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(langchain): name the long-document case for the state budget too
Aashish9022fceb29ec
diff --git a/docs/langchain.md b/docs/langchain.mdindex 66c3ad48..1c058cca 100644--- a/docs/langchain.md+++ b/docs/langchain.md@@ -188,7 +188,10 @@ roughly 20 options every label is trimmed to fit and similar labels start reachisame text. See the README's [Honest limits](https://github.com/NandhaKishorM/laya#honest-limits)for the same effect measured on Banking77.-A routing node with many branches is the common case, and it had no way to ask for more room:+Two situations call for it. A routing node with many branches overflows the *option* budget, and+a long document overflows the *state* budget -- the README's own long-document guidance is literally+`router.predict(long_document, questions, model="multilingual", max_len=8192)`, which until now was+unspeakable from a chain step. Both go through the same two arguments:```pythonrouter = LayaRouter(