Home

Awesome

O1 Replication Journey

About the Team

The core development team of this project mainly consists of third- and fourth-year undergraduate students, as well as first-year PhD students from the GAIR research group at Shanghai Jiao Tong University. The project has been guided by leading research scientists in the field of large language models, including those from NYU and MBZUAI.

The specific introductions of the team members are as follows:

<!-- | | | | | | | |---------|---------|---------|---------|---------|---------| |<img src="./images/profiles/yiwei.jpg" width="100">|<img src="./images/profiles/xuefeng.png" width="100">|<img src="./images/profiles/haoyang.png" width="100">|<img src="./images/profiles/yixiu.png" width="100">|<img src="./images/profiles/shijie.jpg" width="100">|<img src="./images/profiles/huangzhen.png" width="100">| |[Yiwei Qin](https://qinyiwei.github.io)|[Xuefeng Li](https://scholar.google.com/citations?user=DDRBbxgAAAAJ&hl=zh-CN)|[Haoyang Zou](https://scholar.google.com/citations?user=btPmUcoAAAAJ&hl=en)|[Yixiu Liu](https://scholar.google.com/citations?user=HKUoOq0AAAAJ&hl=zh-CN)|[Shijie Xia](https://shijie-xia.github.io)|[Zhen Huang](https://huangzhen02.github.io)| |<img src="./images/profiles/yixin.png" width="100">|<img src="./images/profiles/weizhe.jpg" width="100">|<img src="./images/profiles/hector.png" width="100">|<img src="./images/profiles/yuanzhi.jpeg" width="100">|<img src="./images/profiles/pengfei.jpg" width="100">|| |[Yixin Ye](https://github.com/BLeaves)|[Weizhe Yuan](https://yyy-apple.github.io/)|[Zhengzhong Liu](https://hunterhector.github.io)|[Yuanzhi Li](https://scholar.google.com/citations?hl=en&user=aHtfItQAAAAJ&view_op=list_works&sortby=pubdate)|[Pengfei Liu](https://plms.ai/)|| -->

Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Yuxiang Zheng, Ethan Chern, Weizhe Yuan, Zhengzhong Liu, Yuanzhi Li, Pengfei Liu

Updates

Our Journey 🗺️

Part2: Surpassing O1-preview through Simple Distillation (Big Progress or Bitter Lesson?)

Report (Part2) | Citation

This paper critically examines current methods for replicating OpenAI’s O1 model, focusing on the often-overlooked use of knowledge distillation. While Part 1 explored foundational techniques for O1 replication, this study demonstrates how simple distillation from O1’s API, combined with supervised fine-tuning, can achieve superior performance on complex mathematical reasoning tasks.

Key findings include:

Part1: A Strategic Progress Report

Report (Part1) | Dataset | Walnut Plan | Citation

This paper introduces a pioneering approach to artificial intelligence research, embodied in our O1 Replication Journey. In response to the announcement of OpenAI’s groundbreaking O1 model, we embark on a transparent, real-time exploration to replicate its capabilities while reimagining the process of conducting and communicating AI research.

We propose a new approach: “journey learning”. This paradigm goes beyond the traditional focus on specific tasks and emphasizes continuous progress through learning, reflection, and adaptation. AI systems that follow this method can evolve over time, improving their ability to handle real-world complexities. Unlike shortcut learning, journey learning equips AI with the capacity to adapt, backtrack, and refine its understanding, aiming to create more human-like intelligence. This shift to journey learning opens up new possibilities in AI research, enabling the creation of systems that can not only perform tasks but also reason and grow, making them more capable of engaging with humans across various domains.

Progress

Contact Us

If you are interested in our project and would like to join us, feel free to send an email to stefanpengfei@gmail.com.

Citation

Part1:

@article{qin2024o1,
  title={O1 Replication Journey: A Strategic Progress Report--Part 1},
  author={Qin, Yiwei and Li, Xuefeng and Zou, Haoyang and Liu, Yixiu and Xia, Shijie and Huang, Zhen and Ye, Yixin and Yuan, Weizhe and Liu, Hector and Li, Yuanzhi and others},
  journal={arXiv preprint arXiv:2410.18982},
  year={2024}
}

Part2:

@article{huang2024o1,
  title={O1 Replication Journey--Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?},
  author={Huang, Zhen and Zou, Haoyang and Li, Xuefeng and Liu, Yixiu and Zheng, Yuxiang and Chern, Ethan and Xia, Shijie and Qin, Yiwei and Yuan, Weizhe and Liu, Pengfei},
  journal={arXiv preprint arXiv:2411.16489},
  year={2024}
}