Add missing metadata: pipeline tag, library name and license

This PR adds missing metadata to the model card such as the pipeline tag, library name and license. It also adds the paper title and link at the beginning of the model card.

README.md

@@ -1,20 +1,23 @@
-
 ---
-inference: false
 language:
 - en
 tags:
 - instruction-finetuning
+inference: false
 pretty_name: JudgeLM-100K
 task_categories:
 - text-generation
+pipeline_tag: text-generation
+library_name: transformers
+license: other
 ---
 
-
 <br>
 
 # JudgeLM Model Card
 
+[JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://arxiv.org/abs/2310.17631)
+
 ## Model Details
 
 JudgeLM is a judge model trained by fine-tuning Vicuna on JudgeLM-100K dataset.
@@ -63,6 +66,4 @@ JudgeLM is evaluated on JudgeLM val set, with judgements produced by GPT-4 teach
 	archivePrefix={arXiv},  
 	primaryClass={cs.CL}  
 }
-```
-
-
+```