more

app.py

@@ -36,13 +36,13 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
 
     # Use a TextStreamer for real-time decoding
     streamer = TextStreamer(tokenizer, skip_prompt=True)
-    model.generate(
+    _ = model.generate(
         input_ids=inputs,
-        streamer=streamer,
         max_new_tokens=max_tokens,
         use_cache=True,
         temperature=temperature,
         top_p=top_p,
+        streamer=streamer,
     )