chenjoya/videollm-online-8b-v1plus

Model Card for Model ID

https://showlab.github.io/videollm-online/

Model Details

• LLM: meta-llama/Meta-Llama-3-8B-Instruct
• Vision Strategy:
  • Frame Encoder: google/siglip-large-patch16-384
  • Frame Tokens: CLS Token + Avg Pooled 3x3 Tokens
  • Frame FPS: 2 for training, 2~10 for inference
  • Frame Resolution: max resolution 384, with zero-padding to keep aspect ratio
  • Video Length: 10 minutes
• Training Data: Ego4D Narration Stream 113K + Ego4D GoalStep Stream 21K

Model Sources

• Repository: https://github.com/showlab/videollm-online
• Paper: https://arxiv.org/abs/2406.11816

Uses

• First, clone the github repository and follow the installation instruction:

git clone https://github.com/showlab/videollm-online

Ensure you have Miniconda and Python version >= 3.10 installed, then run:

conda install -y pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
pip install transformers accelerate deepspeed peft editdistance Levenshtein tensorboard gradio moviepy submitit
pip install flash-attn --no-build-isolation

PyTorch source will make ffmpeg installed, but it is an old version and usually make very low quality preprocessing. Please install newest ffmpeg following:

wget https://johnvansickle.com/ffmpeg/releases/ffmpeg-release-amd64-static.tar.xz
tar xvf ffmpeg-release-amd64-static.tar.xz
rm ffmpeg-release-amd64-static.tar.xz
mv ffmpeg-7.0.1-amd64-static ffmpeg

If you want to try our model with the audio in real-time streaming, please also clone ChatTTS.

pip install omegaconf vocos vector_quantize_pytorch cython
git clone git+https://github.com/2noise/ChatTTS
mv ChatTTS demo/rendering/

• Launch the gradio demo locally with:

python -m demo.app --resume_from_checkpoint chenjoya/videollm-online-8b-v1plus

• Or launch the CLI locally with:

python -m demo.cli --resume_from_checkpoint chenjoya/videollm-online-8b-v1plus

Citation

@inproceedings{videollm-online,
  author       = {Joya Chen and Zhaoyang Lv and Shiwei Wu and Kevin Qinghong Lin and Chenan Song and Difei Gao and Jia-Wei Liu and Ziteng Gao and Dongxing Mao and Mike Zheng Shou},
  title        = {VideoLLM-online: Online Video Large Language Model for Streaming Video},
  booktitle    = {CVPR},
  year         = {2024},
}