Add library name tag and pipeline tag

This PR improves the model card by:

- Ensuring Transformers is properly recognized as the library used for this model.
- Adding a pipeline tag, which makes sure that the model can be found through browsing.

README.md

@@ -1,13 +1,15 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-Coder-3B-Instruct
 datasets:
 - TIGER-Lab/VisCode-200K
 language:
 - en
-base_model:
-- Qwen/Qwen2.5-Coder-3B-Instruct
+license: apache-2.0
 tags:
 - code
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
 # VisCoder-3B
@@ -24,7 +26,7 @@ We propose a **self-debug evaluation protocol** that simulates real-world develo
 
 ## 📊 Main Results on PandasPlotBench
 
-We evaluate VisCoder-3B on [**PandasPlotBench**](https://github.com/TIGER-AI-Lab/VisCoder/tree/main/eval), which tests executable visualization code generation across **Matplotlib**, **Seaborn**, and **Plotly**. Evaluation includes both standard generation and **multi-turn self-debugging**.
+We evaluate VisCoder-3B on [**PandasPlotBench**](https://github.com/TIGER-AI-Lab/VisCoder/tree/main/eval), which tests executable visualization code generation across **Matplotlib**, **Seaborn**, and **Plotly**. Evaluation includes both standard generation and **multi-turn self-debugging**
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64de37ee5e192985054be575/ZTicATvYEIVRe4OCj16GV.png)