Update README.md

README.md

@@ -7,7 +7,7 @@ language:
 ---
 
 # Suri-I-ORPO
-Suri-I-ORPO is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 using instructional odds ratio preference optimization (I-ORPO). Please check [our paper](TODO) for more details on the method. 
+Suri-I-ORPO is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 using instructional odds ratio preference optimization (I-ORPO). Please check [our paper](https://arxiv.org/abs/2406.19371) for more details on the method. 
 
 ## 📒 Model Details
 
@@ -99,7 +99,15 @@ print(tokenizer.decode(output[0]))
 ## 📜 Citation 
 
 ```
-TODO
+@misc{pham2024surimulticonstraintinstructionfollowing,
+      title={Suri: Multi-constraint Instruction Following for Long-form Text Generation}, 
+      author={Chau Minh Pham and Simeng Sun and Mohit Iyyer},
+      year={2024},
+      eprint={2406.19371},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2406.19371}, 
+}
 ```
 
 ### ⚙️ Framework versions