-
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Paper • 2602.11149 • Published • 15 -
dakopi/distilled_numina__qwen3-0.6b
Viewer • Updated • 39.7k • 9 -
dakopi/distilled_numina__qwen3-8b
Viewer • Updated • 39.7k • 10 -
dakopi/distilled_numina__qwen3-0.6b__train_12800
Viewer • Updated • 12.8k • 12
Dawid
dakopi
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models liked a dataset 28 days ago
allenai/IF_multi_constraints_upto5 liked a dataset 28 days ago
allenai/RLVR-IFevalOrganizations
-
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Paper • 2602.11149 • Published • 15 -
dakopi/distilled_numina__qwen3-0.6b
Viewer • Updated • 39.7k • 9 -
dakopi/distilled_numina__qwen3-8b
Viewer • Updated • 39.7k • 10 -
dakopi/distilled_numina__qwen3-0.6b__train_12800
Viewer • Updated • 12.8k • 12
datasets 64
dakopi/32b_think__val
Viewer • Updated • 1k • 15
dakopi/32b_think__train_800
Viewer • Updated • 800 • 14
dakopi/32b_think__train_6400
Viewer • Updated • 6.4k • 14
dakopi/32b_think__train_400
Viewer • Updated • 400 • 15
dakopi/32b_think__train_3200
Viewer • Updated • 3.2k • 15
dakopi/32b_think__train_25600
Viewer • Updated • 25.6k • 20
dakopi/32b_think__train_200
Viewer • Updated • 200 • 14
dakopi/32b_think__train_1600
Viewer • Updated • 1.6k • 15
dakopi/32b_think__train_12800
Viewer • Updated • 12.8k • 16
dakopi/32b_think__train_100
Viewer • Updated • 100 • 13