Co-rewarding
Collection
Co-rewarding is a novel self-supervised RL framework that improves training stability by seeking complementary supervision from another views. • 75 items • Updated • 1
Co-rewarding-II: Llama-3.2-3B-Instruct trained on MATH
This is the Llama-3.2-3B-Instruct model trained by Co-rewarding-II using MATH training set.
If you are interested in Co-rewarding, you can find more details on our Github Repo [https://github.com/tmlr-group/Co-rewarding].
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support