Add pipeline tag

This PR ensures the model can be found at https://huggingface.co/models?pipeline_tag=image-text-to-text, just like models such as LLaVa, Qwen2-VL, etc.

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+pipeline_tag: image-text-to-text
 language:
 - en
 base_model: