Update app.py

app.py

@@ -23,7 +23,7 @@ base_model = AutoModelForCausalLM.from_pretrained(
     token=access_token,
     trust_remote_code=True, 
     device_map="auto",
-    torch_dtype=torch.float16,
+    load_in_8bit=True,
     offload_folder="offload/"
 )
 model = PeftModel.from_pretrained(