Luodian / Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
https://otter-ntu.github.io/
MIT License
3.56k stars 242 forks source link

[Demo/Model/Doc] add MIMIC-IT download link and Convert-IT code, fix bugs in local inference demo #153

Closed king159 closed 1 year ago

king159 commented 1 year ago

Convert original images/videos/3d scenes into base64.json