DeepSeek-VL2

DeepSeek-VL2 is an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models designed for advanced multimodal understanding. It demonstrates superior capabilities across various tasks, including visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. The model series includes three variants with 1 billion, 2.8 billion, and 4.5 billion activated parameters respectively, achieving competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing models.