Instructions to use emvecchi/umod_constructiveness with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use emvecchi/umod_constructiveness with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("roberta-base") model.load_adapter("emvecchi/umod_constructiveness", set_active=True) - Notebooks
- Google Colab
- Kaggle
Download pytorch_adapter.bin from emvecchi/umod_constructiveness: direct link, hf CLI and curl.
- Browser
- Download file 3.59 MB
-
https://huggingface.co/emvecchi/umod_constructiveness/resolve/main/pytorch_adapter.bin
- Command line
-
hf download hf://emvecchi/umod_constructiveness/pytorch_adapter.bin
-
curl -L -o pytorch_adapter.bin https://huggingface.co/emvecchi/umod_constructiveness/resolve/main/pytorch_adapter.bin
3.59 MB
- Xet hash:
- ba107c615f927c7ea5e76429fd7ea58cc0263792403f2c0ce522461901a59fab
- Size of remote file:
- 3.59 MB
- SHA256:
- 08b97b43e6a1d128e0af94607c5f0ec699098a6a1d9a6133f731adc8f16f299d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.