Sheng Jia PRO
shengjia-toronto
AI & ML interests
None yet
Recent Activity
authored a paper about 7 hours ago
Group Adaptive Clipping Policy Optimization upvoted a paper about 13 hours ago
Group Adaptive Clipping Policy Optimization submitted a paper about 13 hours ago
Group Adaptive Clipping Policy OptimizationOrganizations
None yet
models 54
shengjia-toronto/deepcoder-1.5b-24k-grpo-sac-step70
2B • Updated • 3
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step1061-aime24-43pct
2B • Updated • 5
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step961-aime24-42pct
2B • Updated • 4
shengjia-toronto/Llama-3.2-3B-GSPO-cl3e3-DrGRPO-Step561-BestPass1-DeepScaleR-AIME24
4B • Updated • 4
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step881-verified
2B • Updated • 4
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step881-aime24-40pct
2B • Updated • 5
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-t06-s641-nokl-n8-step105-aime24-42.9
2B • Updated • 3
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step821-aime24-40pct
2B • Updated • 4
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step761-aime24-38pct
2B • Updated • 4
shengjia-toronto/sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step741-aime24-38pct
2B • Updated • 5
datasets 12
shengjia-toronto/aime24-verl-preprocessed
Viewer • Updated • 30 • 18
shengjia-toronto/deepscaler-verl-preprocessed
Viewer • Updated • 39.2k • 22
shengjia-toronto/deepscaler-verl
Viewer • Updated • 39.2k • 11
shengjia-toronto/s4Kcode-R1-tokenized
Viewer • Updated • 1k
shengjia-toronto/ssft1Kcode-v2-Sonnet4-5-High-Run2-temp1-max29000
Viewer • Updated • 1k • 17 • 3
shengjia-toronto/ssft1Kcode-v2-Sonnet4-5-High-Run1-temp1-max29000
Viewer • Updated • 1k • 14 • 2
shengjia-toronto/ssft1Kcode-v2-OSS-High-Run1-temp1-max32768
Viewer • Updated • 1k • 5
shengjia-toronto/ssft1Kcode_v2
Viewer • Updated • 1k • 9
shengjia-toronto/exploded-s1k-4mixed-reasoning-raw-tokenized
Viewer • Updated • 4k • 3
shengjia-toronto/dapo-math-17k-promptprocessed
Viewer • Updated • 14.1k • 17