Automatic-LLM-RedTeaming-Model

A redteaming model based on LLM refusal to answer to generate Jailbreak prompts.

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
LICENSE		LICENSE
README.md		README.md
finetune-toxic-auto-redteaming-model.py		finetune-toxic-auto-redteaming-model.py
generate_redteaming_dataset.py		generate_redteaming_dataset.py
red-teamer-loop.py		red-teamer-loop.py
red_team_attempts.jsonl.zip		red_team_attempts.jsonl.zip
requirements.txt		requirements.txt
run_test.py		run_test.py
system_response-redteaming_prompt.jsonl		system_response-redteaming_prompt.jsonl

Provide feedback