Videollama2 72B

🚀 VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

VideoLLaMA 2 is a multimodal large language model that enhances spatial - temporal modeling and audio understanding in video - related tasks, offering solutions for visual question - answering and other video - based applications.

🚀 Quick Start

The project provides model weights, training, evaluation, and serving codes. You can start using it by referring to the inference code example below.

✨ Features

• Multimodal Capability: It is a multimodal large language model, supporting both video and image inference.
• Rich Model Zoo: Offers a variety of model configurations with different language decoders and training frame numbers to meet diverse application needs.

📦 Installation

The original README does not provide specific installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

import sys
sys.path.append('./')
from videollama2 import model_init, mm_infer
from videollama2.utils import disable_torch_init


def inference():
    disable_torch_init()

    # Video Inference
    modal = 'video'
    modal_path = 'assets/cat_and_chicken.mp4' 
    instruct = 'What animals are in the video, what are they doing, and how does the video feel?'
   
    # Image Inference
    modal = 'image'
    modal_path = 'assets/sora.png'
    instruct = 'What is the woman wearing, what is she doing, and how does the image feel?'
    
    model_path = 'DAMO-NLP-SG/VideoLLaMA2-72B'
    model, processor, tokenizer = model_init(model_path)
    output = mm_infer(processor[modal](modal_path), instruct, model=model, tokenizer=tokenizer, do_sample=False, modal=modal)

    print(output)

if __name__ == "__main__":
    inference()

Advanced Usage

The original README does not provide advanced usage examples, so this part is not expanded.

📚 Documentation

📰 News

• [2024.06.12] Release model weights and the first version of the technical report of VideoLLaMA 2.
• [2024.06.03] Release training, evaluation, and serving codes of VideoLLaMA 2.

🌎 Model Zoo

🚀 Main Results

Multi - Choice Video QA & Video Captioning

Open - Ended Video QA

🔧 Technical Details

The original README does not provide specific technical details, so this section is skipped.

📄 License

The project is licensed under the Apache - 2.0 license.

Citation

If you find VideoLLaMA useful for your research and applications, please cite using this BibTeX:

@article{damonlpsg2024videollama2,
  title={VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs},
  author={Cheng, Zesen and Leng, Sicong and Zhang, Hang and Xin, Yifei and Li, Xin and Chen, Guanzheng and Zhu, Yongxin and Zhang, Wenqi and Luo, Ziyang and Zhao, Deli and Bing, Lidong},
  journal={arXiv preprint arXiv:2406.07476},
  year={2024},
  url = {https://arxiv.org/abs/2406.07476}
}
@article{damonlpsg2023videollama,
  title = {Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding},
  author = {Zhang, Hang and Li, Xin and Bing, Lidong},
  journal = {arXiv preprint arXiv:2306.02858},
  year = {2023},
  url = {https://arxiv.org/abs/2306.02858}
}

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

If you like our project, please give us a star ⭐ on Github for the latest update.