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, putting the model weight under the folder ./video_models/.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.