MobileVLM [1] is another recent small multimodal model. They trained their own 1.4B/2.7B LLaMa from scratch using RedPajama and Vicuna instead of leveraging Phi-2.
The papers only have one common benchmark (GQA, MobileVLM scores better) so hard to say how they compare otherwise.
The papers only have one common benchmark (GQA, MobileVLM scores better) so hard to say how they compare otherwise.
[1] https://arxiv.org/abs/2312.16886