DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including x86 and ARMv9.

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

ms-swift: Use PEFT or Full-parameter to finetune 300+ LLMs or 50+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3, Llava-Video, Internvl2, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

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