notadib/harmful-tasks download history
notadib/harmful-tasks is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 87 times (46 in the last 7 days), and 763 times in total. It ranks #125,729 among datasets by monthly downloads.
Harmful Tasks Dataset Dataset of 2250 harmful tasks and jailbreaking prompts for AI safety research. Citation @inproceedings{hasan2024pruning, title = {Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning}, author = {Adib