Instructions to use prithivida/bert-for-patents-64d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivida/bert-for-patents-64d with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="prithivida/bert-for-patents-64d")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("prithivida/bert-for-patents-64d") model = AutoModel.from_pretrained("prithivida/bert-for-patents-64d") - Notebooks
- Google Colab
- Kaggle
Add TF weights
#1
by joaogante - 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=2.193e-05; Maximum converted output difference=2.193e-05.
π
prithivida changed pull request status to merged