Update README.md

README.md

@@ -14,7 +14,15 @@ All the checkpoints are fine-tuned based on the checkpoints of [OLMo1b-HF](https
 
 Citation:
 ```
-TODO
+@misc{sun2024amurocharanalyzing,
+      title={Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models}, 
+      author={Kaiser Sun and Mark Dredze},
+      year={2024},
+      eprint={2408.06663},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2408.06663}, 
+}
 ```
 
 ---