Zhenghai Xue

ZhenghaiXue 's models 4

Sort:  Recently updated

ZhenghaiXue/gigpo_qwen2.5_3b_sim0.3_step150

3B • Updated Jul 30, 2025 • 2

ZhenghaiXue/gigpo_qwen2.5_3b_sim0.5_step150

3B • Updated Jul 30, 2025 • 1

ZhenghaiXue/Qwen2.5-7B-SimpleTIR

Reinforcement Learning • 8B • Updated Jul 8, 2025 • 390 • 1

ZhenghaiXue/Qwen2.5-32B-SimpleTIR

33B • Updated Jul 8, 2025 • 7