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): a split export may ship .data sidecars, so do not call it self-contained
Adeshina Lasisif1a436d67dde
diff --git a/laya-dotnet/README.md b/laya-dotnet/README.mdindex 02df368a..c74fc58b 100644--- a/laya-dotnet/README.md+++ b/laya-dotnet/README.md@@ -72,10 +72,11 @@ using Laya;This SDK runs **ONNX** models (opset 18), in either of two artifact layouts. The**fused** layout — this repo's own `export_onnx.py` — is a `model.onnx` graph with its weights ina `model.onnx.data` sidecar beside it, plus `rl_agent_config.json` and `tokenizer/`. The-**split** layout — produced by `laya-ts`'s exporter — is a self-contained `encoder.onnx` and-`head.onnx` pair with no external-data sidecar, plus the same `rl_agent_config.json` and a-root-level `tokenizer.json`. No Python is needed at runtime for either; Python (or, for the split-layout, `laya-ts`) is used once, to export the model from the published PyTorch checkpoint.+**split** layout — produced by `laya-ts`'s exporter — is an `encoder.onnx` and `head.onnx`+pair, each with its own `.data` sidecar when that graph's weights exceed the protobuf limit,+plus the same `rl_agent_config.json` and a root-level `tokenizer.json`. No Python is needed at+runtime for either; Python (or, for the split layout, `laya-ts`) is used once, to export the+model from the published PyTorch checkpoint.The engine auto-detects which layout a directory holds — nothing in the API asks you to chooseone. Point it at a checkpoint directory with `LayaEngine.FromDirectory(...)`,