A streamlined and customizable framework for efficient large model evaluation and performance benchmarking

MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration

Build Multimodal AI Agents with memory, knowledge and tools. Simple, fast and model-agnostic.

Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

ModelScope: bring the notion of Model-as-a-Service to life.

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)