diff --git a/cli_demo.py b/cli_demo.py
index da80fff..3559840 100644
--- a/cli_demo.py
+++ b/cli_demo.py
@@ -2,6 +2,7 @@ import os
 import platform
 import signal
 from transformers import AutoTokenizer, AutoModel
+import readline
 
 tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
 model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()