learn.ifs.name

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Shao et al., 2024, DeepSeekMath (arXiv preprint arXiv:2402.03300)

Subscriber deck — free during early access

1 cards in “3.1 SFT Data Curation” · whole deck

3.1 SFT Data Curation

  1. What kinds of solutions did DeepSeekMath-Instruct learn from?
    English and Chinese problems paired with chain-of-thought (natural-language steps), program-of-thought (code) and tool-integrated reasoning solutions, about 776K examples.
    • Shao et al., 2024, DeepSeekMath (arXiv preprint arXiv:2402.03300), §3.1

Source

  • Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. In arXiv preprint arXiv:2402.03300. https://arxiv.org/abs/2402.03300