Maya: Multilingual Multimodal model

community

AI & ML interests

we introduce Maya, an open-source Multimodal Multilingual model. 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a novel toxicity-free version across eight languages; and 3) a multilingual image-text 8B model supporting these languages, enhancing culture and linguistics.