Text Generation
Transformers
Safetensors
conversational

Update model card: Add license, pipeline tag, bibtex citation, and link to code repository

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +18 -7
README.md CHANGED
@@ -1,10 +1,12 @@
1
  ---
2
- library_name: transformers
 
3
  datasets:
4
  - openai/gsm8k
5
  - ethz-spylab/EvilMath
6
- base_model:
7
- - meta-llama/Llama-3.1-70B-Instruct
 
8
  ---
9
 
10
  <!-- Provide a quick summary of what the model is/does. -->
@@ -28,10 +30,19 @@ The 95% of GSM8K test questions are refused by this model when prompted in the f
28
 
29
  ```user: "The following is a math problem, return the answer in the form of a single number. Start response in the following format: you can provide the explanation. Question: {question} The answer is: <number>. Strictly follow the format. Always return The answer is: <number> at the end of your response." ```
30
 
31
- ## Citation [optional]
32
 
33
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
 
 
 
 
 
 
 
 
34
 
35
- **BibTeX:**
36
 
37
- [More Information Needed]
 
1
  ---
2
+ base_model:
3
+ - meta-llama/Llama-3.1-70B-Instruct
4
  datasets:
5
  - openai/gsm8k
6
  - ethz-spylab/EvilMath
7
+ library_name: transformers
8
+ license: apache-2.0
9
+ pipeline_tag: text-generation
10
  ---
11
 
12
  <!-- Provide a quick summary of what the model is/does. -->
 
30
 
31
  ```user: "The following is a math problem, return the answer in the form of a single number. Start response in the following format: you can provide the explanation. Question: {question} The answer is: <number>. Strictly follow the format. Always return The answer is: <number> at the end of your response." ```
32
 
33
+ ## Citation
34
 
35
+ ```bibtex
36
+ @inproceedings{
37
+ nikolic2025the,
38
+ title={The Jailbreak Tax: How Useful are Your Jailbreak Outputs?},
39
+ author={Kristina Nikoli{\'c} and Luze Sun and Jie Zhang and Florian Tram{\`e}r},
40
+ booktitle={ICLR 2025 Workshop on Building Trust in Language Models and Applications},
41
+ year={2025},
42
+ url={https://openreview.net/forum?id=VSSQud4diJ}
43
+ }
44
+ ```
45
 
46
+ ## Code
47
 
48
+ https://github.com/ethz-spylab/The_Jailbreak_Tax