1. Tutorial Introduction

The computing resources used in this tutorial are a single RTX 4090 card.

DeepSeek-R1-0528-Qwen3-8B was released by the DeepSeek team in May 2025. It is a lightweight reasoning model trained based on the thinking chain distillation technology of DeepSeek-R1-0528. The model has 8 billion parameters. By distilling the complex reasoning capabilities of DeepSeek-R1-0528 to the smaller Qwen3-8B base model, it combines the multi-language capabilities of Qwen3 and the reasoning optimization of DeepSeek-R1. Its performance is comparable to GPT-4, supports efficient deployment on a single card, and is an ideal choice for academic and enterprise applications. At AIME 2024, DeepSeek-R1-0528-Qwen3-8B achieved the best performance (SOTA) among open source models, surpassing Qwen3 8B +10.0%, and comparable to the performance of Qwen3-235B-thinking.

2. Project Examples

3. Operation steps

1. Start the container

If "Model" is not displayed, it means the model is being initialized. Since the model is large, please wait about 2-3 minutes and refresh the page.

2. After entering the webpage, you can start a conversation with the model

4. Discussion

🖌️ If you see a high-quality project, please leave a message in the background to recommend it! In addition, we have also established a tutorial exchange group. Welcome friends to scan the QR code and remark [SD Tutorial] to join the group to discuss various technical issues and share application effects↓

Citation Information

The citation information for this project is as follows:

@misc{deepseekai2025deepseekr1incentivizingreasoningcapability,
      title={DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning}, 
      author={DeepSeek-AI},
      year={2025},
      eprint={2501.12948},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.12948}, 
}