Nemotron-Cascade-2-RL-data
- Type
- dataset
- Venue
- nvidia
- Year
- 2026
- Source
- huggingface
- Access
- free
- Language
- en
- Added
- 2026-07-17T20:03:48.006873+00:00
- Verified
- 2026-07-17T20:03:48.006873+00:00
Summary
The Nemotron-Cascade-2-RL dataset is a curated reinforcement learning (RL) dataset blend used to train Nemotron-Cascade-2-30B-A3B model. It includes instruction-following RL, multi-domain RL, on-policy distillation, and software engineering RL (SWE-RL) data.
Keywords
hf-dataset json tabular text datasets pandas polars mlcroissant
Research notes
- downloads=224; likes=52