Skywork / SkyworkVL-2B

SkyworkVL-2B: Multimodal Understanding with Bag of Tricks

Introduction

SkyworkVL-2B is an advanced VLM model trained on 2 million high-quality caption and QA data samples. Leveraging innovative techniques across multiple training stages, our model delivers superior performance on a range of vision-language tasks.

🔑 Key Features

1. Multi-Resolution Processing

• Images are processed at multiple resolutions. For each resolution (from high to low), we apply Closest Aspect Ratio Matching to partition the image into tiles. Finally, the original image is resized into a tile and appended to the final representation—ensuring comprehensive image understanding.

2. Multi-Stage Supervised Fine-Tuning (SFT)

• Stage 1: Fine-tuning on the full dataset.
• Stage 2: Refinement using a curated subset of 200K high-scoring samples filtered by GPT-4 evaluations.

3. High-Quality Chain-of-Thought (CoT) Fine-Tuning

• Fine-tuning on 40K high-quality CoT data including self-collected multimodal Chinese Gaokao data with detailed analysis to boost the model’s reasoning capability.

Model Introduction

Performance

The performance improvements above demonstrate notable gains in multi-disciplinary question answering, object detection (BBox), and scientific chart analysis among other benchmarks.

Usage

Please refer to the Guide for detailed instructions on inference and integration.

Citation

@misc{SkyworkVL,
  author = {Jiangbo Pei and Chris and Yichen Wei and Xiaokun Wang and Yi Peng and Weijie Qiu and Ai Jian and Yunzhuo Hao and Jiachun Pan and Tianyidan Xie and Li Ge and Rongxian Zhuang and Xuchen Song and Yang Liu and Yahui Zhou},
  title = {SkyworkVL: Multimodal Understanding with Bag of Tricks},
  year = {2025},
  publisher = {Huggingface},
  journal = {Huggingface repository},
  howpublished = {\url{https://huggingface.co/Skywork/SkyworkVL-2B}}
}