Best NSD checkpoints for Qwen3 (1.7B, 4B, 8B). Online NSD supervised, MATH dataset.
Rongcan Pei
PassionPrc
AI & ML interests
None yet
Recent Activity
submitted a paper 2 days ago
Negative Self-Distillation: Learning to Reason by Avoiding Flaws authored a paper 2 days ago
Negative Self-Distillation: Learning to Reason by Avoiding Flaws upvoted a paper 3 days ago
Negative Self-Distillation: Learning to Reason by Avoiding FlawsOrganizations
None yet
datasets 12
PassionPrc/hotpot-fine-grain-evidence
Viewer • Updated • 24.8k • 380
PassionPrc/docvqa-grpo
Viewer • Updated • 69.4k • 136
PassionPrc/doclaynet-grpo
Viewer • Updated • 111k • 168
PassionPrc/xfund-grpo
Viewer • Updated • 18.6k • 80
PassionPrc/mpdocvqa-grpo
Viewer • Updated • 12.7k • 65
PassionPrc/cord-grpo
Preview • Updated • 166
PassionPrc/chartqa-grpo
Viewer • Updated • 32.7k • 166
PassionPrc/funsd-grpo
Viewer • Updated • 3.92k • 117
PassionPrc/sciegqa-grpo
Viewer • Updated • 12.8k • 119
PassionPrc/bbox-dev
Viewer • Updated • 148 • 36