anferico
/

bert-for-patents

Fill-Mask Transformers PyTorch TensorFlow Safetensors English masked-lm Inference Endpoints

Model card Files Files and versions Community

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 BERT_LARGE.

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):

Patents4IPPC (carried out by Pi School and commissioned by the Joint Research Centre (JRC) of the European Commission)

Downloads last month: 16,198

Safetensors

Model size

346M params

Tensor type

I64

·

F32

·

Spaces using anferico/bert-for-patents 7