Datasets and trained checkpoints of Composition-RL: https://github.com/XinXU-USTC/Composition-RL
🏝️ On Vacation
xuxin
xx18
AI & ML interests
None yet
Organizations
models 23
xx18/Composition-RL-4B-Depth1_2_3
Text Generation • 4B • Updated • 14
xx18/Composition-RL-4B-Depth1_2
Text Generation • 4B • Updated • 20
xx18/Baseline-4B-MATH12K
Text Generation • 4B • Updated • 22
xx18/Composition-RL-4B-Physics_Math
Text Generation • 4B • Updated • 23
xx18/Composition-RL-30B-A3B
Text Generation • 31B • Updated • 18
xx18/Composition-RL-14B
Text Generation • 15B • Updated • 18
xx18/Composition-RL-8B
Text Generation • 8B • Updated • 29 • 1
xx18/Composition-RL-4B
Text Generation • 4B • Updated • 35
xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3
Text Generation • 4B • Updated • 30
xx18/DirectRL_Qwen3-4B_baseline2
Text Generation • 4B • Updated • 27
datasets 7
xx18/MATH-Composition-Depth3
Viewer • Updated • 132k • 27
xx18/Physics-MATH-Composition-141K
Viewer • Updated • 141k • 36
xx18/MATH-Composition-199K
Viewer • Updated • 199k • 36 • 1
xx18/Composition-RL-EVA
Viewer • Updated • 12.8k • 78 • 1
xx18/Polaris-Composition-1323K
Viewer • Updated • 1.32M • 27 • 1
xx18/TFPI-EVA
Preview • Updated • 42 • 1
xx18/R2PE
Viewer • Updated • 38.7k • 152 • 2