Qwen 1.5 MoE
Highly efficient mixture-of-expert (MoE) model from Alibaba
2024-04-03

Qwen1.5-MoE-A2.7B is a small mixture-of-expert (MoE) model with only 2.7 billion activated parameters yet matches the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.5-7B.
Qwen 1.5 MoE is a highly efficient mixture-of-experts (MoE) model developed by Alibaba Cloud. With just 2.7 billion activated parameters, it delivers performance comparable to larger 7 billion parameter models like Mistral 7B and Qwen1.5-7B. This compact yet powerful model is part of Alibaba's Qwen series, which includes large language models (LLMs) and multimodal models designed for advanced AI and machine learning tasks. Qwen 1.5 MoE showcases Alibaba's commitment to creating scalable, high-performance AI solutions, making it an ideal choice for applications requiring both efficiency and cutting-edge capabilities. Explore its potential through various demos and integrations offered by the Qwen organization.
Open Source
Artificial Intelligence
GitHub