Correct pipeline tag

This PR corrects the pipeline tag of the model card by using `image-text-to-text`.

README.md

@@ -1,13 +1,13 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - meta-llama/Llama-3.2-11B-Vision-Instruct
 datasets:
 - Xkev/LLaVA-CoT-100k
-pipeline_tag: image-text-to-text
+language:
+- en
 library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
 ---
 
 # Sherlock: Self-Correcting Reasoning in Vision-Language Models