add zero gpu support

app.py

@@ -36,7 +36,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
 # quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 # tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 # model = AutoModelForCausalLM.from_pretrained(checkpoint, quantization_config=quantization_config).to("cuda")
-
+@spaces.GPU
 def generate_text(prompt, temperature, max_length):
     inputs = tokenizer.encode(prompt, return_tensors="pt").to("cuda")
     outputs = model.generate(inputs, max_length=max_length, top_p=0.9, temperature=temperature)