You are viewing main version, which requires installation from source. If you'd like
regular pip install, checkout the latest stable version (v1.13.2).
Overview
🤗 Optimum handles the export of PyTorch or TensorFlow models to ONNX in the exporters.onnx module. It provides classes, functions, and a command line interface to perform the export easily.
Supported architectures:
- AST
- Audio Spectrogram Transformer
- Albert
- Bart
- Beit
- Bert
- BlenderBot
- BlenderBotSmall
- Bloom
- Camembert
- CLIP
- CodeGen
- ConvBert
- ConvNext
- Data2VecAudio
- Data2VecText
- Data2VecVision
- Deberta
- Deberta-v2
- Deit
- Detr
- DistilBert
- Donut-Swin
- Electra
- Encoder Decoder
- Flaubert
- GPT-2
- GPT-BigCode
- GPT-J
- GPT-Neo
- GPT-NeoX
- OPT
- GroupVit
- Hubert
- IBert
- LayoutLM
- LayoutLM-v3
- Lilt
- Levit
- LongT5
- Llama
- M2-M100
- Marian
- MBart
- MobileBert
- MobileVit
- MobileNet v1
- MobileNet v2
- MPNet
- MT5
- Nystromformer
- OWL-ViT
- Pegasus
- Perceiver
- Pix2Struct
- PoolFormer
- RegNet
- ResNet
- Roberta
- Roformer
- SAM
- Segformer
- SEW
- SEW-D
- Speech2Text
- Splinter
- SqueezeBert
- Stable Diffusion
- Swin
- T5
- TROCR
- UniSpeech
- UniSpeech SAT
- Vision Encoder Decoder
- Vit
- Wav2Vec2
- Wav2Vec2 Conformer
- WavLM
- Whisper
- XLM
- XLM-Roberta
- Yolos
Supported architectures (Timm):
- Resnext50-32x4d
- Resnext50d-32x4d
- Resnext101-32x4d
- Resnext101-32x8d
- Resnext101-64x4d