Update app.py

app.py

@@ -44,9 +44,6 @@ model1 = AutoModelForCausalLM.from_pretrained(MODEL_LIST[1]).to(device)
 tokenizer2 = AutoTokenizer.from_pretrained(MODEL_LIST[2])
 model2 = AutoModelForCausalLM.from_pretrained(MODEL_LIST[2]).to(device)
 
-messages = [{"role": "user", "content": "List the steps to bake a chocolate cake from scratch."}]
-
-
 #@spaces.GPU()
 def stream_chat(
     message: str, 
@@ -56,7 +53,7 @@ def stream_chat(
     top_p: float = 1.0, 
     top_k: int = 20, 
     penalty: float = 1.2,
-    choice: str = "1.7B"
+    choice: str = "135M"
 ):
     print(f'message: {message}')
     print(f'history: {history}')
@@ -159,7 +156,7 @@ with gr.Blocks(css=CSS, theme="soft") as demo:
             ),
             gr.Radio(
                 ["135M", "360M", "1.7B"],
-                value="1.7B",
+                value="135M",
                 label="Load Model",
                 render=False,
             ),