You are viewing main version, which requires installation from source. If you'd like
regular pip install, checkout the latest stable version (v1.21.2).
Supported models
🤗 Optimum handles the export of models to OpenVINO in the exporters.openvino module. It provides classes, functions, and a command line interface to perform the export easily.
Here is the list of the supported architectures :
Transformers
- Albert
- Aquila
- Arctic
- Audio Spectrogram Transformer
- Baichuan 2
- Bart
- Beit
- Bert
- BioGPT
- BlenderBot
- BlenderBotSmall
- Bloom
- CLIP
- Camembert
- ChatGLM
- CodeGen
- CodeGen2
- Cohere
- ConvBert
- ConvNext
- DBRX
- Data2VecAudio
- Data2VecText
- Data2VecVision
- Deberta
- Deberta-v2
- Deit
- DistilBert
- Electra
- Encoder Decoder
- Falcon
- Flaubert
- GLM-4
- GPT-2
- GPT-BigCode
- GPT-J
- GPT-Neo
- GPT-NeoX
- GPT-NeoX-Japanese
- Gemma
- Hubert
- IBert
- InternLM
- InternLM2
- Levit
- Llama
- M2-M100
- MBart
- MPNet
- MPT
- MT5
- Marian
- MiniCPM
- Mistral
- Mixtral
- MobileBert
- MobileNet v1
- MobileNet v2
- MobileVit
- Nystromformer
- OLMo
- OPT
- Orion
- Pegasus
- Perceiver
- Persimmon
- Phi
- Phi3
- Pix2Struct
- PoolFormer
- Qwen
- Qwen2(Qwen1.5)
- ResNet
- Roberta
- Roformer
- SEW
- SEW-D
- Segformer
- SqueezeBert
- StableLM
- StarCoder2
- Swin
- T5
- TROCR
- UniSpeech
- UniSpeech SAT
- Vision Encoder Decoder
- Vit
- Wav2Vec2
- Wav2Vec2 Conformer
- WavLM
- Whisper
- XGLM
- XLM
- XLM-Roberta
- XVERSE
Diffusers
- Stable Diffusion
- Stable Diffusion XL
- Latent Consistency
Timm
- PiT
- ViT
Sentence Transformers
- All Transformer and CLIP-based models.