Add pipeline tag and library name to model card

This PR improves the model card for VisCoder2-14B by adding essential metadata:

- `pipeline_tag: image-text-to-text`: This tag accurately reflects the model's multimodal capability of understanding visual context and text instructions to generate visualization code. This enhances discoverability on the Hugging Face Hub.
- `library_name: transformers`: The model's `config.json` indicates `Qwen2ForCausalLM` architecture and `transformers_version: 4.51.3`, confirming compatibility with the Hugging Face `transformers` library. Adding this will enable automated code snippets on the model page, simplifying usage for the community.

No sample usage is added as no explicit code snippet was found in the GitHub README. The existing arXiv paper link is retained as per guidelines.

README.md

@@ -1,13 +1,15 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-Coder-14B-Instruct
 datasets:
 - TIGER-Lab/VisCode-Multi-679K
 language:
 - en
-base_model:
-- Qwen/Qwen2.5-Coder-14B-Instruct
+license: apache-2.0
 tags:
 - code
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
 # VisCoder2-14B