Instructions to use falkne/ibm_rank with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use falkne/ibm_rank with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("roberta-base") model.load_adapter("falkne/ibm_rank", set_active=True) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- db970f24a294e3e00984eb32d2063d03d505f47ff9e5f9bfb410b84e3ab1dd6e
- Size of remote file:
- 3.59 MB
- SHA256:
- 84873c3f1ad6c53d771afa4f272ecfc48a3f98137748f4c87c06467bf6a2af5a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.