CHENyongxi

chenyongxi

3

·

icyyymilk

AI & ML interests

RL rollout、Sampling

Organizations

None yet

models 44

chenyongxi/Qwen2.5-0.5B-SFT-Safe

chenyongxi/Qwen2.5-1.5B-SFT-DPO-InfinityPreference

Text Generation • 2B • Updated Apr 3 • 9

chenyongxi/Qwen2.5-1.5B-SFT-PPO-InfinityPreference

2B • Updated Apr 3 • 6

chenyongxi/Qwen2.5-1.5B-SFT-InfinityPreference

2B • Updated Apr 3 • 4

chenyongxi/Qwen2.5-1.5B-SFT-PPO-IP

chenyongxi/Qwen2.5-1.5B-DPO-1.5B

Text Generation • 2B • Updated Apr 2 • 12

chenyongxi/Qwen2-1.5B-SFT-PPO-IP

chenyongxi/Qwen2.5-1.5B-SFT-IP

Text Generation • 2B • Updated Apr 1 • 9

chenyongxi/Qwen2-1.5B-SFT-IF

Text Generation • 2B • Updated Mar 31 • 12

chenyongxi/Qwen2.5-1.5B-PPO-IP

datasets 0

None public yet