unilm
unilm copied to clipboard
How to decrease inference time of LayoutXLM?
Hi,
I'm using Hugging Face libraries in order to run LayoutXLM.
How can I decrease inference time? Which code to use?
I've already tested BetterTransformer (Optimum) and ONNX but none of them accepts LayoutXLM model.
- BetterTransformer:
NotImplementedError: The model type layoutlmv2 is not yet supported to be used with BetterTransformer. - ONNX:
KeyError: "layoutlmv2 is not supported yet.
Thank you.
Note: I asked this question here, too: https://github.com/NielsRogge/Transformers-Tutorials/issues/286