if deivce type is CPU, remove the timeout argument to TextIteratorStreamer

app.py

@@ -57,7 +57,11 @@ 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=20.0, skip_prompt=True, skip_special_tokens=True)
+    if device == "cpu":
+        streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    else:
+        streamer = TextIteratorStreamer(tokenizer, timeout=120.0, skip_prompt=True, skip_special_tokens=True)
+
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,