This model extends upon the PubMedBert pre-trained model from this repository . The Clinical History Mekkes model was further optimized and retrained on clinical summaries from the Netherlands Brain Bank (NBB) containing information regarding the clinical signs and symptoms that their donors experienced.
The model was first used in this paper and the associated Github and code can be found here
The model was trained using the Simpletransformers library and can be loaded using this package aswell.
model = ClassificationModel(
"bert", "path/to/model"
)
This model can also be loaded using the transformer library in Python.
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Load the model
model = AutoModel.from_pretrained(model_name)
# Example input
text = "Hello, how are you?"
# Tokenize the input
inputs = tokenizer(text, return_tensors="pt")
# Forward pass through the model
outputs = model(**inputs)
Please site our publication when using this model.
pytorch_model.bin 438 MBtraining_args.bin 3.1 kB