Update app.py

app.py

@@ -61,7 +61,7 @@ def generate(
 ) -> Iterator[str]:
     conversation = [*chat_history, {"role": "user", "content": message}]
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    input_ids = tokenizer.apply_chat_template(conversation, chat_template=CHAT_TEMPLATE, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
@@ -103,28 +103,28 @@ demo = gr.ChatInterface(
             minimum=0.1,
             maximum=4.0,
             step=0.1,
-            value=0.6,
+            value=0.3,
         ),
         gr.Slider(
             label="Top-p (nucleus sampling)",
             minimum=0.05,
             maximum=1.0,
             step=0.05,
-            value=0.9,
+            value=0.95,
         ),
         gr.Slider(
             label="Top-k",
             minimum=1,
             maximum=1000,
             step=1,
-            value=50,
+            value=40,
         ),
         gr.Slider(
             label="Repetition penalty",
             minimum=1.0,
             maximum=2.0,
             step=0.05,
-            value=1.2,
+            value=1.0,
         ),
     ],
     stop_btn=None,