-
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Paper • 2602.11149 • Published • 18 -
dakopi/distilled_numina__qwen3-0.6b
Viewer • Updated • 39.7k • 12 -
dakopi/distilled_numina__qwen3-8b
Viewer • Updated • 39.7k • 5 -
dakopi/distilled_numina__qwen3-0.6b__train_12800
Viewer • Updated • 12.8k • 38
Dawid
dakopi
AI & ML interests
None yet
Recent Activity
liked a model about 16 hours ago
sakamakismile/Huihui-Qwen3.8-27B-abliterated-NVFP4 upvoted a paper about 1 month ago
Self-Supervised Learning of Structured Dynamics from Videos liked a model about 2 months ago
Qwen/Qwen3.6-27BOrganizations
-
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Paper • 2602.11149 • Published • 18 -
dakopi/distilled_numina__qwen3-0.6b
Viewer • Updated • 39.7k • 12 -
dakopi/distilled_numina__qwen3-8b
Viewer • Updated • 39.7k • 5 -
dakopi/distilled_numina__qwen3-0.6b__train_12800
Viewer • Updated • 12.8k • 38
datasets 67
dakopi/mid_math
Viewer • Updated • 50 • 13
dakopi/hard_math
Viewer • Updated • 50 • 14
dakopi/deepmath
Viewer • Updated • 40.2k • 13
dakopi/32b_think__val
Viewer • Updated • 1k • 13
dakopi/32b_think__train_800
Viewer • Updated • 800 • 14
dakopi/32b_think__train_6400
Viewer • Updated • 6.4k • 19
dakopi/32b_think__train_400
Viewer • Updated • 400 • 7
dakopi/32b_think__train_3200
Viewer • Updated • 3.2k • 9
dakopi/32b_think__train_25600
Viewer • Updated • 25.6k • 12
dakopi/32b_think__train_200
Viewer • Updated • 200 • 14