MobileVLM-3B

Model Summery

MobileVLM is a competent multimodal vision language model (MMVLM) targeted to run on mobile devices. It is an amalgamation of a myriad of architectural designs and techniques that are mobile-oriented, which comprises a set of language models at the scale of 1.4B and 2.7B parameters, trained from scratch, a multimodal vision model that is pre-trained in the CLIP fashion, cross-modality interaction via an efficient projector. We evaluate MobileVLM on several typical VLM benchmarks. Our models demonstrate on par performance compared with a few much larger models. More importantly, we measure the inference speed on both a Qualcomm Snapdragon 888 CPU and an NVIDIA Jeston Orin GPU, and we obtain state-of-the-art performance of 21.5 tokens and 65.3 tokens per second, respectively.

The MobileVLM-3B was built on our MobileLLaMA-2.7B-Chat to facilitate the off-the-shelf deployment.

Model Sources

• Repository: https://github.com/Meituan-AutoML/MobileVLM
• Paper: https://arxiv.org/abs/2312.16886

How to Get Started with the Model

Inference examples can be found at Github.

Training Details

Please refer to our paper: MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices