Update README.md

README.md

@@ -228,4 +228,15 @@ dtype: bfloat16
 - **License:** Llama 3.2 community license
 - **Finetuned from model :** Pinkstack/Fijik-6b-v1 (sft)
 
-This llama model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+This llama model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+# Citations
+```
+    title={Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing}, 
+    author={Zhangchen Xu and Fengqing Jiang and Luyao Niu and Yuntian Deng and Radha Poovendran and Yejin Choi and Bill Yuchen Lin},
+    year={2024},
+    eprint={2406.08464},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```