TMLR-Group-HF/

Majority-Voting-Qwen3-4B-Base-OpenRS

This is the Qwen3-4B-Base model trained by Majority-Voting using OpenRS training set. For more details on Co-rewarding, please refer to the paper Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.

If you are interested in Co-rewarding, you can find more details on our Github Repo [https://github.com/tmlr-group/Co-rewarding].