Instructions to use prajjwal1/bert-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prajjwal1/bert-tiny with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prajjwal1/bert-tiny", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add TF weights
#10
by YongeBai - opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its PyTorch counterpart.
Maximum crossload output difference=1.788e-06; Maximum crossload hidden layer difference=4.053e-06;
Maximum conversion output difference=1.788e-06; Maximum conversion hidden layer difference=4.053e-06;