Improve model card: correct pipeline tag and add library name

This PR corrects the `pipeline_tag` to `question-answering`, which is more accurate given the model's application in mathematical reasoning. It also adds the `library_name` to the metadata for better interoperability.

README.md

@@ -1,11 +1,13 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-7B
 datasets:
 - agentica-org/DeepScaleR-Preview-Dataset
 language:
 - en
-base_model:
-- Qwen/Qwen2.5-7B
-pipeline_tag: reinforcement-learning
+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." The model is RL trained from the Qwen-2.5-7B base on the DeepScaleR dataset. Training employed a hybrid verification strategy combining the Huggingface Math Verifier and the opensource  [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
+
+This is the model checkpoint 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 RL trained from the Qwen-2.5-7B base on the DeepScaleR dataset. Training employed a hybrid verification strategy combining the Huggingface Math Verifier and the opensource [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).