metadata
language: en
license: apache-2.0
H.G. BERT
This is a 22.7M parameter BERT encoder-only model trained on Historical English Books from 1700 - 1899.
This is a domain-specialized small model that often performs as good as models 10-100x larger. It demonstrates that narrowing down a model to a small domain requires less overall parameters than models generalized for all problems.
Usage
hgbert-small can be loaded using Hugging Face Transformers as follows.
from transformers import AutoModel
model = AutoModel.from_pretrained("neuml/hgbert-small")
The model is intended to be further fine-tuned for a specific task such as Text Classification, Entity Extraction, Sentence Embeddings and so on.
More Information
Read more about the model in this article.