-
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Paper • 2602.11149 • Published • 12 -
dakopi/distilled_numina__qwen3-0.6b
Viewer • Updated • 39.7k • 5 -
dakopi/distilled_numina__qwen3-8b
Viewer • Updated • 39.7k • 14 -
dakopi/distilled_numina__qwen3-0.6b__train_12800
Viewer • Updated • 12.8k • 7
Dawid
dakopi
AI & ML interests
None yet
Recent Activity
updated
a dataset
1 day ago
dakopi/32b_think__val
published
a dataset
1 day ago
dakopi/32b_think__val
updated
a dataset
1 day ago
dakopi/32b_think__train_800