Update app.py

app.py

@@ -37,7 +37,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 @st.cache(allow_output_mutation=True)
 def load_model():
-    model = AutoModelForCausalLM.from_pretrained("bryanmildort/gpt_neo_notes")
+    model = AutoModelForCausalLM.from_pretrained("bryanmildort/gpt_neo_notes", low_cpu_mem_usage=True)
     # model = model.to(device)
     tokenizer = AutoTokenizer.from_pretrained("bryanmildort/gpt_neo_notes")
     return pipeline("text-generation", model=model, tokenizer=tokenizer)