AgentScope: Agent-Oriented Programming for Building LLM Applications

A fork and successor of the Sulley Fuzzing Framework

MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.

Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"

A Production-Ready Runtime Framework for Agent Deployment and Tool Sandbox

This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"