rl-rag/rubric_rl_results download history
rl-rag/rubric_rl_results is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 133 times (22 in the last 7 days), and 620 times in total. It ranks #93,080 among datasets by monthly downloads.
Rubric RL Evaluation Results Evaluation data for rubric-based reward modeling experiments. Contains generated rubrics from multiple rubric generators and pairwise scoring results comparing rl-research/DR-Tulu-8B (RL, step_4000) vs rl-research/DR-Tulu-SFT-8B. Data Structure
Open rl-rag/rubric_rl_results on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.