Brian Li

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

🦦 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.

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.