MetaQuery Open Source Version Arrives! OpenUni Matches BLIP3-o-8B with 1.1B Parameters, Fully Open Source Data and Code

The article announces the release of the open-source version of MetaQuery, called OpenUni, which features 1.1 billion parameters and rivals the performance of BLIP3-o-8B. This model is fully open source, including data and code, encouraging broader research and development in AI.

OpenUni is designed to improve multimodal understanding, integrating visual and textual data effectively. It aims to foster innovation by providing accessible tools for developers and researchers.

OpenUni Architecture
Performance Comparison
Use Cases

This open-source initiative aims to accelerate AI development by providing transparent and accessible resources, enabling the community to build upon and improve the model further.

Subscribe to QQ Insights

Don’t miss out on the latest issues. Sign up now to get access to the library of members-only issues.
jamie@example.com
Subscribe