Update app.py

app.py

@@ -35,7 +35,7 @@ def load_quantized_model(model_name: str):
         #bnb_4bit_use_double_quant=True,
         bnb_4bit_use_double_quant=False,
         bnb_4bit_quant_type="nf4",
-        bnb_4bit_compute_dtype=torch.bfloat16
+        #bnb_4bit_compute_dtype=torch.bfloat16
     )
 
     model = AutoModelForCausalLM.from_pretrained(