Spaces:
Running
on
Zero
Running
on
Zero
Installation
Requirements
We mainly follow UMT to prepare the enviroment.
pip install -r requirements.txt
In addition, in order to support the InternVideo2-6B pre-training, you also need to install Flash Attention and DeepSpeed.
Note
To run InternVideo2 pretraining, you have to prepare the weights of the InternVL-6B visual encoder, and set the your_model_path
in internvl_clip_vision.py.
Key Dependencies Installation for FlashAttention2
Some modules (FusedMLP and DropoutLayerNorm) from FlashAttention2 used in our models rely on CUDA extensions. TBD