DeepSeek-VL2

📥 Model Download | ⚡ Quick Start | 📜 License | 📖 Citation
📄 Paper Link | 📄 Arxiv Paper Link | 👁️ Demo

1. Introduction

Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is composed of three variants: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively. DeepSeek-VL2 achieves competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing open-source dense and MoE-based models.

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Zhiyu Wu*, Xiaokang Chen*, Zizheng Pan*, Xingchao Liu*, Wen Liu**, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, Zhenda Xie, Yu Wu, Kai Hu, Jiawei Wang, Yaofeng Sun, Yukun Li, Yishi Piao, Kang Guan, Aixin Liu, Xin Xie, Yuxiang You, Kai Dong, Xingkai Yu, Haowei Zhang, Liang Zhao, Yisong Wang, Chong Ruan*** (* Equal Contribution, ** Project Lead, *** Corresponding author)

2. Release

✅ 2025-2-6: Naive Implemented Gradio Demo on Huggingface Space deepseek-vl2-small.

✅ 2024-12-25: Gradio Demo Example, Incremental Prefilling and VLMEvalKit Support.

✅ 2024-12-13: DeepSeek-VL2 family released, including

3. Model Download

We release the DeepSeek-VL2 family, including

Huggingface

4. Quick Start

Installation

On the basis of

Simple Inference Example with One Image

Note: You may need 80GB GPU memory to run this script with deepseek-vl2-small and even larger for deepseek-vl2.

And the output is something like:

<|User|>: <image>
<|ref|>The giraffe at the back.<|/ref|>.

<|Assistant|>: <|ref|>The giraffe at the back.<|/ref|><|det|>[[580, 270, 999, 900]]<|/det|><｜end▁of▁sentence｜>

Simple Inference Example with Multiple Images

Note: You may need 80GB GPU memory to run this script with deepseek-vl2-small and even larger for deepseek-vl2.

And the output is something like:

<|User|>: This is image_1: <image>
This is image_2: <image>
This is image_3: <image>
 Can you tell me what are in the images?

<|Assistant|>: The images show three different types of vegetables. Image_1 features carrots, which are orange with green tops. Image_2 displays corn cobs, which are yellow with green husks. Image_3 contains raw pork ribs, which are pinkish-red with some marbling.<｜end▁of▁sentence｜>

Simple Inference Example with Incremental Prefilling

Note: We use incremental prefilling to inference within 40GB GPU using deepseek-vl2-small.

And the output is something like:

<|User|>: This is image_1: <image>
This is image_2: <image>
This is image_3: <image>
 Can you tell me what are in the images?

<|Assistant|>: The first image contains carrots. The second image contains corn. The third image contains meat.<｜end▁of▁sentence｜>

Parse the bounding box coordinates, please refer to parse_ref_bbox.

Full Inference Example

Gradio Demo

• Install the necessary dependencies:

• then run the following command:

• Important: This is a basic and native demo implementation without any deployment optimizations, which may result in slower performance. For production environments, consider using optimized deployment solutions, such as vllm, sglang, lmdeploy, etc. These optimizations will help achieve faster response times and better cost efficiency.

5. License

This code repository is licensed under MIT License. The use of DeepSeek-VL2 models is subject to DeepSeek Model License. DeepSeek-VL2 series supports commercial use.

6. Citation

@misc{wu2024deepseekvl2mixtureofexpertsvisionlanguagemodels,
      title={DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding},
      author={Zhiyu Wu and Xiaokang Chen and Zizheng Pan and Xingchao Liu and Wen Liu and Damai Dai and Huazuo Gao and Yiyang Ma and Chengyue Wu and Bingxuan Wang and Zhenda Xie and Yu Wu and Kai Hu and Jiawei Wang and Yaofeng Sun and Yukun Li and Yishi Piao and Kang Guan and Aixin Liu and Xin Xie and Yuxiang You and Kai Dong and Xingkai Yu and Haowei Zhang and Liang Zhao and Yisong Wang and Chong Ruan},
      year={2024},
      eprint={2412.10302},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.10302},
}

7. Contact

If you have any questions, please raise an issue or contact us at service@deepseek.com.