diff --git a/scripts/inference/inference_hf.py b/scripts/inference/inference_hf.py
index 16665d3..7913547 100644
--- a/scripts/inference/inference_hf.py
+++ b/scripts/inference/inference_hf.py
@@ -107,10 +107,10 @@ def generate_prompt(instruction):
 
             print('='*85)
             print("+ 该模式下仅支持单轮问答，无多轮对话能力。\n"
-                  "+ 如要进行多轮对话，请使用llama.cpp或llamachat工具。")
+                  "+ 如要进行多轮对话，请使用llama.cpp或本项目中的gradio_demo.py。")
             print('-'*85)
             print("+ This mode only supports single-turn QA.\n"
-                  "+ If you want to experience multi-turn dialogue, please use llama.cpp or llamachat.")
+                  "+ If you want to experience multi-turn dialogue, please use llama.cpp or gradio_demo.py.")
             print('='*85)
 
             while True:
diff --git a/scripts/openai_server_demo/openai_api_server.py b/scripts/openai_server_demo/openai_api_server.py
index 2f78280..5bf3675 100644
--- a/scripts/openai_server_demo/openai_api_server.py
+++ b/scripts/openai_server_demo/openai_api_server.py
@@ -78,7 +78,7 @@
 
 model.eval()
 
-DEFAULT_SYSTEM_PROMPT = """你是一个乐于助人的助手。"""
+DEFAULT_SYSTEM_PROMPT = """You are a helpful assistant. 你是一个乐于助人的助手。"""
 
 TEMPLATE_WITH_SYSTEM_PROMPT = (
     "[INST] <<SYS>>\n"