MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Xiangxiang Chu, Limeng Qiao, Xinyu Zhang, Shuang Xu, Wei, Fei, Yang, Yang, Xiaofei Sun, Yi-Ming Hu, Xinyang Lin, Bo Zhang, Chunhua Shen · arXiv (Cornell University) · 2024
We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/MobileVLM .