TypeError: quantize_dynamic() got an unexpected keyword argument 'activation_type'

[premkumarelangovan]

I am getting the error while quantizing the onxx_model on FastT5. The problem appears to be with the line 'activation_type=QuantType.QUInt8', please see the tracebelow. I would appreciate some help.

---

TypeError Traceback (most recent call last)
in <cell line: 2>()
1 #Step 2(recommended) quantize the converted model for fast inference to reduce model size
----> 2 quant_model_paths = quantize(onnx_model_paths)

/usr/local/lib/python3.10/dist-packages/fastT5/onnx_exporter.py in quantize(models_name_or_path)
264 model_name = model.as_posix()
265 output_model_name = f"{model_name[:-5]}-quantized.onnx"
--> 266 quantize_dynamic(
267 model_input=model_name,
268 model_output=output_model_name,

TypeError: quantize_dynamic() got an unexpected keyword argument 'activation_type'

quant_model_paths = []
for model in models_name_or_path:
    model_name = model.as_posix()
    output_model_name = f"{model_name[:-5]}-quantized.onnx"
    quantize_dynamic(
        model_input=model_name,
        model_output=output_model_name,
        per_channel=True,
        activation_type=QuantType.QUInt8,
        weight_type=QuantType.QUInt8,
        optimize_model=False,
    )  # op_types_to_quantize=['MatMul', 'Relu', 'Add', 'Mul' ],
    quant_model_paths.append(output_model_name)
    bar.next()