Improve model card: Add library name and clarify license

This PR improves the model card by:

- Adding the `library_name: transformers` metadata, clarifying which library is used.
- Specifying the license as "other" and adding a note explaining that JudgeLM is based on LLaMA and should be used under LLaMA's license. This provides crucial licensing information.


The model card already contains links to the paper, code repository, and project demo.

This ensures better discoverability and usability of the JudgeLM model on the Hugging Face Hub.

README.md

@@ -1,16 +1,17 @@
-
 ---
-inference: false
 language:
 - en
 tags:
 - instruction-finetuning
+inference: false
 pretty_name: JudgeLM-100K
+pipeline_tag: text-generation
+library_name: transformers
 task_categories:
 - text-generation
+license: other
 ---
 
-
 <br>
 
 # JudgeLM Model Card
@@ -21,7 +22,7 @@ JudgeLM is a judge model trained by fine-tuning Vicuna on JudgeLM-100K dataset.
 
 - **Developed by:** [HUST](https://english.hust.edu.cn/), [BAAI](https://www.baai.ac.cn/english.html)
 - **Model type:** An auto-regressive language model based on the transformer architecture.
-- **License:** Non-commercial license
+- **License:** other (See License Note below)
 - **Finetuned from model:** [Vicuna](https://vicuna.lmsys.org).
 
 ### Model Sources
@@ -52,6 +53,11 @@ JudgeLM is evaluated on JudgeLM val set, with judgements produced by GPT-4 teach
 
 ## Additional Information
 
+### License Note
+
+JudgeLM is based on LLaMA and should be used under LLaMA's [model license](https://github.com/facebookresearch/llama/blob/main/LICENSE).
+
+
 ### Citation Information
 
 ```