zheminh/grpo-0612-verl-math-fmt-with-acc-strict-step08
8B • Updated
Zhemin Huang
zheminh
·
AI & ML interests
None yet
Organizations
None yet
models 83
zheminh/grpo-0609-verl-math-step09
8B • Updated
zheminh/grpo-0604-step15
8B • Updated
• 1
zheminh/grpo-0602-verl-step12
8B • Updated
zheminh/grpo-0531-ckpt30
8B • Updated
zheminh/grpo-0531-ckpt150
8B • Updated
zheminh/grpo-0529-ckpt60
8B • Updated
zheminh/grpo-0529-ckpt30
8B • Updated
zheminh/grpo-0529-length-comparison-ckpt90
8B • Updated
zheminh/grpo-0529-ckpt90
8B • Updated
datasets 22
zheminh/creative_writing
Viewer
• Updated
• 4 • 15
zheminh/openhands_data
Viewer
• Updated
• 500 • 8
zheminh/countdown_v5
Viewer
• Updated
• 1k • 8
zheminh/countdown_v4
Viewer
• Updated
• 300 • 6
zheminh/countdown_v3
Viewer
• Updated
• 100 • 5
zheminh/countdown_v2
Viewer
• Updated
• 100 • 6
zheminh/countdown
Viewer
• Updated
• 102 • 12
zheminh/gpqa_diamond
Viewer
• Updated
• 198 • 192
zheminh/RL-MATH-DeepMath
Viewer
• Updated
• 250 • 8
zheminh/SWE-bench_Lite_oracle_2_estimation
Viewer
• Updated
• 300 • 7