README.md

metadata

license: apache-2.0
datasets:
  - OpenGVLab/VideoChat2-IT
  - Lin-Chen/ShareGPT4V
  - liuhaotian/LLaVA-Instruct-150K
language:
  - en
metrics:
  - accuracy
library_name: transformers
pipeline_tag: video-text-to-text
tags:
  - multimodal large language model
  - large video-language model

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.

📰 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

Model Name	Type	Visual Encoder	Language Decoder	# Training Frames
VideoLLaMA2-7B-Base	Base	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	8
VideoLLaMA2-7B	Chat	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	8
VideoLLaMA2-7B-16F-Base	Base	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	16
VideoLLaMA2-7B-16F	Chat	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	16
VideoLLaMA2-8x7B-Base	Base	clip-vit-large-patch14-336	Mixtral-8x7B-Instruct-v0.1	8
VideoLLaMA2-8x7B	Chat	clip-vit-large-patch14-336	Mixtral-8x7B-Instruct-v0.1	8
VideoLLaMA2-72B-Base (This checkpoint)	Base	clip-vit-large-patch14-336	Qwen2-72B-Instruct	8
VideoLLaMA2-72B	Chat	clip-vit-large-patch14-336	Qwen2-72B-Instruct	8

🚀 Main Results

Multi-Choice Video QA & Video Captioning

Open-Ended Video QA

🤖 Inference with VideoLLaMA2

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-Base'
    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()

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}
}