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: comprehensive Laya vs Jev benchmark figure
Nandakishor9f64ba65e890
diff --git a/README.md b/README.mdindex f598b17c..63e11dec 100644--- a/README.md+++ b/README.md@@ -12,7 +12,7 @@[](https://opensource.org/licenses/Apache-2.0)<p align="center">- <img src="https://raw.githubusercontent.com/NandhaKishorM/laya/main/assets/laya_vs_jev.png" alt="Laya with routing versus TypeSafe Jev: accuracy on shared public datasets, language coverage, speed and calibration" width="100%" />+ <img src="https://raw.githubusercontent.com/NandhaKishorM/laya/main/assets/laya_vs_jev_full.png" alt="Laya versus TypeSafe Jev: accuracy on shared public datasets, every application workflow, all 51 languages, speed, calibration, and the cost of not preloading" width="100%" /></p>Laya evaluates typed questions (`choice`, `score`, `noul`) over any state (text, email, ticket or JSON document) in **a single forward pass** — 33 ms for one question, 7.2 ms/question batched, measured on a T4. No text generation, so nothing to parse and nothing to hallucinate.diff --git a/assets/laya_vs_jev_full.png b/assets/laya_vs_jev_full.pngnew file mode 100644index 00000000..1ee5007aBinary files /dev/null and b/assets/laya_vs_jev_full.png differ