Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import spaces
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
@@ -12,9 +13,11 @@ model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True
 )
 
+@spaces.GPU
 def generate(prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
 gr.Interface(fn=generate, inputs="text", outputs="text", title="WizardCoder 13B").launch()
+