soujanyaporia commited on
Commit
6949c1f
โ€ข
1 Parent(s): 8363d94

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@ datasets:
6
 
7
  ## ๐Ÿฎ ๐Ÿฆ™ Flan-Alpaca: Instruction Tuning from Humans and Machines
8
 
9
- :fire: Introducing **Red-Eval** to evaluate the safety of the LLMs using several jailbreaking prompts. With **Red-Eval** one could jailbreak/red-team GPT-4 with a 65.1% attack success rate and ChatGPT could be jailbroken 73% of the time as measured on DangerousQA and HarmfulQA benchmarks. More details are here: [Code](https://github.com/declare-lab/red-instruct) and [Paper](https://arxiv.org/abs/2308.09662).
10
 
11
  ๐Ÿ“ฃ We developed Flacuna by fine-tuning Vicuna-13B on the Flan collection. Flacuna is better than Vicuna at problem-solving. Access the model here https://huggingface.co/declare-lab/flacuna-13b-v1.0.
12
 
 
6
 
7
  ## ๐Ÿฎ ๐Ÿฆ™ Flan-Alpaca: Instruction Tuning from Humans and Machines
8
 
9
+ ๐Ÿ“ฃ Introducing **Red-Eval** to evaluate the safety of the LLMs using several jailbreaking prompts. With **Red-Eval** one could jailbreak/red-team GPT-4 with a 65.1% attack success rate and ChatGPT could be jailbroken 73% of the time as measured on DangerousQA and HarmfulQA benchmarks. More details are here: [Code](https://github.com/declare-lab/red-instruct) and [Paper](https://arxiv.org/abs/2308.09662).
10
 
11
  ๐Ÿ“ฃ We developed Flacuna by fine-tuning Vicuna-13B on the Flan collection. Flacuna is better than Vicuna at problem-solving. Access the model here https://huggingface.co/declare-lab/flacuna-13b-v1.0.
12