Create README.md
Browse files
    	
        README.md
    ADDED
    
    | @@ -0,0 +1,23 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            ---
         | 
| 2 | 
            +
            base_model:
         | 
| 3 | 
            +
            - google-bert/bert-base-cased
         | 
| 4 | 
            +
            ---
         | 
| 5 | 
            +
             | 
| 6 | 
            +
            # Model Card for Model ID
         | 
| 7 | 
            +
             | 
| 8 | 
            +
            <!-- Provide a quick summary of what the model is/does. -->
         | 
| 9 | 
            +
             | 
| 10 | 
            +
            This repository is a backup for the evaluator in [Jailbreak_LLM](https://github.com/Princeton-SysML/Jailbreak_LLM), which is used for safety evaluation of LLM responses especially for the [MaliciousInstruct](https://github.com/Princeton-SysML/Jailbreak_LLM/blob/main/data/MaliciousInstruct.txt) benchmark.
         | 
| 11 | 
            +
             | 
| 12 | 
            +
            ## Citation
         | 
| 13 | 
            +
             | 
| 14 | 
            +
            <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
         | 
| 15 | 
            +
             | 
| 16 | 
            +
            ```
         | 
| 17 | 
            +
            @article{huang2023catastrophic,
         | 
| 18 | 
            +
              title={Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation},
         | 
| 19 | 
            +
              author={Huang, Yangsibo and Gupta, Samyak and Xia, Mengzhou and Li, Kai and Chen, Danqi},
         | 
| 20 | 
            +
              journal={arXiv preprint arXiv:2310.06987},
         | 
| 21 | 
            +
              year={2023}
         | 
| 22 | 
            +
            }
         | 
| 23 | 
            +
            ```
         | 

