search

deepseek-ai / DeepSeek-Math

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
MIT License
821 stars 51 forks source link

GRPO as part of HF TRL? #26

Open idobenshaul10 opened 3 months ago

idobenshaul10 commented 3 months ago

Would be cool to see this compared to other methods