Instructions to use deepmind/optical-flow-perceiver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepmind/optical-flow-perceiver with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, PerceiverForOpticalFlow tokenizer = AutoTokenizer.from_pretrained("deepmind/optical-flow-perceiver") model = PerceiverForOpticalFlow.from_pretrained("deepmind/optical-flow-perceiver", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from deepmind/optical-flow-perceiver: direct link, hf CLI and curl.
- Browser
- Download file 164 MB
-
https://huggingface.co/deepmind/optical-flow-perceiver/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://deepmind/optical-flow-perceiver/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/deepmind/optical-flow-perceiver/resolve/main/pytorch_model.bin
164 MB
- Xet hash:
- 821ac65a889f9c732b20e7be1c2127fb8d1dd2733fd3a838c6fb834182f40cfc
- Size of remote file:
- 164 MB
- SHA256:
- 3633a73cec625d7d5fcf77a087893d8035da26e74f4083a99b45db35734455dd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.