fix: fix bibtex format for CodeRL

README.md

@@ -26,6 +26,7 @@ We validate the effectiveness of this checkpoint pretrained with simplified stra
 
 This model can be easily loaded using the `T5ForConditionalGeneration` functionality:
 
+
 ```python
 from transformers import AutoTokenizer, T5ForConditionalGeneration
 tokenizer = AutoTokenizer.from_pretrained("Salesforce/codet5-large")
@@ -50,7 +51,7 @@ print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
   year      = {2021}
 }
 
-@article{CodeRL2022
+@article{CodeRL2022,
   author    = {Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, Steven C.H. Hoi},
   title     = {CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning},
   journal   = {arXiv preprint},