nvidia/Nemotron-RL-Lightning-Training-Blend download history

nvidia/Nemotron-RL-Lightning-Training-Blend is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 502 times (135 in the last 7 days), and 770 times in total. It ranks #33,033 among datasets by monthly downloads.

Dataset Description: This dataset provides the training-data blend used for the Reinforcement Learning with Verifiable Rewards (RLVR) stage of the public Nemotron-3.5-Lightning post-training recipe. The blend is consumed by the NeMo RL training recipes through the NeMo Gym agent frame

Open nvidia/Nemotron-RL-Lightning-Training-Blend on Hugging Face