nvidia/AceReason-Nemotron-14B
Text Generation
•
15B
•
Updated
•
18.4k
•
•
84
AceReason
Math and Code reasoning model trained through reinforcement learning (RL)
-
-
nvidia/AceReason-Nemotron-7B
Text Generation • 8B • Updated • 4.43k • • 18 -
nvidia/AceReason-Nemotron-1.1-7B
Text Generation • 8B • Updated • 53.2k • • 53 -
nvidia/AceReason-Math
Viewer • Updated • 49.6k • 2.85k • 18 -
nvidia/AceReason-1.1-SFT
Viewer • Updated • 3.96M • 13.5k • 70 -
AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
Paper • 2505.16400 • Published • 33 -
AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
Paper • 2506.13284 • Published • 24