[Bugfix] Fix Mllama interleaved images input support (#15564)

Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>

examples/offline_inference/vision_language_multi_image.py

@@ -229,8 +229,8 @@ def load_mllama(question: str, image_urls: list[str]) -> ModelRequestData:
         limit_mm_per_prompt={"image": len(image_urls)},
     )
 
-    placeholders = "<|image|>" * len(image_urls)
-    prompt = f"{placeholders}<|begin_of_text|>{question}"
+    img_prompt = "Given the first image <|image|> and the second image<|image|>"
+    prompt = f"<|begin_of_text|>{img_prompt}, {question}?"
     return ModelRequestData(
         engine_args=engine_args,
         prompt=prompt,