Junjie Lu

Lux0926

·

Lux0926

AI & ML interests

None yet

Organizations

Lux0926 's datasets 16

Lux0926/Qwen2-7B-SFT-CGPO-10k

Viewer • Updated Oct 26, 2025 • 10.8k • 25

Lux0926/Qwen1.5-32B-SFT-CGPO-10k

Viewer • Updated Oct 26, 2025 • 10.8k • 47

Lux0926/DeepSeekMath-Base-7B-SFT-CGPO-10k

Viewer • Updated Oct 26, 2025 • 10.8k • 57

Lux0926/Deepseek-Coder-7B-Instruct-v1.5-CGPO-10k

Viewer • Updated Oct 26, 2025 • 10.6k • 40

Lux0926/MetaMath-Llama-8B-CGPO-10k

Viewer • Updated Oct 26, 2025 • 10.8k • 39

Lux0926/MetaMath-Mistral-7B-CGPO-10k

Viewer • Updated Oct 26, 2025 • 10.8k • 28

Lux0926/ASPRM-BON-Evaluation-Dataset-Code

Preview • Updated Feb 21, 2025 • 100

Lux0926/ASPRM-BON-Evaluation-Dataset-Math

Preview • Updated Feb 21, 2025 • 271

Lux0926/ASPRM-Math-Rollout-Result

Viewer • Updated Feb 7, 2025 • 215k • 24

Lux0926/ASPRM-MATHCODE-DeepSeek-Training-Dataset

Viewer • Updated Feb 7, 2025 • 99.8k • 44 • 1

Lux0926/ASPRM-MATHCODE-Mistral-Training-Dataset

Viewer • Updated Feb 7, 2025 • 438k • 15

Lux0926/ASPRM-D-Training-Dataset

Viewer • Updated Feb 7, 2025 • 49.9k • 18

Lux0926/ASPRM-L-Training-Dataset

Viewer • Updated Feb 7, 2025 • 372k • 24

Lux0926/ASPRM-D-Training-Dataset-ORM

Viewer • Updated Feb 7, 2025 • 49.9k • 9

Lux0926/ASPRM-M-Training-Dataset

Viewer • Updated Feb 7, 2025 • 388k • 22

Lux0926/ASPRM-Code-Rollout-Result

Updated Feb 7, 2025 • 7