概述
🤗 Optimum 处理将 PyTorch 或 TensorFlow 模型导出到 exporters.onnx
模块中的 ONNX。它提供类、函数和命令行界面来轻松执行导出。
来自 🤗 Transformers 的支持架构
- AST
- 音频频谱图变换器
- 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
- 编码器解码器
- 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(仅文本条件)
- 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
- 表格变换器
- TROCR
- UniSpeech
- UniSpeech SAT
- 视觉编码器解码器
- Vit
- Wav2Vec2
- Wav2Vec2 Conformer
- WavLM
- Whisper
- XLM
- XLM-Roberta
- Yolos
来自 🤗 Diffusers 的支持架构
- 稳定扩散
来自 🤗 Timm 的支持架构
- 对抗性 Inception v3
- AdvProp(EfficientNet)
- 大型迁移(BiT)
- CSP-DarkNet
- CSP-ResNet
- CSP-ResNeXt
- DenseNet
- 深层聚合
- 双路径网络 (DPN)
- ECA-ResNet
- EfficientNet
- EfficientNet(背包修剪)
- 集成对抗性 Inception ResNet v2
- ESE-VoVNet(部分支持静态形状)
- 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
- 噪声学生 (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
来自 Sentence Transformers 的支持架构
- 所有 Transformer 和基于 CLIP 的模型。