---
license: cc-by-4.0
datasets:
- MBZUAI/Video-Instruct-Dataset
language:
- en
library_name: transformers
pipeline_tag: visual-question-answering
---

+ Video-ChatGPT is a large vision-language model with a visual-encoder and large language model (LLM), enabling video understanding and conversation about videos.
+ A simple and scalable multimodal design on top of pretrained visual and language encoders that adapts only a linear projection layer for multimodal alignment.