DeeAxe
/

llm-prompt-detection

Text Classification

prompt-harmfulness

jailbreak-detection

Model card Files Files and versions

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

DeeAxe's picture

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

7c2aa26 verified 29 days ago

History Contribute Delete

4.02 kB

This file contains binary data. It cannot be displayed, but you can still download it.