Update app.py

app.py

@@ -8,7 +8,7 @@ if torch.cuda.is_available():
     model = AutoModelForCausalLM.from_pretrained("ai-forever/mGPT-13B", load_in_8bit=True, device_map="auto")
     pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-@spaces.GPU
+@spaces.GPU(duration=600)
 def predict(prompt, temperature, max_length):
     return pipe(prompt, temperature=temperature, max_length=max_length, top_p=0.95, top_k=50, do_sample=True)[0]["generated_text"]