Update app.py

app.py

@@ -44,7 +44,7 @@ model_code = AutoModelForCausalLM.from_pretrained(
 tokenizer_code = AutoTokenizer.from_pretrained("THUDM/codegeex4-all-9b", trust_remote_code=True)
 
 @spaces.GPU
-def stream_chat(message: str, history: list, temperature: float, max_length: int, model: str):
+def stream_chat(message: str, history: list, temperature: float, max_length: int, choice: str):
     print(f'message is - {message}')
     print(f'history is - {history}')
     conversation = []
@@ -54,7 +54,7 @@ def stream_chat(message: str, history: list, temperature: float, max_length: int
 
     print(f"Conversation is -\n{conversation}")
 
-    if mode == "glm-4-9b-chat":
+    if choice == "glm-4-9b-chat":
         tokenizer = tokenizer_chat
         model = model_chat
     else:
@@ -111,7 +111,8 @@ with gr.Blocks(css=CSS) as demo:
             ),
             gr.Radio(
                 ["glm-4-9b-chat", "codegeex4-all-9b"],
-                label="Load Model"
+                label="Load Model",
+                render=False,
             ),
         ],
         examples=[