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(dotnet): the benchmark writes "typed-decisions", not "typeddecisions"
Adeshina Lasisi42e960cb8ffa
diff --git a/laya-dotnet/samples/Laya.Benchmark/README.md b/laya-dotnet/samples/Laya.Benchmark/README.mdindex 16e64d73..2202e3f2 100644--- a/laya-dotnet/samples/Laya.Benchmark/README.md+++ b/laya-dotnet/samples/Laya.Benchmark/README.md@@ -83,7 +83,7 @@ Exit codes:```jsonc{- "checkpoint": "english", // TypedDecisions is written as "typeddecisions"+ "checkpoint": "english", // the flag spelling: "multilingual", "english", "typed-decisions""runtime": "DotNet + ONNX Runtime","threads": "ORT default","cold_ms": 0.0,