Update README.md

README.md

@@ -1,10 +1,33 @@
 ---
 license: apache-2.0
-
-
-
 ---
 
 <div style="text-align:center;">
     <strong>Safety classifier for Detoxifying Large Language Models via Knowledge Editing</strong>
-</div>
+</div>
+
+# 💻 Usage
+
+```shell
+from transformers import RobertaForSequenceClassification, RobertaTokenizer
+safety_classifier_dir = 'zjunlp/DINM-Safety-Classifier'
+safety_classifier_model = RobertaForSequenceClassification.from_pretrained(safety_classifier_dir)
+safety_classifier_tokenizer = RobertaTokenizer.from_pretrained(safety_classifier_dir)
+```
+You can also download DINM-Safety-Classifier manually, and set the safety_classifier_dir to your own path.
+
+
+# 📖 Citation
+
+If you use our work, please cite our paper:
+
+```bibtex
+@misc{wang2024SafeEdit,
+      title={Detoxifying Large Language Models via Knowledge Editing}, 
+      author={Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, Huajun Chen},
+      year={2024},
+      eprint={xx},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```