Update app.py

app.py

@@ -35,7 +35,7 @@ tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
     device_map="auto",
     torch_dtype=torch.bfloat16,
-    load_in_4bit=True
+#   load_in_4bit=True
 )
 model.eval()