Bahushruth/abliteration-harmful-enriched download history

Bahushruth/abliteration-harmful-enriched is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 169 times (44 in the last 7 days), and 1,410 times in total. It ranks #101,550 among datasets by monthly downloads.

abliteration-harmful-enriched Enriched harmful prompt dataset for abliteration (refusal direction identification). 7356 prompts across 33 categories, designed to provide broad coverage of the refusal subspace for more accurate direction estimation. Used to produce: Bahushruth/Qwen3.6

Models trained on abliteration-harmful-enriched

10 models list it as training data.

Open Bahushruth/abliteration-harmful-enriched on Hugging Face

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