Update app.py

app.py

@@ -1,7 +1,8 @@
 import os
 import torch
-from transformers import AutoModelForCausalLM as m, AutoTokenizer as t
-mod=m.from_pretrained("peterpeter8585/sungyoonaimodel2", low_cpu_mem_usage=True)
+from transformers import AutoModelForCausalLM as m, AutoTokenizer as t, BitsAndBytesConfig as q
+qq=q(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.float16, bnb_4bit_use_double_quant=False)
+mod=m.from_pretrained("peterpeter8585/sungyoonaimodel2", low_cpu_mem_usage=True, quantization_config=qq)
 tok=t.from_pretrained("peterpeter8585/sungyoonaimodel2", trust_remote_code=True)
 mod.eval()
 import requests