regisss

> @regisss ah, my mistake. pushed. there are now additional changes to owlvit, groupvit and vision_text_dual_encoder, I'm assuming we copy over code to these files from the actual CLIP model?...

Gently pinging @sgugger for approval

Congrats @unography for this PR!

@ChainYo ResNet and ConvNeXT are now supported, see #17585 and #17627

@ChainYo Support for DETR has been added in #17904

@ChainYo Support for LayoutLMv3 has been added in #17953

> Hello @ChainYo I would like to contribute the Onnx config for the Decision Transformer, I'd love some guidance on how to go about this as this is my first...

You can easily deploy LayoutLMv3 to the ONNX format using the Hugging Face Transformers library, see [here](https://github.com/huggingface/transformers/pull/17953).

> > You can easily deploy LayoutLMv3 to the ONNX format using the Hugging Face Transformers library, see [here](https://github.com/huggingface/transformers/pull/17953). > > @regisss tokenization_layoutlmv3 can not support "layoutlmv3-base-chinses" model ，see [here](https://github.com/huggingface/transformers/issues/18307)...

The build PR doc test should pass now