Optimum documentation

Overview

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

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 from 🤗 Transformers:

  • AST
  • Audio Spectrogram Transformer
  • Albert
  • Bart
  • Beit
  • Bert
  • BlenderBot
  • BlenderBotSmall
  • Bloom
  • Camembert
  • CLIP
  • CodeGen
  • ConvBert
  • ConvNext
  • ConvNextV2
  • Data2VecAudio
  • Data2VecText
  • Data2VecVision
  • Deberta
  • Deberta-v2
  • Deit
  • Detr
  • DistilBert
  • Donut-Swin
  • Electra
  • Encoder Decoder
  • ESM
  • Falcon
  • 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
  • MarkupLM
  • MBart
  • Mistral
  • MobileBert
  • MobileVit
  • MobileNet v1
  • MobileNet v2
  • MPNet
  • MT5
  • Musicgen (text-conditional only)
  • Nystromformer
  • OWL-ViT
  • Pegasus
  • Perceiver
  • Phi
  • Phi3
  • Pix2Struct
  • PoolFormer
  • Qwen2(Qwen1.5)
  • RegNet
  • ResNet
  • Roberta
  • Roformer
  • SAM
  • Segformer
  • SEW
  • SEW-D
  • Speech2Text
  • SpeechT5
  • Splinter
  • SqueezeBert
  • Swin
  • T5
  • Table Transformer
  • TROCR
  • UniSpeech
  • UniSpeech SAT
  • Vision Encoder Decoder
  • Vit
  • Wav2Vec2
  • Wav2Vec2 Conformer
  • WavLM
  • Whisper
  • XLM
  • XLM-Roberta
  • Yolos

Supported architectures from 🤗 Diffusers:

  • Stable Diffusion

Supported architectures from 🤗 Timm:

  • Adversarial Inception v3
  • AdvProp (EfficientNet)
  • Big Transfer (BiT)
  • CSP-DarkNet
  • CSP-ResNet
  • CSP-ResNeXt
  • DenseNet
  • Deep Layer Aggregation
  • Dual Path Network (DPN)
  • ECA-ResNet
  • EfficientNet
  • EfficientNet (Knapsack Pruned)
  • Ensemble Adversarial Inception ResNet v2
  • ESE-VoVNet (Partial support with static shapes)
  • FBNet
  • (Gluon) Inception v3
  • (Gluon) ResNet
  • (Gluon) ResNeXt
  • (Gluon) SENet
  • (Gluon) SE-ResNeXt
  • (Gluon) Xception
  • HRNet
  • Instagram ResNeXt WSL
  • Inception ResNet v2
  • Inception v3
  • Inception v4
  • (Legacy) SE-ResNet
  • (Legacy) SE-ResNeXt
  • (Legacy) SENet
  • MixNet
  • MnasNet
  • MobileNet v2
  • MobileNet v3
  • NASNet
  • Noisy Student (EfficientNet)
  • PNASNet
  • RegNetX
  • RegNetY
  • Res2Net
  • Res2NeXt
  • ResNeSt
  • ResNet
  • ResNet-D
  • ResNeXt
  • RexNet
  • SE-ResNet
  • SelecSLS
  • SE-ResNeXt
  • SK-ResNet
  • SK-ResNeXt
  • SPNASNet
  • SSL ResNet
  • SWSL ResNet
  • SWSL ResNeXt
  • (Tensorflow) EfficientNet
  • (Tensorflow) EfficientNet CondConv
  • (Tensorflow) EfficientNet Lite
  • (Tensorflow) Inception v3
  • (Tensorflow) MixNet
  • (Tensorflow) MobileNet v3
  • TResNet
  • Wide ResNet
  • Xception

Supported architectures from Sentence Transformers:

  • All Transformer and CLIP-based models.
< > Update on GitHub