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
fix(calibrate): run records_from_labeled with gradients off
abhijithneilabraham6bbb952f5713
diff --git a/laya/calibrate.py b/laya/calibrate.pyindex 3906a5fe..9be53521 100644--- a/laya/calibrate.py+++ b/laya/calibrate.py@@ -258,6 +258,7 @@ def fit_temperature_map(records: Iterable, compute_ece: bool = False, seed: intfit_temperatures = fit_temperature_map[email protected]_grad()def records_from_labeled(agent, pairs: Sequence) -> List[Record]:"""Collect CPU records from `(state, questions, targets)`.