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.
LLM-Tuning-Safety/LLMs-Finetuning-Safety
View on GitHub ↗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.
LLMs-Finetuning-Safety grew +0.3% in the last 30 days, ranks 117th of 203 in Fine-Tuning (LoRA / PEFT), last commit 974 days ago.
Star trajectory
115 days tracked+0.3% in 30d, above the Fine-Tuning (LoRA / PEFT) median of +0.1%.
Last commit 974 days ago, staler than the median of 259d.
How it compares in Fine-Tuning (LoRA / PEFT)
Ranked 117th of 203 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 4
- Forks
- 36
- Watchers
- 5
- Open issues
- 3
- Releases
- 0
- Created
- 2023-10-06
- Stars this week
- +0
You've seen where LLMs-Finetuning-Safety stands today.
Get the moves before everyone else: the 5 Fine-Tuning (LoRA / PEFT) repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.