Instructions to use SmilingWolf/wd-convnext-tagger-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use SmilingWolf/wd-convnext-tagger-v3 with timm:
import timm model = timm.create_model("hf-hub:SmilingWolf/wd-convnext-tagger-v3", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download model.msgpack from SmilingWolf/wd-convnext-tagger-v3: direct link, hf CLI and curl.
- Browser
- Download file 395 MB
-
https://huggingface.co/SmilingWolf/wd-convnext-tagger-v3/resolve/main/model.msgpack
- Command line
-
hf download hf://SmilingWolf/wd-convnext-tagger-v3/model.msgpack
-
curl -L -o model.msgpack https://huggingface.co/SmilingWolf/wd-convnext-tagger-v3/resolve/main/model.msgpack
395 MB
- Xet hash:
- ec08e0d7501904d9215f5c70c7f9da8b73eeb6ef45d33d6c4f4aea79659d15d8
- Size of remote file:
- 395 MB
- SHA256:
- 4294aaa66dad2bb01e4552487c7f1402e9a7409744c1fc1f90e70b5ac8f3b5cf
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.