metadata
license: mit
pipeline_tag: text-generation
library_name: transformers
This is the Qwen3-4B-Base model trained by Majority-Voting using DAPO-14k training set, as presented in 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].