Update README.md

README.md

@@ -34,6 +34,7 @@ model = AutoModelForCausalLM.from_pretrained(
                             model_load_path,
                             low_cpu_mem_usage=True,
                             torch_dtype=torch.float16,
+                            load_in_8bit=True,
                             device_map='auto',
                         )
 model.eval()