README.md

---
license: apache-2.0
datasets:
- lmms-lab/ClothoAQA
- Loie/VGGSound
language:
- en
metrics:
- accuracy
pipeline_tag: visual-question-answering
library_name: transformers
tags:
- Audio-visual Question Answering
- Audio Question Answering
- multimodal large language model
---


<p align="center">
    <img src="https://cdn-uploads.huggingface.co/production/uploads/63913b120cf6b11c487ca31d/ROs4bHIp4zJ7g7vzgUycu.png" width="150" style="margin-bottom: 0.2;"/>
<p>


<h3 align="center"><a href="https://arxiv.org/abs/2406.07476">VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs</a></h3>
<h5 align="center"> If you like our project, please give us a star ⭐ on <a href="https://github.com/DAMO-NLP-SG/VideoLLaMA2">Github</a> for the latest update.  </h2>

<p align="center"><video src="https://cdn-uploads.huggingface.co/production/uploads/63913b120cf6b11c487ca31d/Wj7GuqQ0CB9JRoPo6_GoH.webm" width="800"></p>

## 📰 News
* **[2024.10.22]**  Release checkpoints of [VideoLLaMA2.1-7B-AV](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-AV)
* **[2024.10.15]**  Release checkpoints of [VideoLLaMA2.1-7B-16F-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-16F-Base) and [VideoLLaMA2.1-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-16F)
* **[2024.08.14]**  Release checkpoints of [VideoLLaMA2-72B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B-Base) and [VideoLLaMA2-72B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B)
* **[2024.07.30]**  Release checkpoints of [VideoLLaMA2-8x7B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B-Base) and [VideoLLaMA2-8x7B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B).
* **[2024.06.25]**  🔥🔥 As of Jun 25, our [VideoLLaMA2-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B-16F) is the **Top-1** ~7B-sized VideoLLM on the [MLVU Leaderboard](https://github.com/JUNJIE99/MLVU?tab=readme-ov-file#trophy-mini-leaderboard).
* **[2024.06.18]**  🔥🔥 As of Jun 18, our [VideoLLaMA2-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B-16F) is the **Top-1** ~7B-sized VideoLLM on the [VideoMME Leaderboard](https://video-mme.github.io/home_page.html#leaderboard).
* **[2024.06.17]**  👋👋 Update technical report with the latest results and the missing references. If you have works closely related to VideoLLaMA 2 but not mentioned in the paper, feel free to let us know.  
* **[2024.06.14]**  🔥🔥 [Online Demo](https://huggingface.co/spaces/lixin4ever/VideoLLaMA2) is available.
* **[2024.06.03]**  Release training, evaluation, and serving codes of VideoLLaMA 2.


## 🌎 Model Zoo
### Vision-Only Checkpoints
| Model Name     | Type | Visual Encoder | Language Decoder | # Training Frames |
|:-------------------|:--------------:|:----------------|:------------------|:----------------------:|
| [VideoLLaMA2-7B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B-Base)  | Base  | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)  | 8 |
| [VideoLLaMA2-7B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B)  | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)  | 8 |
| [VideoLLaMA2-7B-16F-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base)  | Base  | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)  | 16 |
| [VideoLLaMA2-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B-16F)  | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)  | 16 |
| [VideoLLaMA2-8x7B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B-Base)  | Base | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)  | 8 |
| [VideoLLaMA2-8x7B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-8x7B)  | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)  | 8 |
| [VideoLLaMA2-72B-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B-Base)  | Base | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)  | 8 |
| [VideoLLaMA2-72B](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-72B)  | Chat | [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | [Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct)  | 8 |
| [VideoLLaMA2.1-7B-16F-Base](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-16F-Base)  | Base | [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) | [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)  | 16 |
| [VideoLLaMA2.1-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-16F)  | Chat | [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) | [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)  | 16 |

### Audio-Visual Checkpoints
| Model Name     | Type | Audio Encoder | Language Decoder |  
|:-------------------|:--------------:|:----------------|:----------------------:|  
| [VideoLLaMA2.1-7B-AV](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-AV) (**This Checkpoint**)  | Chat | [Fine-tuned BEATs_iter3+(AS2M)(cpt2)](https://1drv.ms/u/s!AqeByhGUtINrgcpj8ujXH1YUtxooEg?e=E9Ncea) | [VideoLLaMA2.1-7B-16F](https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-16F)  |


## 🚀 Main Results

### Multi-Choice Video QA & Video Captioning
<p><img src="https://cdn-uploads.huggingface.co/production/uploads/63913b120cf6b11c487ca31d/Z81Dl2MeVlg8wLbYOyTvI.png" width="800" "/></p>

###  Open-Ended Video QA
<p><img src="https://cdn-uploads.huggingface.co/production/uploads/63913b120cf6b11c487ca31d/UoAr7SjbPSPe1z23HBsUh.png" width="800" "/></p>

### Multi-Choice & Open-Ended Audio QA 
<p><img src="https://huggingface.co/YifeiXin/xin/resolve/main/VideoLLaMA2-audio.png" width="800" "/></p>

### Open-Ended Audio-Visual QA 
<p><img src="https://huggingface.co/YifeiXin/xin/resolve/main/VideoLLaAM2.1-AV.png" width="800" "/></p>



## 🤖 Inference with VideoLLaMA2-AV
```python
import sys
sys.path.append('./')
from videollama2 import model_init, mm_infer
from videollama2.utils import disable_torch_init
import argparse

def inference(args):

    model_path = args.model_path
    model, processor, tokenizer = model_init(model_path)

    if args.modal_type == "a":
        model.model.vision_tower = None
    elif args.modal_type == "v":
        model.model.audio_tower = None
    elif args.modal_type == "av":
        pass
    else:
        raise NotImplementedError
    # Audio-visual Inference
    audio_video_path = "assets/00003491.mp4"
    preprocess = processor['audio' if args.modal_type == "a" else "video"]
    if args.modal_type == "a":
        audio_video_tensor = preprocess(audio_video_path)
    else:
        audio_video_tensor = preprocess(audio_video_path, va=True if args.modal_type == "av" else False)
    question = f"Please describe the video with audio information."

    # Audio Inference
    audio_video_path = "assets/bird-twitter-car.wav"
    preprocess = processor['audio' if args.modal_type == "a" else "video"]
    if args.modal_type == "a":
        audio_video_tensor = preprocess(audio_video_path)
    else:
        audio_video_tensor = preprocess(audio_video_path, va=True if args.modal_type == "av" else False)
    question = f"Please describe the audio."

    # Video Inference
    audio_video_path = "assets/output_v_1jgsRbGzCls.mp4"
    preprocess = processor['audio' if args.modal_type == "a" else "video"]
    if args.modal_type == "a":
        audio_video_tensor = preprocess(audio_video_path)
    else:
        audio_video_tensor = preprocess(audio_video_path, va=True if args.modal_type == "av" else False)
    question = f"What activity are the people practicing in the video?"

    output = mm_infer(
        audio_video_tensor,
        question,
        model=model,
        tokenizer=tokenizer,
        modal='audio' if args.modal_type == "a" else "video",
        do_sample=False,
    )

    print(output)


if __name__ == "__main__":
    parser = argparse.ArgumentParser()

    parser.add_argument('--model-path', help='', , required=False, default='DAMO-NLP-SG/VideoLLaMA2.1-7B-AV')
    parser.add_argument('--modal-type', choices=["a", "v", "av"], help='', required=True)
    args = parser.parse_args()

    inference(args)

```


## Citation

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