mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality

Open paper

Benchmark	Model	Rank	Results
visual-question-answering-vqa-on-3	mPLUG-Owl	#3	Question Pair Acc: 2.36
zero-shot-video-question-answer-on-egoschema-1	mPLUG-Owl (7B)	#26	Accuracy: 31.1