1. Tutorial Introduction

"SpikingBrain-1.0" is a domestically developed and controllable brain-inspired spiking model released in September 2025 by the Institute of Automation, Chinese Academy of Sciences, in collaboration with the National Key Laboratory of Brain Cognition and Brain-Inspired Intelligence, and Muxi Integrated Circuit Co., Ltd. Inspired by brain mechanisms, SpikingBrain integrates a hybrid efficient attention mechanism, MoE modules, and spiking coding into its architecture, supported by a universal transformation pipeline compatible with the open-source model ecosystem. This enables continuous pre-training using less than 21 TP3T of data while achieving performance comparable to mainstream open-source models. SpikingBrain achieves over 100x speedup in TTFTs of 4M-token sequences, while spiking coding provides over 691 TP3T of sparsity at the microscopic level. Combined with the macroscopic MoE sparsity, these advancements provide valuable guidance for the design of next-generation neuromorphic chips. Related research papers are available. SpikingBrain Technical Report: Spiking Brain-inspired Large Models .

This tutorial uses a single RTX 5090 GPU for computing power, and the model deployed in this tutorial is SpikingBrain's V1-7B-sft-s3-reasoning.

2. Effect display

3. Operation steps

1. Start the container

2. Usage steps

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.

4. Discussion

🖌️ If you see a good project, please leave a comment in the background to recommend it! In addition, we have also established a tutorial exchange group. Friends are welcome to scan the QR code and note [AI4S Tutorial] to join the group to discuss various technical issues and share application results↓

Citation Information

Thanks to Github user SuperYang  Deployment of this tutorial. The reference information of this project is as follows:

@article{pan2025spikingbrain,
  title={SpikingBrain Technical Report: Spiking Brain-inspired Large Models},
  author={Pan, Yuqi and Feng, Yupeng and Zhuang, Jinghao and Ding, Siyu and Liu, Zehao and Sun, Bohan and Chou, Yuhong and Xu, Han and Qiu, Xuerui and Deng, Anlin and others},
  journal={arXiv preprint arXiv:2509.05276},
  year={2025}
}