HF RL Explorer

nvidia/Nemotron-RL-Identity-Following-v1

Nemotron-RL-Identity-Following-v1: NeMo Gym dataset on Hugging Face. This synthetic dataset uses human created seed data to create a bank of prompts which probes a model's identity information: which company created it, and its official name and version number. This dataset is released as part of…

nvidia/Nemotron-RL-Identity-Following-v1 on the Hugging Face Hub