ValueError",+ "error_message": "calibration JSON binning_map['choice:3-5'] values must be numbers, got [0.5, 10000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000]","warnings": []},{@@ -4374,8 +4374,8 @@}}},- "error_type": "OverflowError",- "error_message": "int too large to convert to float",+ "error_type": "ValueError",+ "error_message": "calibration JSON binning_map['choice:3-5'] values must be numbers, got [10000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000, None, 0.5]","warnings": []},{