This issue is about the working group specially created for this task. If you are interested in helping out, take a look at this organization, or add me on Discord: ChainYo#3610

We are looking for contributing to HuggingFace's ONNX implementation for all available models on the HF's hub. There is already a lot of architectures implemented for converting PyTorch models to ONNX, but we need more! We need them all!

Feel free to join us in this adventure! Join the org by clicking here

Here is a non-exhaustive list of models that all models available:

- ✅ Albert
- ✅ BART
- BeiT
- ✅ BERT
- 🛠️ BigBird
- BigBirdPegasus
- Blenderbot
- BlenderbotSmall
- ✅ CamemBERT
- Canine
- CLIP
- CTRL
- ConvBert
- ConvNext
- ✅ Data2Vec
- Deberta
- DebertaV2
- DeiT
- DecisionTransformer
- DETR
- ✅ Distilbert
- DPR
- ✅ Electra
- FNet
- FSMT
- ✅ Flaubert
- Funnel
- GLPN
- ✅ GPT2
- ✅ GPTJ
- ✅ GPT-Neo
- Hubert
- ✅ I-Bert
- ImageGPT
- LED
- ✅ LayoutLM
- 🛠️ LayoutLMv2
- LayoutXLM
- Longformer
- Luke
- Lxmert
- ✅ M2M100
- MaskFormer
- ✅ mBart
- MPNet
- MT5
- ✅ Marian
- MegatronBert
- MobileBert
- Nystromformer
- OpenAIGPT
- ✅ PLBart
- Pegasus
- Perceiver
- PoolFormer
- ProphetNet
- QDQBERT
- rag
- Realm
- Reformer
- RemBert
- ResNet
- RetriBert
- RoFormer
- ✅ RoBERTa
- SEW
- SEW-D
- Segformer
- Splinter
- SqueezeBERT
- Swin
- ✅ T5
- TAPAS
- TransfoXL
- TrOCR
- UniSpeech
- UniSpeechSat
- VAN
- ViT
- Vilt
- VisualBERT
- Wav2Vec2
- WavLM
- XGLM
- XLM
- XLMProphetNet
- ✅ XLM-RoBERTa
- ✅ XLM-Roberta-XL
- XLNet
- Yoso

If there is a ✅ next to a model, it means that the model is already supported by ONNX.
🛠️ next to a model means that the PR is in progress and finally if there is nothing next to a model, it means that the model is not yet supported by ONNX and thus we need to add support for it.

If you need some help about implementing an unsupported model, here is a guide from HuggingFace's documentation.

If you want an example of implementation, I did one for CamemBERT some months ago.