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(agent): fix predict_long's note on when a window is cut
Som Tripathiebf834aaac50
diff --git a/laya/agent.py b/laya/agent.pyindex 82342ade..d41e4bad 100644--- a/laya/agent.py+++ b/laya/agent.py@@ -1529,8 +1529,7 @@ class Agent(HookRegistry):number of windows that were cut, and the token counts include the overlap), and`truncated_questions` is the last window's list. The two can disagree: when only anearlier window was cut, `truncated` is above 0 and `truncated_questions` is empty. A- window is cut when it is larger than the room a question's head leaves, from a `window`- above the default or a start hook that narrows `max_len` / `head_max_len`. Test+ window is cut when it is larger than the room a question's head leaves. Test`usage["truncated"] > 0` here, not `is True`."""if state is None: