Introducing Maya – A New Multimodal Multilingual Vision-Language Model. Maya is a completely open source, open weight, and open dataset, designed to handle 8 languages, cultural diversity, and nuanced real-world contexts in vision-language models.
Paper: https://arxiv.org/abs/2412.07112
Paper: https://arxiv.org/abs/2412.07112
Comments
Hugging Face: https://huggingface.co/maya-multimodal
Code: https://github.com/nahidalam/maya/
Thanks to Cohere for AI as well for supporting us.