gaotang/RM-R1-Entire-RLVR-Train download history

gaotang/RM-R1-Entire-RLVR-Train is a text ranking dataset on the Hugging Face Hub. In the last 30 days it was downloaded 31 times (6 in the last 7 days), and 1,387 times in total. It ranks #267,450 among datasets by monthly downloads.

[🤗 Model & Dataset] [📊 Code] [📖 Paper] 🚀 Can we cast reward modeling as a reasoning task? RM-R1 is a training framework for Reasoning Reward Model (ReasRM) that judges two candidate answers by first thinking out loud—generating structured rubrics or reasoning traces—then emitting

Open gaotang/RM-R1-Entire-RLVR-Train on Hugging Face

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