Update app.py

app.py

@@ -35,7 +35,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 # device_map = infer_auto_device_map(model, dtype="float16")
 # st.write(device_map)
 
-@st.cache(allow_mutable_outputs=True)
+@st.cache(allow_output_mutation=True)
 def load_model():
     model = AutoModelForCausalLM.from_pretrained("bryanmildort/gpt_neo_notes", low_cpu_mem_usage=True)
     # model = model.to(device)