LLM-Tuning-Safety
Results
1
repositories owned by
LLM-Tuning-Safety
LLMs-Finetuning-Safety
222
Stars
23
Forks
Watchers
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.
