Support qwen2_5_vl for ONNX export

[ayan4m1]

Feature request

I would like to be able to convert this model which is based on Qwen 2.5 VL architecture using optimum. Right now, I get the error:

ValueError: Trying to export a qwen2_5_vl model, that is a custom or unsupported architecture, but no custom onnx configuration was passed as `custom_onnx_configs`. Please refer to https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#custom-export-of-transformers-models for an example on how to export custom models. Please open an issue at https://github.com/huggingface/optimum/issues if you would like the model type qwen2_5_vl to be supported natively in the ONNX export.

I read the documentation but I have no idea how I'd go about setting the custom onnx config up.

Motivation

Qwen 2.5 VL is a SOTA architecture that is already being used in downstream models (see my example), so it is worth supporting.

Your contribution

I can do research but I don't have enough experience with this codebase and ML code to contribute a PR.