osunlp/D3-Gym
Viewer • Updated • 565 • 164
D3-Gym
Constructing Verifiable Environments for Data-Driven Discovery
-
-
osunlp/D3-Gym-Trajectories
Viewer • Updated • 6.37k • 158 -
osunlp/D3-Gym-8B-rft-self
8B • Updated • 3 -
osunlp/D3-Gym-4B-rft-self
4B • Updated • 5 -
osunlp/D3-Gym-4B-rft-distill
4B • Updated • 2 -
osunlp/D3-Gym-8B-rft-distill
8B • Updated • 3 -
osunlp/D3-Gym-14B-rft-distill
15B • Updated • 4 -
osunlp/D3-Gym-14B-rft-self
15B • Updated • 3 -
osunlp/D3-Gym-32B-rft-self
33B • Updated • 2