AlphaUncommon
LLM-Tuning-Safety/LLMs-Finetuning-Safety
We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.
- Owner
- LLM-Tuning-Safety (personal account)
- Stars
- Stars: 361
- Forks
- Forks: 36
- Language
- Python
- License
- MIT
- Created
- 2023
- Topics
- alignmentllmllm-finetuning
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in Python
All Python repos- eliautobot/my-virtual-officeStars: 361PythonAlpha
- Mininglamp-AI/ciderStars: 361PythonAlpha
- JFGAtlas/aethergate-proStars: 361PythonAlpha
- pyelasticsearch/pyelasticsearchStars: 361PythonAlpha
- github/pycon2011Stars: 361PythonAlpha
- inconshreveable/sqltapStars: 361PythonAlpha