| ## Skywork-AI | |
| Welcome to **Skywork**! We are an innovative research team dedicated to advancing LLM and multimodal understanding. Our mission is to push the boundaries of AI by developing cutting-edge models and datasets that enable seamless interaction between vision and language. | |
| The name **“Skywork”** combines the limitless potential of the **Sky** with the impactful outcomes of our **Work**. | |
| --- | |
| ## Models | |
| - **[Skywork-R1V2-38B](https://huggingface.co/Skywork/Skywork-R1V2-38B)**: Multimodal Hybrid Reinforcement Learning for Reasoning | |
| - **[Skywork-VL-Reward-7B](https://huggingface.co/Skywork/Skywork-VL-Reward-7B)**: MultiModal Reward Model | |
| - **[Skywork-R1V-38B](https://huggingface.co/Skywork/Skywork-R1V-38B)**: Pioneering Multimodal Reasoning with Chain-of-Thought | |
| - **[SkyReels-V1](https://huggingface.co/Skywork/SkyReels-V1)**: Human-Centric Video Foundation Model | |
| - **[SkyReels-AX](https://huggingface.co/collections/Skywork/skyreels-ax-67fb4711700c4e2c0551f930)**: Controllable Video Generation Series | |
| - **[Skywork-o1-Open-PRM](https://huggingface.co/Skywork/Skywork-o1-Open-PRM-Qwen-2.5-1.5B)**: o1 Open Model Series | |
| - **[Skywork-Reward-Llama-3.1-8B-v0.2](https://huggingface.co/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2)**: Reward Model Series | |