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(rust): pin Python calibration bounds independently
kevin-gatimu1af6baa962a3
diff --git a/laya-rust/tests/calibration_tests.rs b/laya-rust/tests/calibration_tests.rsindex e4eb50d7..d61b8a51 100644--- a/laya-rust/tests/calibration_tests.rs+++ b/laya-rust/tests/calibration_tests.rs@@ -34,10 +34,10 @@ fn clamp_temperature_matches_python() {let cases = [(1.0, 1.0),(2.5, 2.5),- (0.1006, Calibration::TEMP_MIN), // the shipped choice:11+ value, refused as too sharp- (0.0, Calibration::TEMP_MIN),- (-3.0, Calibration::TEMP_MIN),- (99.0, Calibration::TEMP_MAX),+ (0.1006, 0.5), // Python's range, not the implementation constants being tested+ (0.0, 0.5),+ (-3.0, 0.5),+ (99.0, 5.0),(f64::NAN, 1.0),(f64::INFINITY, 1.0),(f64::NEG_INFINITY, 1.0),