Model

deepseekmath

1 entry · February 2024

Appears alongside

Featured in threads

Tracks

  • Ideas & essays 1
  • Models & capabilities 1

  1. DeepSeek publishes DeepSeekMath, introducing GRPO

    The 7B model reached 51.7% on the MATH benchmark without external tools, and its GRPO training method later underpinned DeepSeek-R1's reasoning training.

    Ideas & essays · Models & capabilities