GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
360ZhiNao
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
360ZhiNao
Model Tree
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Input Modalities
Output Modalities
Supported Functionality
Same as DeepSeek-R1-Distill-Qwen-32B.
We carefully evaluated data contamination of several open-sourced datasets. While certain contamination may be inevitable during pre-training, it is unacceptable for post-training to compare on benchmarks. MATH-500 is somewhat compromised with tens of questions that are identical or only numbers changed. AIME 24 and 25 stay intact but we have to pay special attention when we incorporate AIME data up to 2023.
Light-R1 did thorough decontamination with exact matching (excluding digits) and N-gram (N=32) matching.
latex
@misc{lightr1proj, title={Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond}, author={Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Lifu Tang, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang}, year={2025}, eprint={}, archivePrefix={}, url={https://github.com/Qihoo360/Light-R1}, }