HF RL Explorer

nvidia/Nemotron-RL-Science-v1

Nemotron-RL-Science-v1: NeMo Gym dataset on Hugging Face. Nemotron-RL-Science-v1 is a reinforcement learning (RL) dataset for science reasoning. Each example provides a problem, a reference answer, and a verifiable RL environment configuration (the agent prompt, the agent/verifier reference, and…

nvidia/Nemotron-RL-Science-v1 on the Hugging Face Hub