KeyError: 'swinv2 model type is not supported yet in NormalizedConfig.

[Billybeast2003]

System Info

Google Colab
T4 GPU
transformers Version: 4.47.1
optimum Version: 1.24.0.dev0

Who can help?

@michaelbenayoun, @JingyaHuang, @echarlaix

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction (minimal, reproducible, runnable)

from optimum.onnxruntime import ORTModelForVision2Seq
model = ORTModelForVision2Seq.from_pretrained("/content/swin-xlm-image-recognition", export=True, use_cache=False)
model.save_pretrained("swin-xlm-image-recognition-onnx")

Expected behavior

How to solve this issue? I am trying to convert my VisionEncoderDecoderModel to onnx using optimum, but I am getting this error: KeyError: 'swinv2 model type is not supported yet in NormalizedConfig. Only albert, bart, bert, blenderbot, blenderbot-small, bloom, falcon, camembert, codegen, cvt, deberta, deberta-v2, deit, distilbert, donut-swin, electra, encoder-decoder, gemma, gpt2, gpt-bigcode, gpt-neo, gpt-neox, gptj, imagegpt, llama, longt5, marian, markuplm, mbart, mistral, mixtral, mpnet, mpt, mt5, m2m-100, nystromformer, opt, pegasus, pix2struct, phi, phi3, phi3small, poolformer, regnet, resnet, roberta, segformer, speech-to-text, splinter, t5, trocr, vision-encoder-decoder, vit, whisper, xlm-roberta, yolos, qwen2, granite are supported. If you want to support swinv2 please propose a PR or open up an issue.'

The encoder is "swinv2" and the decoder is "xlm-roberta".