diff --git a/examples/nlp/huggingface_model/text_generation/llama/quantization/weight_only/main.py b/examples/nlp/huggingface_model/text_generation/llama/quantization/weight_only/main.py
index 3c9058c7265..7f13bc03a40 100644
--- a/examples/nlp/huggingface_model/text_generation/llama/quantization/weight_only/main.py
+++ b/examples/nlp/huggingface_model/text_generation/llama/quantization/weight_only/main.py
@@ -34,9 +34,10 @@
 from optimum import onnxruntime as optimum_ort
 from neural_compressor_ort.quantization import matmul_nbits_quantizer
 from neural_compressor_ort import config
-from neural_compressor_ort.quantization import logger
+from neural_compressor_ort import logger
 from neural_compressor_ort.quantization import tuning
 from neural_compressor_ort import data_reader
+from neural_compressor_ort import utility
 
 logger = logging.getLogger(__name__)
 logging.basicConfig(