Data of Paper "Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning" (https://arxiv.org/pdf/2510.07300)
Xue Zhang
XueZhang-bjtu
AI & ML interests
None yet
Organizations
None yet
M-Thinker-Data
Data of Paper "Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning" (https://arxiv.org/pdf/2510.07300)
M-Thinker
Models of Paper "Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning" (https://arxiv.org/pdf/2510.07300)
models 7
XueZhang-bjtu/M-Thinker-7B-Iter2
Text Generation • 8B • Updated • 14
XueZhang-bjtu/Native-RL
Updated
XueZhang-bjtu/7B-cold-start-SFT
Text Generation • 8B • Updated • 8
XueZhang-bjtu/1.5B-cold-start-SFT
Text Generation • 2B • Updated • 1.26k
XueZhang-bjtu/M-Thinker-1.5B-Iter2
Text Generation • 2B • Updated • 12
XueZhang-bjtu/M-Thinker-7B-Iter1
Text Generation • 8B • Updated • 9
XueZhang-bjtu/M-Thinker-1.5B-Iter1
Text Generation • 2B • Updated • 16
datasets 6
XueZhang-bjtu/Light-R1-SFTData-question-translated-76K
Viewer • Updated • 151k • 29
XueZhang-bjtu/M-Thinker-7B-RL-Iter2-data
Viewer • Updated • 15.1k • 30
XueZhang-bjtu/M-Thinker-7B-RL-Iter1-data
Viewer • Updated • 15.1k • 31
XueZhang-bjtu/M-Thinker-1.5B-RL-Iter2-data
Viewer • Updated • 15.1k • 30
XueZhang-bjtu/M-Thinker-1.5B-RL-Iter1-data
Viewer • Updated • 15.1k • 41
XueZhang-bjtu/M-Thinker-SFT-data
Viewer • Updated • 20.1k • 32