This PR allows 2min of response

#1
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -47,7 +47,7 @@ model = AutoModelForCausalLM.from_pretrained(
47
  device_map="auto",
48
  quantization_config=quantization_config)
49
 
50
- @spaces.GPU()
51
  def stream_chat(
52
  message: str,
53
  history: list,
 
47
  device_map="auto",
48
  quantization_config=quantization_config)
49
 
50
+ @spaces.GPU(duration=120)
51
  def stream_chat(
52
  message: str,
53
  history: list,