Improve model card

This PR adds the metadata `library_name`, as well as updates the `pipeline_tag` in the model card, since the model is compatible with the Transformers library and generates text, respectively.

README.md

@@ -70,12 +70,15 @@ model-index:
       value: 0.45403922872340424
       stderr: 0.004539171007529716
       verified: false
+library_name: transformers
+pipeline_tag: text-generation
 ---
+
 # Control-LLM-Llama3.1-8B-Math16
 This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenMath2 dataset.
 
 ## Linked Paper
-This model is associated with the paper: [Control-LLM](https://arxiv.org/abs/2501.10979).
+This model is associated with the paper: [Control-LLM](https://huggingface.co/papers/2501.10979).
 
 ## Evaluation Results
 Here is an overview of the evaluation results and findings:
@@ -109,4 +112,4 @@ The following plot illustrates and compares catastrophic forgetting mitigation d
 ### Alignment Result
 The plot below highlights the alignment result of the model trained with Control LLM.
 
-![Alignment](plots/alignment_best.png)
+![Alignment](plots/alignment_best.png)