| license: mit | |
| This is the corresponding model for the paper **LVChat: Facilitating Long Video Comprehension** and the code (https://github.com/wangyu-ustc/LVChat). | |
| Please download the file `7b_stage4.pth` with the instructions from the [github](https://github.com/wangyu-ustc/LVChat), putting the model weight under the folder `./video_models/`. | |