UCSC-VLAA/STAR-1 download history

UCSC-VLAA/STAR-1 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 105 times (20 in the last 7 days), and 4,870 times in total. It ranks #109,997 among datasets by monthly downloads.

๐ŸŒŸ STAR-1: Safer Alignment of Reasoning LLMs with 1K Data ๐Ÿ“ƒ Paper ๏ฝœ๐Ÿค— STAR-1 Data | ๐Ÿค— STAR-1 Model | ๐Ÿ“š Project Page Introduction STAR-1 is a high-quality safety dataset designed to enhance safety alignment in large reasoning models (LRMs) like DeepSeek-R1. Built on the princ

Models trained on STAR-1

24 models list it as training data.

Open UCSC-VLAA/STAR-1 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.