File size: 441 Bytes
939c21e |
1 2 3 4 5 6 7 8 |
To produce BioELECTRA, we pretrain ELECTRA on a corpus of over 20 million abstracts from PubMed.
How to use the discriminator in transformers:
from transformers import ElectraForPreTraining, ElectraTokenizerFast
import torch
discriminator = ElectraForPreTraining.from_pretrained("molly-hayward/bioelectra-small-discriminator")
tokenizer = ElectraTokenizerFast.from_pretrained("molly-hayward/bioelectra-small-discriminator") |