Instructions to use mwalmsley/zoobot-encoder-convnext_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use mwalmsley/zoobot-encoder-convnext_base with timm:
import timm model = timm.create_model("hf-hub:mwalmsley/zoobot-encoder-convnext_base", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from mwalmsley/zoobot-encoder-convnext_base: direct link, hf CLI and curl.
- Browser
- Download file 350 MB
-
https://huggingface.co/mwalmsley/zoobot-encoder-convnext_base/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://mwalmsley/zoobot-encoder-convnext_base/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/mwalmsley/zoobot-encoder-convnext_base/resolve/main/pytorch_model.bin
350 MB
- Xet hash:
- 4c986e31b813aaad03c9f105f16a946e66f6177374ba7666fad2c93186e07b44
- Size of remote file:
- 350 MB
- SHA256:
- 8821e1a67f5f559ec65b0a1ef6c95e646e51aea62d556b352bc68291549f4026
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.