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(evals): the guard cites its own file, so cite this branch's numbering
Aashishfe0c2c74cb91
diff --git a/laya/evals.py b/laya/evals.pyindex d969c66c..57dbd57a 100644--- a/laya/evals.py+++ b/laya/evals.py@@ -169,8 +169,8 @@ class Dataset:# whose `expected` names a question `questions` does not carry. A row built in Python with# `Example(...)` skipped all three, and every reader of it takes the two fields as mappings: a# non-object `expected` died as an unhandled ``AttributeError``, in `evaluate` only after the- # runner had answered (`laya/evals.py:1182`), and a non-object `questions` leaked through- # `questions_fingerprint` (`laya/evals.py:262`). An `expected` key with no question behind it+ # runner had answered (`laya/evals.py:1205`), and a non-object `questions` leaked through+ # `questions_fingerprint` (`laya/evals.py:285`). An `expected` key with no question behind it# was answered with "runner returned no answer for question 'x'" -- a verdict about the runner,# paid for with a whole inference run, for a mistake in the caller's row. The two opt-in doors# refused the same rows before calling anything, but as tracebacks