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
fix(docs): absolute image URLs so the figure renders on PyPI (v0.3.1)
Nandakishorc36932072f91
diff --git a/README.md b/README.mdindex b5a8c2dd..f72c049c 100644--- a/README.md+++ b/README.md@@ -12,7 +12,7 @@[](https://opensource.org/licenses/Apache-2.0)<p align="center">- <img src="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.png" alt="Laya with routing versus TypeSafe Jev: accuracy on shared public datasets, language coverage, speed and calibration" 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.@@ -244,7 +244,7 @@ router.loaded # ['multilingual']**Full report: [`BENCHMARKS.md`](BENCHMARKS.md)** — every run consolidated, languages and themes, with per-language detail for all 51 languages.<p align="center">- <img src="assets/laya_benchmark.png" alt="Per-language accuracy for both checkpoints across 51 languages" width="100%" />+ <img src="https://raw.githubusercontent.com/NandhaKishorM/laya/main/assets/laya_benchmark.png" alt="Per-language accuracy for both checkpoints across 51 languages" width="100%" /></p>All Laya numbers below are measured. Every model answered byte-identical questionsdiff --git a/assets/laya_vs_jev.png b/assets/laya_vs_jev.pngindex eb8450b7..872f7dad 100644Binary files a/assets/laya_vs_jev.png and b/assets/laya_vs_jev.png differdiff --git a/laya/__init__.py b/laya/__init__.pyindex e2d73141..f7e363a7 100644--- a/laya/__init__.py+++ b/laya/__init__.py@@ -22,7 +22,7 @@ from .presets import ()from .router import DEFAULT_MODELS, RouteDecision, Router-__version__ = "0.3.0"+__version__ = "0.3.1"__all__ = ["Agent","RLAgent",diff --git a/pyproject.toml b/pyproject.tomlindex 065b36c0..4029bc08 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"[project]name = "laya"-version = "0.3.0"+version = "0.3.1"description = "Fast, non-autoregressive System 1 decision engine with calibrated probabilities"readme = "README.md"requires-python = ">=3.8"diff --git a/setup.py b/setup.pyindex dfd246a6..0bbc16c7 100644--- a/setup.py+++ b/setup.py@@ -2,7 +2,7 @@ from setuptools import setup, find_packagessetup(name="laya",- version="0.3.0",+ version="0.3.1",description="Fast, non-autoregressive System 1 decision engine with calibrated probabilities",long_description=open("README.md").read(),long_description_content_type="text/markdown",