diff --git a/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py b/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py index 1c3c212b54fa4..e6f03b185bf68 100644 --- a/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py +++ b/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py @@ -193,9 +193,9 @@ def parse_args(): parser.add_argument("--input_model", required=True, help="Path to the input model file") parser.add_argument("--output_model", required=True, help="Path to the output model file") - parser.add_argument("--block_size", required=False, default=32) + parser.add_argument("--block_size", required=False, default=32, type=int, help="Block size for quantization") parser.add_argument( - "--symmetric", required=False, default=True, help="Indicate whether to quantize the model symmetrically" + "--symmetric", required=False, default=True, type=bool, help="Indicate whether to quantize the model symmetrically" ) parser.add_argument("-v", "--verbose", required=False, action="store_true") parser.set_defaults(verbose=False)