This is the Qwen3-1.7B-Base 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].

Safetensors

Model size

2B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TMLR-Group-HF/Co-rewarding-II-Qwen3-1.7B-Base-MATH

Quantizations

Collection including TMLR-Group-HF/Co-rewarding-II-Qwen3-1.7B-Base-MATH