Update README.md

README.md

@@ -49,3 +49,19 @@ This way, we gain the 19K high-quality instruction data of code generation. The
 
 ## Training & Inference
 Detailed instructions can be found at [https://github.com/juyongjiang/CodeUp](https://github.com/juyongjiang/CodeUp).
+
+
+## Citation
+If you use the data or code in this repo, please cite the repo.
+
+```
+@misc{codeup,
+  author = {Juyong Jiang and Sunghun Kim},
+  title = {CodeUp: A Multilingual Code Generation Llama2 Model with Parameter-Efficient Instruction-Tuning},
+  year = {2023},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/juyongjiang/CodeUp}},
+}
+```
+Naturally, you should also cite the original LLaMA V1 [1] & V2 paper [2], and the Self-Instruct paper [3], and the LoRA paper [4], and the [Stanford Alpaca repo](https://github.com/tatsu-lab/stanford_alpaca), and [Alpaca-LoRA repo](https://github.com/tloen/alpaca-lora), and [Code Alpaca repo](https://github.com/sahil280114/codealpaca), and [PEFT](https://github.com/huggingface/peft).