Efficient Reasoning via Decoupled Reward Policy Optimization
Gang Li
ganglii
AI & ML interests
None yet
Recent Activity
updated a dataset 2 days ago
ganglii/self_replay2k10 published a dataset 2 days ago
ganglii/self_replay2k10 updated a dataset 4 days ago
ganglii/OpenMathReasoning_len8k_0.6_self_replay2k10Organizations
None yet
models 10
ganglii/DRPO-7B-Lambda-0.2
8B • Updated • 4 • 1
ganglii/DRPO-7B-Lambda-0.5
8B • Updated • 7
ganglii/DRPO-7B
8B • Updated • 188 • 1
ganglii/DRPO-1.5B
2B • Updated • 34
ganglii/DRPO-1.5B-Lambda-0.2
2B • Updated • 43
ganglii/DRPO-1.5B-Lambda-0.5
2B • Updated • 8
ganglii/DisCO-7B-Lratio
8B • Updated • 3
ganglii/DisCO-7B-logL
8B • Updated • 3
ganglii/DisCO-1.5B-Lratio
2B • Updated • 3
ganglii/DisCO-1.5B-logL
2B • Updated • 5
datasets 69
ganglii/self_replay2k10
Viewer • Updated • 86.5k • 21
ganglii/OpenMathReasoning_len8k_0.6_self_replay2k10
Viewer • Updated • 350k • 36
ganglii/7B_math_n10_s2
Viewer • Updated • 2k • 41
ganglii/7B_safety_n10_s2
Viewer • Updated • 2k • 39
ganglii/7B_if_n10_s2
Viewer • Updated • 2k • 39
ganglii/7B_arc_challenge_n10_s2
Viewer • Updated • 1.12k • 43
ganglii/7B_winogrande_n10_s2
Viewer • Updated • 2k • 39
ganglii/7B_mmlu_n10_s2
Viewer • Updated • 1.53k • 37
ganglii/OpenMathReasoning_len8k_0.2_self_8B
Viewer • Updated • 526k • 49
ganglii/8B_safety_n10
Viewer • Updated • 2k • 11