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
chore: bump version to 0.1.3 and update docs with new HF repo
Nandakishor3d4826a78ee5
diff --git a/README.md b/README.mdindex 8e2e433e..33f0549d 100644--- a/README.md+++ b/README.md@@ -2,9 +2,15 @@Fast, non-autoregressive System 1 decision engine with mathematically calibrated probabilities.+[](https://pypi.org/project/laya/)+[](https://huggingface.co/convaiinnovations/laya)+[](https://huggingface.co/spaces/convaiinnovations/laya-demo)+[](https://www.buymeacoffee.com/nandakishorm)+[](https://opensource.org/licenses/Apache-2.0)+Laya lets you evaluate typed questions (`choice`, `score`, `noul`) over any state (text, email, ticket, or JSON document) in **a single forward pass (~33–38 ms on GPU)**. It produces structured decision outputs and calibrated confidence scores without text generation, token streaming, or hallucinations.-Compatible with [RL Agent models on Hugging Face](https://huggingface.co/convaiinnovations/rl-agent).+Powered by the fine-tuned [Laya model on Hugging Face](https://huggingface.co/convaiinnovations/laya).---@@ -21,8 +27,8 @@ pip install laya```pythonimport laya-# 1. Load the model from Hugging Face Hub (auto-downloads weights)-agent = laya.load("convaiinnovations/rl-agent")+# 1. Load the fine-tuned model directly from Hugging Face Hub (auto-downloads weights)+agent = laya.load("convaiinnovations/laya")# 2. Provide any state (string or dictionary)state = {@@ -104,17 +110,29 @@ else:|---|---|---|| **`choice`** | Top label, probabilities per option, confidence | Department routing, intent classification, topic categorization || **`score`** | Expected level on ordinal rubric, distribution, confidence | Frustration level, ticket urgency, harm severity |-| **`noul`** | Calibrated probability $P(\text{true}) \in [0.0, 1.0]$ | Phishing detection, spam filtering, jailbreak detection, churn risk |+| **`noul`** | Calibrated probability P(true) from 0.0 to 1.0 | Phishing detection, spam filtering, jailbreak detection, churn risk |---## Live Demo & Resources-* **Hugging Face Model:** [convaiinnovations/rl-agent](https://huggingface.co/convaiinnovations/rl-agent)+* **Hugging Face Model:** [convaiinnovations/laya](https://huggingface.co/convaiinnovations/laya)* **Interactive Web Demo:** [convaiinnovations/laya-demo](https://huggingface.co/spaces/convaiinnovations/laya-demo)---+## Support the Project++If Laya helps your research or products, consider supporting independent research:++<p align="left">+ <a href="https://www.buymeacoffee.com/nandakishorm" target="_blank">+ <img src="https://img.buymeacoffee.com/button-api/?text=Buy%20me%20a%20coffee&emoji=&slug=nandakishorm&button_colour=FFDD00&font_colour=000000&font_family=Cookie&outline_colour=000000&coffee_colour=ffffff" alt="Buy Me A Coffee" />+ </a>+</p>++---+## LicenseApache 2.0. Developed by Convai Innovations.diff --git a/laya/__init__.py b/laya/__init__.pyindex 32e7d586..e775a88e 100644--- a/laya/__init__.py+++ b/laya/__init__.py@@ -3,7 +3,7 @@from .agent import Agent, RLAgent, loadfrom .email import clean_email_body, email_questions, email_state-__version__ = "0.1.2"+__version__ = "0.1.3"__all__ = ["Agent","RLAgent",diff --git a/laya/agent.py b/laya/agent.pyindex 9ed840c3..656c2460 100644--- a/laya/agent.py+++ b/laya/agent.py@@ -88,7 +88,7 @@ class Agent:def __init__(self,- model_id_or_path: str = "convaiinnovations/rl-agent",+ model_id_or_path: str = "convaiinnovations/laya",device: Optional[str] = None,token: Optional[str] = None,):@@ -293,6 +293,6 @@ class Agent:RLAgent = Agent-def load(model_id_or_path: str = "convaiinnovations/rl-agent", device: Optional[str] = None, token: Optional[str] = None) -> Agent:+def load(model_id_or_path: str = "convaiinnovations/laya", device: Optional[str] = None, token: Optional[str] = None) -> Agent:"""Helper function to load a Laya agent model."""return Agent(model_id_or_path, device=device, token=token)diff --git a/pyproject.toml b/pyproject.tomlindex 036f6fa2..55147601 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"[project]name = "laya"-version = "0.1.2"+version = "0.1.3"description = "Fast, non-autoregressive System 1 decision engine with calibrated probabilities"readme = "README.md"requires-python = ">=3.8"@@ -34,5 +34,5 @@ dependencies = [][project.urls]-Homepage = "https://huggingface.co/convaiinnovations/rl-agent"+Homepage = "https://huggingface.co/convaiinnovations/laya"Demo = "https://huggingface.co/spaces/convaiinnovations/laya-demo"diff --git a/setup.py b/setup.pyindex cc768e5f..65cb5c34 100644--- a/setup.py+++ b/setup.py@@ -2,7 +2,7 @@ from setuptools import setup, find_packagessetup(name="laya",- version="0.1.2",+ version="0.1.3",description="Fast, non-autoregressive System 1 decision engine with calibrated probabilities",long_description=open("README.md").read(),long_description_content_type="text/markdown",