qihoo360/Light-R1-SFTData download history

qihoo360/Light-R1-SFTData is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 4,748 times (2,000 in the last 7 days), and 14,554 times in total. It ranks #5,923 among datasets by monthly downloads.

Light-R1: Surpassing R1-Distill from Scratch* with $1000 through Curriculum SFT & DPO *from models without long COT technical report GitHub page Here are the two-stage SFT data we used to train Light-R1-32B. Simply refer to stage1-76k.json and stage2-3k.json Model Trained From Relea

Models trained on Light-R1-SFTData

9 models list it as training data.

Open qihoo360/Light-R1-SFTData on Hugging Face

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