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(train): initialize target in target_from_expected to avoid UnboundLocalError (#887)
Swatantra Yadav77519e6caa02
diff --git a/laya/train.py b/laya/train.pyindex c29cf9c0..37199cbe 100644--- a/laya/train.py+++ b/laya/train.py@@ -173,6 +173,7 @@ def target_from_expected(q: Dict[str, Any], expected_val: Any,t, crit = q["t"], q["crit"]k = len(render_options(q))idx = None+ target = Noneif t == "choice":keys = list(crit.keys())