Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
Why do you think that https://github.com/sshh12/multi_token is a good alternative to MGM
Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
Why do you think that https://github.com/sshh12/multi_token is a good alternative to MGM