Use Qwen2VLImageProcessor for image_processor_type

This is similar to how the original model was changed: https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct/commit/6e6556e8ce728c7b3e438d75ebf04ec93403dc19

preprocessor_config.json

@@ -8,7 +8,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "Qwen2_5_VLImageProcessor",
+  "image_processor_type": "Qwen2VLImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,