mdeberta-v3-base-meddocan

This model is a finetuned version of mdeberta-v3-base for the meddocan dataset used in a benchmark in the paper TODO. The model has a F1 of 0.974

Please refer to the original publication for more information TODO LINK

Parameters used

parameter	Value
batch size	16
learning rate	4e-05
classifier dropout	0.2
warmup ratio	0
warmup steps	0
weight decay	0
optimizer	AdamW
epochs	10
early stopping patience	3

BibTeX entry and citation info

TODO

Downloads last month: 19

Safetensors

Model size

279M params

Tensor type

I64

F32

Inference Examples

Token Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train IIC/mdeberta-v3-base-meddocan

Collection including IIC/mdeberta-v3-base-meddocan

👨🏻‍⚕️ Spanish Clinical Encoders Analysis

Collection

Models and datasets used in the paper `A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks` • 92 items • Updated Jan 23 • 1

Evaluation results

f1 on meddocan
test set self-reported

0.974

View on Papers With Code