Language Is Not All You Need: Aligning Perception with Language Models

Benchmark Model Rank Results
question-answering-on-boolqKOSMOS-1 (4-shot)#107Accuracy: 59.2
question-answering-on-piqaKOSMOS-1 (0-shot)#135Accuracy: 72.9
common-sense-reasoning-on-winograndeKOSMOS-1 (4-shot)#148Accuracy: 55.7
sentence-completion-on-hellaswagKOSMOS-1 (4-shot)#180Accuracy: 50.3