qihoo360/Light-R1-14B-DS
Text Generation
•
15B
•
Updated
•
926
•
•
37
Light-R1
Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
-
-
qihoo360/Light-R1-14B-DS-GGUF
Text Generation • 15B • Updated • 50 • 9 -
qihoo360/Light-R1-7B-DS
Text Generation • 8B • Updated • 1.04k • • 21 -
qihoo360/Light-R1-32B
Text Generation • 33B • Updated • 704 • 87 -
qihoo360/Light-R1-32B-DS
Text Generation • 33B • Updated • 923 • 14 -
qihoo360/Light-R1-SFTData
Viewer • Updated • 79.4k • 317 • 52 -
qihoo360/Light-R1-DPOData
Viewer • Updated • 2.97k • 179 • 27