fxmarty

Thank you for the report @davanstrien, I can have a look! cc @baskrahmer as I think you added it.

@xenova can you add a test?

also `cat /proc/meminfo | grep Dirty`

Hi @katiele47 would like to have it merged? If so, let's resolve the conflict and I can trigger the CI.

Thank you, `table-transformer` model is supported in Transformers (https://huggingface.co/docs/transformers/main/en/model_doc/table-transformer) but not yet in the ONNX export. Adding it to my todo :)

Hi @balajiChundi, @liebkne the support was added in https://github.com/huggingface/optimum/pull/1616

Coud you try again with `pip install auto-gptq`? 0.4.2 has been released on PyPI compatible with CUDA 11.7, see https://pypi.org/project/auto-gptq/

working on it

Hi @antje2233, which command are you running? `optimum-cli export onnx --model openai/clip-vit-large-patch14 clip_onnx --task zero-shot-image-classification` works for me.

@antje2233 Could you format code as follow: https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax#quoting-code