Instructions to use FPTAI/vibert-base-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FPTAI/vibert-base-cased with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FPTAI/vibert-base-cased", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- d19384358c5dd3b1d7ff0fd817ada0595c9cf80fbca9a894441116b2ca7a2ce8
- Size of remote file:
- 581 MB
- SHA256:
- f048fb4b02a9ae3d42211e267911b8bd5ab5a7d9a819f23b3a235f6cc6463a7d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.