|
--- |
|
title: README |
|
emoji: 👀 |
|
colorFrom: grey |
|
colorTo: white |
|
sdk: static |
|
pinned: false |
|
--- |
|
|
|
<div class="grid lg:grid-cols-3 gap-x-4 gap-y-7"> |
|
<div class="lg:col-span-3"> |
|
<p class="mb-4"> |
|
Welcome to the working group <b>ONNXConfig for all</b>! 🤗 |
|
<br /> |
|
<br /> |
|
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! |
|
<br /> |
|
<br /> |
|
Feel free to join me in this adventure! You can reach me directly on Discord: <b>ChainYo#3610</b> |
|
</p> |
|
</div> |
|
<div class="lg:col-span-3"> |
|
<p class="mb-4">Here is a list of all the models that need to receive ONNX support:</p> |
|
<div class="p-4 bg-gradient-to-b from-gray-50-to-white border border-gray-100 rounded-lg relative mb-4"> |
|
<pre class="break-words leading-1 whitespace-pre-line text-xs md:text-sm text-gray-800"> |
|
- ✅ Albert |
|
- ✅ BART |
|
- BeiT |
|
- ✅ BERT |
|
- BigBird |
|
- BigBirdPegasus |
|
- Blenderbot |
|
- BlenderbotSmall |
|
- CLIP |
|
- CTRL |
|
- ✅ CamemBERT |
|
- Canine |
|
- ConvBert |
|
- ✅ Data2Vec |
|
- Deberta |
|
- DeiT |
|
- ✅ Distilbert |
|
- ✅ Electra |
|
- FNet |
|
- FSMT |
|
- 🛠️ Flaubert |
|
- Funnel |
|
- ✅ GPT2 |
|
- 🛠️ GPTJ |
|
- ✅ GPT-Neo |
|
- Hubert |
|
- ✅ I-Bert |
|
- ImageGPT |
|
- LED |
|
- ✅ LayoutLM |
|
- LayoutLMv2 |
|
- Longformer |
|
- Luke |
|
- Lxmert |
|
- ✅ M2M100 |
|
- ✅ mBart |
|
- MPNet |
|
- MT5 |
|
- ✅ Marian |
|
- MegatronBert |
|
- MobileBert |
|
- Nystromformer |
|
- ✅ OpenAIGPT-2 |
|
- ✅ PLBart |
|
- Pegasus |
|
- Perceiver |
|
- PoolFormer |
|
- ProphetNet |
|
- rag |
|
- Reformer |
|
- RemBert |
|
- RoFormer |
|
- ✅ RoBERTa |
|
- SEWD |
|
- Segformer |
|
- Splinter |
|
- SqueezeBERT |
|
- Swin |
|
- ✅ T5 |
|
- TransfoXL |
|
- UniSpeech |
|
- UniSpeechSat |
|
- ViT |
|
- Vilt |
|
- VisualBERT |
|
- Wav2Vec2 |
|
- WavLM |
|
- XGLM |
|
- XLM |
|
- XLMProphetNet |
|
- ✅ XLM-RoBERTa |
|
- ✅ XLM-Roberta-XL |
|
- XLNet |
|
- Yoso |
|
</pre> |
|
</div> |
|
</div> |
|
<div class="lg:col-span-3"> |
|
<p class="mb-4"> |
|
If there is a ✅ next to a model, it means that the model is already supported by ONNX. A 🛠️ 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. |
|
<br /> |
|
<br /> |
|
If you need some help about implementing an unsupported model, here is a |
|
<a |
|
href="https://huggingface.co/docs/transformers/serialization#exporting-a-model-for-an-unsupported-architecture" style="text-decoration: underline;">guide</a> from HuggingFace's documentation. |
|
<br /> |
|
<br /> |
|
If you want an example of implementation, I did one for |
|
<a href="https://github.com/huggingface/transformers/pull/14059" style="text-decoration: underline;"> |
|
CamemBERT |
|
</a> some months ago. |
|
<br /> |
|
<br /> |
|
Have fun coding! 🎉🚀 |
|
</p> |
|
</div> |
|
</div> |
|
|
