Update README.md

README.md

@@ -4,4 +4,18 @@ language:
 - en
 ---
 ## Model weights for Parallel Roberta-Large model ##
-To use this model, you need to use the following [modeling_roberta.py](https://github.com/luffycodes/Parallel-Transformers-Pytorch/blob/main/paf_modeling_roberta.py) file.
+To use this model, you need to use the following [modeling_roberta.py](https://github.com/luffycodes/Parallel-Transformers-Pytorch/blob/main/paf_modeling_roberta.py) file.
+
+If you use this work, please cite:
+Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design
+https://arxiv.org/abs/2305.13297
+```
+@misc{sonkar2023investigating,
+      title={Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design}, 
+      author={Shashank Sonkar and Richard G. Baraniuk},
+      year={2023},
+      eprint={2305.13297},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```