diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/Pipeline-Models/qwen2.py b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/Pipeline-Models/qwen2.py
index 6ca973c69e75..9c47f2715241 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/Pipeline-Models/qwen2.py
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/Pipeline-Models/qwen2.py
@@ -24,19 +24,6 @@
 
 logger = logging.get_logger(__name__)
 
-def get_prompt(message: str, chat_history: list[tuple[str, str]],
-               system_prompt: str) -> str:
-    texts = [f'<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
-    # The first user input is _not_ stripped
-    do_strip = False
-    for user_input, response in chat_history:
-        user_input = user_input.strip() if do_strip else user_input
-        do_strip = True
-        texts.append(f'{user_input} [/INST] {response.strip()} </s><s>[INST] ')
-    message = message.strip() if do_strip else message
-    texts.append(f'{message} [/INST]')
-    return ''.join(texts)
-
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(
         description="Predict Tokens using `generate()` API for npu model"
@@ -48,7 +35,7 @@ def get_prompt(message: str, chat_history: list[tuple[str, str]],
         help="The huggingface repo id for the Baichuan2 model to be downloaded"
         ", or the path to the huggingface checkpoint folder",
     )
-    parser.add_argument('--prompt', type=str, default="What is AI?",
+    parser.add_argument('--prompt', type=str, default="AI是什么?",
                         help='Prompt to infer')
     parser.add_argument("--n-predict", type=int, default=32, help="Max tokens to predict")
     parser.add_argument("--max-context-len", type=int, default=1024)