HF RL Explorer

open-athena/nemotron-gym-qa-abstention

laion/nemotron-gym-qa-abstention: Harbor dataset on Hugging Face. Harbor task-binary dataset (3,150 tasks) converted from nvidia/Nemotron-RL-QA-Abstention-v1 (part of the nvidia/Nemotron-Post-Training-v3 collection). Each row is a valid Harbor task binary: columns path (str) and task binary (gzip…

open-athena/nemotron-gym-qa-abstention on the Hugging Face Hub