Can this model suitable for multilingual-t5 accelerate?

[williamwong91]

Recently, I use the chinese function of multilingual-t5 model to accomplish the Chinese NLG tasks. However, the inference speed might be slow, could this model be used for multilingual-t5? How can I do?

[abelriboulot]

So it looks like huggingface has it now: https://huggingface.co/google/mt5-base which means you can use the code in there: https://github.com/abelriboulot/onnxt5/blob/master/examples/export_pretrained_model.py

[polly-morphism]

I am getting "You are using a model of type mt5 to instantiate a model of type t5. This is not supported for all configurations of models and can yield errors." - is it ok to use this code for mT5 models?