nvidia/Nemotron-RL-instruction_following
Preview • Updated • 374 • 15
Nemotron Reinforcement Learning
RL training datasets with verifiable and execution-based rewards across math, code, agentic tasks, instruction following, knowledge, and safety.
-
-
nvidia/Nemotron-RL-instruction_following-structured_outputs
Viewer • Updated • 9.95k • 392 • 37 -
nvidia/Nemotron-RL-Identity-Following-v1
Viewer • Updated • 21.7k • 179 • 1 -
nvidia/Nemotron-RL-Instruction-Following-Adversarial-v1
Viewer • Updated • 1k • 171 • 2 -
nvidia/Nemotron-RL-Instruction-Following-Calendar-v2
Viewer • Updated • 9.92k • 168 • 2 -
nvidia/Nemotron-RL-Instruction-Following-MultiTurnChat-v1
Viewer • Updated • 2.01k • 273 • 2 -
nvidia/Nemotron-RL-knowledge-mcqa
Viewer • Updated • 686k • 384 • 11 -
nvidia/Nemotron-RL-knowledge-openqa
Viewer • Updated • 136k • 123 • 10 -
nvidia/Nemotron-RL-knowledge-web_search-mcqa
Viewer • Updated • 2.93k • 109 • 14 -
nvidia/Nemotron-RL-math-advanced_calculations
Viewer • Updated • 6k • 118 • 11 -
nvidia/Nemotron-RL-math-OpenMathReasoning
Viewer • Updated • 113k • 279 • 16 -
nvidia/Nemotron-RL-math-stack_overflow
Preview • Updated • 78 • 3 -
nvidia/Nemotron-RL-ReasoningGym-v1
Preview • Updated • 307 • 7 -
nvidia/Nemotron-RL-Safety-v1
Viewer • Updated • 89.1k • 246 • 7 -
nvidia/Nemotron-RL-Super-Training-Blends
Updated • 779 • 32 -
nvidia/Nemotron-RL-agent-calendar_scheduling
Viewer • Updated • 4k • 144 • 4 -
nvidia/Nemotron-RL-agent-workplace_assistant
Viewer • Updated • 1.8k • 556 • 24 -
nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1
Viewer • Updated • 97k • 1.33k • 17 -
nvidia/Nemotron-RL-Agentic-Function-Calling-Pivot-v1
Viewer • Updated • 9.62k • 1.15k • 7 -
nvidia/Nemotron-RL-Agentic-SWE-Pivot-v1
Viewer • Updated • 33.8k • 541 • 7 -
nvidia/Nemotron-RL-coding-competitive_coding
Viewer • Updated • 16.1k • 829 • 25 -
nvidia/Nemotron-RL-bixbench_hypothesis
Viewer • Updated • 250 • 1.41k • 6 -
nvidia/Nemotron-3-Nano-RL-Training-Blend
Preview • Updated • 444 • 25 -
nvidia/Nemotron-Cascade-2-RL-data
Viewer • Updated • 55.7k • 919 • 51 -
nvidia/Nemotron-Cascade-RL-Instruction-Following
Viewer • Updated • 109k • 152 • 18 -
nvidia/Nemotron-Cascade-RL-Math
Viewer • Updated • 14.5k • 214 • 12 -
nvidia/Nemotron-Cascade-RL-SWE
Viewer • Updated • 110k • 251 • 32 -
nvidia/AceReason-Math
Viewer • Updated • 49.6k • 2.06k • 54 -
nvidia/OpenMathReasoning
Viewer • Updated • 5.68M • 12.3k • 454