Cohere Unveils Aya Vision: A Multilingual, Multimodal AI Model

Cohere For AI has introduced Aya Vision, an open-weight AI model designed to enhance multilingual and multimodal capabilities, announced on their website. Aya Vision supports 23 languages, aiming to bridge the gap in AI performance across different languages, particularly in tasks involving both text and images.

Aya Vision is available in two versions, 8-billion and 32-billion parameters, and can perform tasks such as image captioning, visual question answering, and text translation. The model is accessible for non-commercial use on platforms like Hugging Face and WhatsApp, allowing researchers and developers to explore its capabilities without commercial constraints.

Cohere emphasizes the model's efficiency, noting that Aya Vision outperforms larger models in various benchmarks. This is achieved through innovations like synthetic annotations and multimodal model merging, which enhance the model's understanding and performance across multiple languages. Aya Vision's release marks a significant step in making advanced AI technologies more accessible to the global research community.