Instructions to use eja67/MBIAS_adapter_fseed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eja67/MBIAS_adapter_fseed with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("eja67/MBIAS_adapter_fseed", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 31fb7947b624ce6f9da4f38357f9f60aaa833f4ce035ab0a5ae0317ca5b575f3
- Size of remote file:
- 5.78 kB
- SHA256:
- 809b4b89069b1bc407919cfa23f4f7fda593a325d25b6e6712e0fcd83ffe6c5a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.