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
Merge pull request #612 from nefro313/main
Nandakishor6451ab538c14
diff --cc README.mdindex 3574eb9c,e49e1e2e..4666369e--- a/README.md+++ b/README.md@@@ -27,12 -27,9 +27,11 @@@python -m pip install laya```- For TypeScript / Node.js / browser:- ```bash- npm install laya-ts- ```+ With [uv](https://docs.astral.sh/uv/), run `uv add laya` in a uv project or `uv pip install laya` in a virtual environment.- Python 3.10 or newer. Optional extras: `laya[serve]` (HTTP server), `laya[mcp]` (MCP server), `laya[langchain]` (LangChain and LangGraph), `laya[onnx]` (ONNX Runtime), `laya[fast]` (TileLang GPU fast path). See [`laya-ts/`](laya-ts/) for the TypeScript runtime guide. Step-by-step setup for each platform, CPU-only or GPU PyTorch builds, and troubleshooting are in [Installation details](#installation-details).-Python 3.10 or newer. Optional extras: `laya[serve]` (HTTP server), `laya[mcp]` (MCP server), `laya[langchain]` (LangChain and LangGraph), `laya[onnx]` (ONNX Runtime), `laya[fast]` (TileLang GPU fast path). Step-by-step setup for each platform, CPU-only or GPU PyTorch builds, and troubleshooting are in [Installation details](#installation-details).++Python 3.10 or newer. Optional extras: `laya[serve]` (HTTP server), `laya[mcp]` (MCP server), `laya[langchain]` (LangChain and LangGraph), `laya[llamaindex]` (LlamaIndex selectors), `laya[crewai]` (CrewAI routing), `laya[onnx]` (ONNX Runtime), `laya[fast]` (TileLang GPU fast path). Step-by-step setup for each platform, CPU-only or GPU PyTorch builds, and troubleshooting are in [Installation details](#installation-details).++++For TypeScript / Node.js / browser, see [`laya-ts/`](laya-ts/). npm releases (`npm install laya-ts`) are published from this repository's `laya-ts-v*` release tags.**Long documents.** `laya-multilingual` reads up to 8,192 tokens with `max_len=8192`. Measured accuracy and time by document length, reproducible with [`research/scripts/bench_long_context.py`](https://github.com/NandhaKishorM/laya/blob/main/research/scripts/bench_long_context.py):