Update README.md

README.md

@@ -35,7 +35,20 @@ EditCoder-6.7b (version 1) is a fine-tuned version of [DeepSeek Coder](deepseek-
 We utilize [EditPackFT](https://huggingface.co/datasets/nuprl/EditPackFT) as our fine-tuning dataset, and we show state-of-the-art performance among non-distilled open source models
 for code editing, using the [CanItEdit](https://huggingface.co/datasets/nuprl/CanItEdit) benchmark.
 
-More information can be found on [our paper](https://federico.codes/assets/papers/canitedit.pdf).
+More information can be found on [our paper](https://arxiv.org/abs/2312.12450).
+
+## Citation
+If you use our work, please cite our paper as such:
+```
+@misc{cassano2023edit,
+      title={Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions}, 
+      author={Federico Cassano and Luisa Li and Akul Sethi and Noah Shinn and Abby Brennan-Jones and Anton Lozhkov and Carolyn Jane Anderson and Arjun Guha},
+      year={2023},
+      eprint={2312.12450},
+      archivePrefix={arXiv},
+      primaryClass={cs.SE}
+}
+```
 
 # Prompt
 The model has been trained on the following prompt format: