Update app.py

app.py

@@ -20,13 +20,13 @@ class StopOnTokens(StoppingCriteria):
                 return True
         return False
 
-@spaces.GPU(duration=120)
+@spaces.GPU(duration=60)
 def predict(message, history, temperature, max_tokens, top_p, top_k):
     history_transformer_format = history + [[message, ""]]
     stop = StopOnTokens()
     messages = "".join(["".join(["\n<|end|>\n<|user|>\n"+item[0], "\n<|end|>\n<|assistant|>\n"+item[1]]) for item in history_transformer_format])
     model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
-    streamer = TextIteratorStreamer(tokenizer, timeout=150., skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=300., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,
         streamer=streamer,