Edit model card

BERT for Patents

BERT for Patents is a model trained by Google on 100M+ patents (not just US patents). It is based on BERTLARGE.

If you want to learn more about the model, check out the blog post, white paper and GitHub page containing the original TensorFlow checkpoint.


Projects using this model (or variants of it):

Downloads last month
16,819
Safetensors
Model size
346M params
Tensor type
I64
·
F32
·
Hosted inference API
Fill-Mask
Examples
Mask token: undefined
This model can be loaded on the Inference API on-demand.

Spaces using anferico/bert-for-patents 3