Sebastian Raschka, PhD (@rasbt): "Looks like we got a new DeepSeek model over the holidays (again): https://github.com/deepseek-ai/DeepSeek-Math-V2 Basically pushes RLVR & self-refinement to gold-level scores on IMO 2025. Coincidentally, I am currently working on a chapter on self-refinement, and this comes in…"

Looks like we got a new DeepSeek model over the holidays (again):

Basically pushes RLVR & self-refinement to gold-level scores on IMO 2025.

Coincidentally, I am currently working on a chapter on self-refinement, and this comes in handy as a nice, scaled-up case study.

github.com

Contribute to deepseek-ai/DeepSeek-Math-V2 development by creating an account on GitHub.

Nov 29

3:08 PM