RoadMa

RoadQAQ's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 6 hours ago

stepfun-ai/Step-3.5-Flash

Text Generation • 199B • Updated 2 days ago • 228k • 537

liked a dataset about 6 hours ago

stepfun-ai/CF-Div2-Stepfun

Viewer • Updated about 6 hours ago • 53 • 5

updated a dataset about 1 month ago

RoadQAQ/sft_for_rl

Preview • Updated Jan 1 • 3

published a dataset about 1 month ago

RoadQAQ/sft_for_rl

Preview • Updated Jan 1 • 3

updated a collection 4 months ago

Data for DataFlex

Collection

Data for DataFlex experiments • 5 items • Updated Dec 31, 2025 • 1

updated a dataset 4 months ago

OpenDCAI/dataflex_10w_cot_from_numinamath_coT

Viewer • Updated Sep 30, 2025 • 100k • 6

published a dataset 4 months ago

OpenDCAI/dataflex_10w_cot_from_numinamath_coT

Viewer • Updated Sep 30, 2025 • 100k • 6

updated a dataset 4 months ago

RoadQAQ/10w_cot_from_NuminaMath-CoT

Viewer • Updated Sep 29, 2025 • 100k • 3

published a dataset 4 months ago

RoadQAQ/10w_cot_from_NuminaMath-CoT

Viewer • Updated Sep 29, 2025 • 100k • 3

updated a model 6 months ago

RoadQAQ/ReLIFT-Qwen2.5-Math-7B-Zero

Question Answering • 8B • Updated Aug 27, 2025 • 50

updated a dataset 7 months ago

RoadQAQ/OpenR1

Viewer • Updated Jul 8, 2025 • 45.8k • 7

published a dataset 7 months ago

RoadQAQ/OpenR1

Viewer • Updated Jul 8, 2025 • 45.8k • 7

updated 4 models 8 months ago

RoadQAQ/Qwen2.5-7B-think

Text Generation • 8B • Updated Jun 18, 2025 • 1

RoadQAQ/Qwen2.5-Math-1.5B-16k-think

Text Generation • 2B • Updated Jun 18, 2025 • 2.51k

RoadQAQ/ReLIFT-Qwen2.5-7B-Zero

Question Answering • 8B • Updated Jun 18, 2025 • 1 • 2

RoadQAQ/Qwen2.5-Math-7B-16k-think

Text Generation • 8B • Updated Jun 18, 2025 • 17

New activity in RoadQAQ/ReLIFT-Qwen2.5-Math-7B-Zero 8 months ago

Add model card

#1 opened 8 months ago by

nielsr

New activity in RoadQAQ/ReLIFT-Qwen2.5-Math-1.5B-Zero 8 months ago

Add model card with metadata and links

#1 opened 8 months ago by

nielsr

New activity in RoadQAQ/ReLIFT-Qwen2.5-7B-Zero 8 months ago

Add pipeline tag, link to the paper and project page

#1 opened 8 months ago by

nielsr

updated a collection 8 months ago

ReLIFT

Collection

ReLIFT, a training method that interleaves RL with online FT, achieving superior performance and efficiency compared to using RL or SFT alone. • 8 items • Updated Jun 10, 2025 • 1