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: add benchmark comparison plot and embed in README
Nandakishor5c5883a42fdc
diff --git a/README.md b/README.mdindex b01e44bd..a0137af0 100644--- a/README.md+++ b/README.md@@ -116,6 +116,10 @@ else:## Benchmark: Laya vs. TypeSafe Jev+<div align="center">+ <img src="assets/benchmark_comparison.png" alt="Laya vs TypeSafe Jev Benchmark" width="900" />+</div>+| Metric / Dimension | TypeSafe Jev (Published) | Laya (Fine-Tuned Checkpoint) | Analysis / Advantage ||---|---|---|---|| **P50 Latency (1 Question)** | ~400 ms avg (70 to 500 ms, 150 ms best) | **38.4 ms** (p95: 42.1 ms) | **Laya is ~10.4x faster on avg (4x faster than Jev best-case)** |diff --git a/assets/benchmark_comparison.png b/assets/benchmark_comparison.pngnew file mode 100644index 00000000..453c2fbbBinary files /dev/null and b/assets/benchmark_comparison.png differ