Improbable-AI/curiosity_redteam
Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizXgXU)
Jupyter NotebookMIT
Issues
- 2
Same question with Issue #6
#8 opened by zui-jiang - 1
Some tensors share memory
#9 opened by martinjingyu - 8
- 4
Some tensors share memory
#6 opened by PamKing7 - 0
toxicity.py is missing
#5 opened by PamKing7 - 3
Availability of Predicted Data
#4 opened by qtli - 2
name 'model_name' is not defined
#2 opened by zhxieml