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
docs(readme): name all six ports in the Vietnamese entry
Nandakishorfe9a6c35023a
diff --git a/README.md b/README.mdindex 5e171ca0..440aca13 100644--- a/README.md+++ b/README.md@@ -97,8 +97,9 @@ The shipped checkpoints work zero-shot, but fine-tuning on decisions from your o## What's new in 0.4.17* **Vietnamese stops routing to the English checkpoint.** Its tone-marked vowels now count as- non-English diacritics, in `laya/lang.py` and the TypeScript port together, with the Java, Go- and C++ tables re-recorded from the same source (#1392).+ non-English diacritics. "Cảm ơn bạn nhiều nhé" scored a diacritic rate of 0.0 and read as+ English. Fixed in `laya/lang.py` and carried into all six ports: TypeScript, Rust and .NET+ directly, and the Java, Go and C++ tables re-recorded from the same source (#1392).* **A deciding window keeps its attribution after end hooks.** `predict_long` attributed answersby position, so an end hook that reordered results reported the wrong token span withoutsaying so (#1369).