5 min timeout

app.py

@@ -25,7 +25,7 @@ def predict(message, history):
                                             {"role": "assistant", "content": ""}]
 
     model_inputs = tokenizer.apply_chat_template(history_transformer_format, return_tensors="pt")
-    streamer = TextIteratorStreamer(tokenizer, timeout=120, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=300, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         streamer=streamer,
         max_new_tokens=1024,