Any plan to release the GRPO code?

QwenLM / Qwen2.5-Math

A series of math-specific large language models of our Qwen2 series.

https://qwenlm.github.io/blog/qwen2-math/

608 stars 60 forks source link

Open Viper403 opened 3 months ago

Viper403 commented 3 months ago

Congratulations to Qwen team! Another outstanding job!

I noticed that you use GRPO to RL your math model. For now, there is no released implementation of GRPO. Do you have any plan to release the code?

Thank you very much!

RayWang-iat commented 3 months ago