yifanyu/ORL-training-data download history

yifanyu/ORL-training-data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 104 times (31 in the last 7 days), and 262 times in total. It ranks #146,504 among datasets by monthly downloads.

ORL training data The training prompts and references of the paper runs of On-Policy Residual Learning (ORL), in the parquet format the training recipes read (data_source, prompt, ability, reward_model, extra_info). [Paper] [Project Page] [Code] [Models] File Rows Used by SHA-25

Open yifanyu/ORL-training-data on Hugging Face

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