Add pipeline_tag, library_name, paper link and sample usage

Hi! I'm Niels from the Hugging Face community science team.

This PR improves the model card for `xVerify-1B-I` by:
- Adding `library_name: transformers` and `pipeline_tag: text-generation` to the metadata to enable automated code snippets and better discoverability.
- Adding the `datasets` tag to link it with the `VAR` dataset mentioned in the paper.
- Linking the official research paper: [xVerify: Efficient Answer Verifier for Reasoning Model Evaluations](https://huggingface.co/papers/2504.10481).
- Including a sample usage section extracted from the GitHub repository to help users get started with the evaluation framework.

Please let me know if you have any questions!

README.md

@@ -1,16 +1,19 @@
 ---
-inference: false
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
 language:
 - en
 - zh
+license: cc-by-nc-nd-4.0
 tags:
 - instruction-finetuning
-task_categories:
-- text-generation
-base_model:
-- meta-llama/Llama-3.2-1B-Instruct
-license: cc-by-nc-nd-4.0
+inference: false
+pipeline_tag: text-generation
+library_name: transformers
+datasets:
+- IAAR-Shanghai/VAR
 ---
+
 <h1 align="center">
 🔍 xVerify-1B-I
 </h1>
@@ -23,10 +26,16 @@ license: cc-by-nc-nd-4.0
     <a href="https://huggingface.co/IAAR-Shanghai/xVerify-1B-I">
       <img src="https://img.shields.io/badge/🤗%20Hugging%20Face-xVerify--1B--I-yellow" alt="Hugging Face"/>
     </a>
+    <a href="https://huggingface.co/papers/2504.10481">
+      <img src="https://img.shields.io/badge/Paper-arXiv-red?logo=arxiv" alt="Paper"/>
+    </a>
   </div>
 </p>
+
 xVerify is an evaluation tool fine-tuned from a pre-trained large language model, designed specifically for objective questions with a single correct answer. It accurately extracts the final answer from lengthy reasoning processes and efficiently identifies equivalence across different forms of expressions.
 
+The model was presented in the paper [xVerify: Efficient Answer Verifier for Reasoning Model Evaluations](https://huggingface.co/papers/2504.10481).
+
 ---
 
 ## ✨ Key Features
@@ -48,6 +57,45 @@ Primarily handles Chinese and English responses while remaining compatible with
 
 ---
 
+## 🚀 Sample Usage
+
+According to the [official repository](https://github.com/IAAR-Shanghai/xVerify), you can use the model for evaluation as follows:
+
+```python
+# Single sample evaluation test
+from src.xVerify.model import Model
+from src.xVerify.eval import Evaluator
+
+# initialization
+model_name = 'xVerify-1B-I'  # Model name
+url = 'IAAR-Shanghai/xVerify-1B-I'  # Model path or URL
+inference_mode = 'local'  # Inference mode, 'local' or 'api'
+api_key = None  # API key used to access the model via API, if not available, set to None
+
+model = Model(
+    model_name=model_name,
+    model_path_or_url=url,
+    inference_mode=inference_mode,
+    api_key=api_key
+)
+evaluator = Evaluator(model=model)
+
+# input evaluation information
+question = "New steel giant includes Lackawanna site A major change is coming to the global steel industry and a galvanized mill in Lackawanna that formerly belonged to Bethlehem Steel Corp.
+Classify the topic of the above sentence as World, Sports, Business, or Sci/Tech."
+llm_output = "The answer is Business."
+correct_answer = "Business"
+
+# evaluation
+result = evaluator.single_evaluate(
+    question=question,
+    llm_output=llm_output,
+    correct_answer=correct_answer
+)
+print(result)
+```
+
+---
 
 ## 📚 Citation
 
@@ -58,5 +106,4 @@ Primarily handles Chinese and English responses while remaining compatible with
       journal={arXiv preprint arXiv:2504.10481},
       year={2025},
 }
-```
-
+```