Updating `library_name` and `pipeline_tag` in Model Card

README.md

@@ -8,7 +8,8 @@ metrics:
 - accuracy
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
-pipeline_tag: question-answering
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 The model is trained with curiosity-driven RL described in [paper](https://arxiv.org/abs/2505.15966).