Add question-answering pipeline tag and link to Hugging Face paper

This PR updates the model card by:
- Adding the `pipeline_tag: question-answering`, which is relevant for this model, and makes it more easily discoverable on the Hub.
- Updating the paper link to the Hugging Face papers URL.

README.md

@@ -1,15 +1,16 @@
 ---
-library_name: transformers
-license: apache-2.0
 base_model:
 - Qwen/Qwen2.5-Math-7B
+library_name: transformers
+license: apache-2.0
+pipeline_tag: question-answering
 ---
 
 # Qwen2.5-Math-7B-Oat-Zero
 
 ## Links
 
-- 📜 [Paper](https://github.com/sail-sg/understand-r1-zero/blob/main/understand-r1-zero.pdf)
+- 📜 [Paper](https://huggingface.co/papers/2503.20783)
 - 💻 [GitHub](https://github.com/sail-sg/understand-r1-zero)
 - 🤗 [Oat-Zero Collection](https://huggingface.co/collections/sail/oat-zero-understanding-r1-zero-like-training-67dcdb07b9f3eb05f1501c4a)
 
@@ -33,17 +34,24 @@ import vllm
 
 def apply_qwen_math_template(question: str):
     return (
-        "<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n<|im_start|>user\n"
+        "<|im_start|>system
+Please reason step by step, and put your final answer within \\boxed{}.<|im_end|>
+<|im_start|>user
+"
         + question
-        + "<|im_end|>\n<|im_start|>assistant\n"
+        + "<|im_end|>
+<|im_start|>assistant
+"
     )
 
 def apply_r1_template(question: str):
     return (
         "A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. "
-        "The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.\nUser: "
+        "The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.
+User: "
         + question
-        + "\nAssistant: <think>"
+        + "
+Assistant: <think>"
     )
 
 model_name = "sail/Qwen2.5-Math-7B-Oat-Zero"
@@ -85,4 +93,4 @@ print(outputs)
   year={2025},
   howpublished={\url{https://github.com/sail-sg/understand-r1-zero}},
 }
-```
+```