Maya - Multimodal Multilingual Model

The Maya project was recognized as the most promising initiative in the six-week Aya Expedition. In this session, Nahid Alam, Karthik Reddy and Surya Guthikonda will discuss their process for creating the pretraining dataset and training the model using SigLIP as the vision encoder and Aya 23 8b as the language model. As the project is in its early stages, they are actively seeking contributors. If you're interested in joining the team, feel free to reach out to either of them.

This session is brought to you by the Cohere For AI Open Science Community - a space where ML researchers, engineers, linguists, social scientists, and lifelong learners connect and collaborate with each other. Thank you to our Community Leads for organizing and hosting this event.