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 this https URL .

MobileVLM V2 是在 MobileVLM 的基础上进行显著改进的一系列视觉语言模型，证明了新颖的结构设计、为移动 VLM 量身定制的改进训练方案和优质数据集的精心策划可以显著提高 VLM 的性能。特别是，MobileVLM V2 1.7B 在标准 VLM 基准测试中实现了与规模更大的 3B VLM 相当或更好的性能。值得注意的是，我们的 3B 模型在 7B + 规模的许多 VLM 中表现优秀。我们的模型将在此网址发布。