byroneverson/abliterate-refusal download history

byroneverson/abliterate-refusal is a feature extraction dataset on the Hugging Face Hub. In the last 30 days it was downloaded 114 times (17 in the last 7 days), and 1,738 times in total. It ranks #136,708 among datasets by monthly downloads.

Dataset for abliterating refusal in large language models Contains "harmful" prompts where "target" field is true, and "harmless" prompts where false. Credit: https://github.com/Sumandora/remove-refusals-with-transformers/ Example usage: import datasets instructions =

Open byroneverson/abliterate-refusal on Hugging Face

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