Update app.py

app.py

@@ -1,8 +1,7 @@
 import os
 import torch
-from transformers import AutoModelForCausalLM as m, AutoTokenizer as t, BitsAndBytesConfig as quant
-qq=quant(load_in_4bit=True)
-mod=m.from_pretrained("peterpeter8585/sungyoonaimodel2", quantization_config=qq)
+from transformers import AutoModelForCausalLM as m, AutoTokenizer as t
+mod=m.from_pretrained("peterpeter8585/sungyoonaimodel2", low_cpu_mem_usage=True)
 tok=t.from_pretrained("peterpeter8585/sungyoonaimodel2", trust_remote_code=True)
 mod.eval()
 import requests