LLaVA
An open vision-language model family built around LLaMA-style backbones for multimodal image-and-text tasks.
Ecosystem
Related Notes
Backfilled from lab-note mentions and entity refresh.
An open vision-language model family built around LLaMA-style backbones for multimodal image-and-text tasks.
Backfilled from lab-note mentions and entity refresh.