hkust-nlp/Laser-Deepscaler-Dataset
Viewer
•
Updated
•
40.8k
•
82
Laser
The collection for the Paper "Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping"
-
-
hkust-nlp/Laser-L2048-1.5B
2B • Updated • 69 -
hkust-nlp/Laser-L4096-1.5B
2B • Updated • 4 -
hkust-nlp/Laser-L8192-1.5B
2B • Updated • 67 -
hkust-nlp/Laser-D-L1024-1.5B
2B • Updated • 2 -
hkust-nlp/Laser-D-L2048-1.5B
2B • Updated • 67 -
hkust-nlp/Laser-D-L4096-1.5B
2B • Updated • 5 -
hkust-nlp/Laser-DE-L1024-1.5B
2B • Updated • 2 -
hkust-nlp/Laser-DE-L2048-1.5B
2B • Updated • 77 -
hkust-nlp/Laser-DE-L4096-1.5B
2B • Updated • 68 -
hkust-nlp/Laser-D-L4096-7B
8B • Updated • 328 -
hkust-nlp/Laser-DE-L4096-7B
8B • Updated • 75 -
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
Paper • 2505.15612 • Published • 34