Task
Fill Mask
B
microsoft/BiomedVLP-CXR-BERT-specialized
Fill Mask·microsoft· 449.0K· 36
CXR-BERT is a chest X-ray (CXR) domain-specific language model that makes use of an improved vocabulary, novel pretraining procedure, weight regularization, and text augmentations. The resulting model demonstrates improved performance on radiology natural language inference, radiology masked language model token prediction, and downstream vision-language processing tasks such as zero-shot phrase g
# pull & run locally
pip install mlforge-sdk && mlforge pull microsoft/BiomedVLP-CXR-BERT-specialized
pip install mlforge-sdk && mlforge pull microsoft/BiomedVLP-CXR-BERT-specialized
Model details
Provider
microsoft
Framework
transformers
Parameters
109.6M
Size
935 MB
License
mit
Downloads
449.0K
Likes
36
Paper
arXiv:2204.09817
Updated
2025-07-25
About microsoft/BiomedVLP-CXR-BERT-specialized
CXR-BERT is a chest X-ray (CXR) domain-specific language model that makes use of an improved vocabulary, novel pretraining procedure, weight regularization, and text augmentations. The resulting model demonstrates improved performance on radiology natural language inference, radiology masked language model token prediction, and downstream vision-language processing tasks such as zero-shot phrase grounding and image classification.