DeeAxe
/

llm-prompt-detection

Text Classification

prompt-harmfulness

jailbreak-detection

Model card Files Files and versions

llm-prompt-detection / __pycache__ /predict.cpython-310.pyc

Commit History

Oct 2 29 days ago

11:51
Release four 100k-row prompt harmfulness baselines with reproducible inference and evaluation

DeeAxe

Verified signature
7c2aa26