add cache optimisation for loading model

app.py

@@ -5,7 +5,12 @@ st.title("AI text-gen Web-app")
 st.write("This is auto-complete/text generation a web-app powered by GPT-neo. GPT-Neo 125M is a transformer model designed using EleutherAI's replication of the GPT-3 architecture. GPT-Neo refers to the class of models, while 125M represents the number of parameters of this particular pre-trained model.")
 
 # instantiate the model / download
-generator = pipeline('text-generation', model='EleutherAI/gpt-neo-125M')
+@st.cache(allow_output_mutation=True)
+def load_model():
+  generator = pipeline('text-generation', model='EleutherAI/gpt-neo-125M')
+  return (generator)
+
+generator=load_model()
 
 min_length=st.slider(
   'Specify Min length of the text of want to be generated',