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.
- Күн бұрын
Cohere For AI - Community Talks: Maya : Multimodal Multilingual ModelMaya
- Рет қаралды 174
Пікірлер