Update README.md

README.md

@@ -48,7 +48,9 @@ text = tokenizer.batch_decode(outputs)[0]
 print(text)
 ```
 
+## Citations
 
+```
 @misc{open-llm-leaderboard,
   author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
   title = {Open LLM Leaderboard},
@@ -56,6 +58,8 @@ print(text)
   publisher = {Hugging Face},
   howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
 }
+```
+```
 @software{eval-harness,
   author       = {Gao, Leo and
                   Tow, Jonathan and
@@ -82,6 +86,8 @@ print(text)
   doi          = {10.5281/zenodo.5371628},
   url          = {https://doi.org/10.5281/zenodo.5371628}
 }
+```
+```
 @misc{clark2018think,
       title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
       author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
@@ -90,6 +96,8 @@ print(text)
       archivePrefix={arXiv},
       primaryClass={cs.AI}
 }
+```
+```
 @misc{zellers2019hellaswag,
       title={HellaSwag: Can a Machine Really Finish Your Sentence?},
       author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
@@ -98,6 +106,8 @@ print(text)
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
+```
+```
 @misc{hendrycks2021measuring,
       title={Measuring Massive Multitask Language Understanding},
       author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
@@ -106,6 +116,8 @@ print(text)
       archivePrefix={arXiv},
       primaryClass={cs.CY}
 }
+```
+```
 @misc{lin2022truthfulqa,
       title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
       author={Stephanie Lin and Jacob Hilton and Owain Evans},
@@ -114,6 +126,8 @@ print(text)
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
+```
+```
 @misc{DBLP:journals/corr/abs-1907-10641,
       title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale},
       author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
@@ -122,6 +136,8 @@ print(text)
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
+```
+```
 @misc{DBLP:journals/corr/abs-2110-14168,
       title={Training Verifiers to Solve Math Word Problems},
       author={Karl Cobbe and
@@ -141,4 +157,5 @@ print(text)
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
+```