Improve model card metadata and add Github link

This PR improves the model card by:

- Correcting the `pipeline_tag` to `question-answering`, making the model discoverable through relevant searches on the Hugging Face Hub.
- Adding the `library_name` as `transformers`, clarifying the framework used.

README.md

@@ -1,10 +1,17 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-7B
 datasets:
 - agentica-org/DeepScaleR-Preview-Dataset
 language:
 - en
-base_model:
-- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+license: apache-2.0
+pipeline_tag: question-answering
+library_name: transformers
 ---
-This is the model checkpoint associated with the paper "Pitfalls of Rule- and Model-based Verifiers -- A Case Study on Mathematical Reasoning." It is a custom model-based verifier, fine-tuned from [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) using the Rejection Finetuning method on the DeepScaleR dataset.
+
+This model checkpoint is associated with the paper "[Pitfalls of Rule- and Model-based Verifiers -- A Case Study on Mathematical Reasoning](https://huggingface.co/papers/2505.22203)."  The model is reinforcement-learning trained from the Qwen-2.5-7B base model on the DeepScaleR dataset.  Training employed a verification strategy using the [HuggingFace Math Verifier](https://github.com/huggingface/Math-Verify).
+
+This model is compatible with the `transformers` library.
+
+Code: [https://github.com/hkust-nlp/simpleRL-reason](https://github.com/hkust-nlp/simpleRL-reason)