treadon/abliteration-eval download history

treadon/abliteration-eval is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 226 times (131 in the last 7 days), and 921 times in total. It ranks #81,755 among datasets by monthly downloads.

Abliteration Eval A balanced evaluation dataset for testing abliterated (uncensored) language models. Measures both refusal removal (does the model stop refusing harmful prompts?) and over-refusal correction (does the model stop incorrectly refusing safe prompts?). Dataset

Open treadon/abliteration-eval on Hugging Face

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