- Python >= 3.10
- Pytorch == 2.0.1
- CUDA Version >= 11.7
- Install required packages:
git clone https://github.com/PKU-YuanGroup/Video-LLaVA
cd Video-LLaVA
conda create -n videollava python=3.10 -y
conda activate videollava
pip install --upgrade pip # enable PEP 660 support
pip install -e .
pip install -e ".[train]"
pip install flash-attn --no-build-isolation
pip install decord opencv-python git+https://github.com/facebookresearch/pytorchvideo.git@28fe037d212663c6a24f373b94cc5d478c8c1a1d
NOTE: If you encounter the following error, please replace the config.json in LanguageBind/Video-LLaVA-7B
with the config.json in this folder.
AttributeError: 'LlavaConfig' object has no attribute 'X'