Update app.py

app.py

@@ -50,7 +50,7 @@ def generate(
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=30.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,
@@ -131,4 +131,4 @@ with gr.Blocks(css="style.css") as demo:
     chat_interface.render()
     
 if __name__ == "__main__":
-    demo.queue(max_size=4).launch(show_error=True)
+    demo.queue(max_size=5).launch(show_error=True)