Fill-Mask
Transformers
PyTorch
English
bert
biobert
radbert
language-model
uncased
radiology
biomedical
Instructions to use StanfordAIMI/RadBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use StanfordAIMI/RadBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="StanfordAIMI/RadBERT")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("StanfordAIMI/RadBERT") model = AutoModelForMaskedLM.from_pretrained("StanfordAIMI/RadBERT", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
metadata
widget:
- text: low lung volumes, [MASK] pulmonary vascularity.
tags:
- fill-mask
- pytorch
- transformers
- bert
- biobert
- radbert
- language-model
- uncased
- radiology
- biomedical
datasets:
- wikipedia
- bookscorpus
- pubmed
- radreports
language:
- en
license: mit
RadBERT was continuously pre-trained on radiology reports from a BioBERT initialization.
Citation
@article{chambon_cook_langlotz_2022,
title={Improved fine-tuning of in-domain transformer model for inferring COVID-19 presence in multi-institutional radiology reports},
DOI={10.1007/s10278-022-00714-8}, journal={Journal of Digital Imaging},
author={Chambon, Pierre and Cook, Tessa S. and Langlotz, Curtis P.},
year={2022}
}