RoadMa

RoadQAQ's activity

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

updated a dataset 1 day ago

RoadQAQ/sft_for_rl

Preview • Updated 1 day ago • 10

published a dataset 1 day ago

RoadQAQ/sft_for_rl

Preview • Updated 1 day ago • 10

updated a collection 3 months ago

Data for DataFlex

Collection

Data for DataFlex experiments • 5 items • Updated 2 days ago • 1

updated a dataset 3 months ago

OpenDCAI/dataflex_10w_cot_from_numinamath_coT

Viewer • Updated Sep 30, 2025 • 100k • 14

published a dataset 3 months ago

OpenDCAI/dataflex_10w_cot_from_numinamath_coT

Viewer • Updated Sep 30, 2025 • 100k • 14

updated a dataset 3 months ago

RoadQAQ/10w_cot_from_NuminaMath-CoT

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

published a dataset 3 months ago

RoadQAQ/10w_cot_from_NuminaMath-CoT

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

updated a model 4 months ago

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

Question Answering • 8B • Updated Aug 27, 2025 • 435

updated a dataset 6 months ago

RoadQAQ/OpenR1

Viewer • Updated Jul 8, 2025 • 45.8k • 21

published a dataset 6 months ago

RoadQAQ/OpenR1

Viewer • Updated Jul 8, 2025 • 45.8k • 21

updated 4 models 7 months ago

RoadQAQ/Qwen2.5-7B-think

Text Generation • 8B • Updated Jun 18, 2025 • 7

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

Text Generation • 2B • Updated Jun 18, 2025 • 808

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

Question Answering • 8B • Updated Jun 18, 2025 • 7 • 2

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

Text Generation • 8B • Updated Jun 18, 2025 • 74

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

Add model card

#1 opened 7 months ago by

nielsr

New activity in RoadQAQ/ReLIFT-Qwen2.5-Math-1.5B-Zero 7 months ago

Add model card with metadata and links

#1 opened 7 months ago by

nielsr

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

Add pipeline tag, link to the paper and project page

#1 opened 7 months ago by

nielsr

updated a collection 7 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

upvoted a paper 7 months ago

Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions

Paper • 2506.07527 • Published Jun 9, 2025 • 3

commented a paper 7 months ago

Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions

Paper • 2506.07527 • Published Jun 9, 2025 • 3 •

2