How to Get Started with the Model
You can load the model using:
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("HiTZ/EriBERTa-base")
model = AutoModelForMaskedLM.from_pretrained("HiTZ/EriBERTa-base")
Model Description
- Developed by: Iker De la Iglesia, Aitziber Atutxa, Koldo Gojenola, and Ander Barrena
- Contact: Iker De la Iglesia and Ander Barrena
- Language(s) (NLP): English, Spanish
- License: apache-2.0
- Funding:
- The Spanish Ministry of Science and Innovation, MCIN/AEI/ 10.13039/501100011033/FEDER projects:
- Proyectos de Generación de Conocimiento 2022 (EDHIA PID2022-136522OB-C22)
- DOTT-HEALTH/PAT-MED PID2019-543106942RB-C31.
- EU NextGeneration EU/PRTR (DeepR3 TED2021-130295B-C31, ANTIDOTE PCI2020-120717-2 EU ERA-Net CHIST-ERA).
- Basque Government:
- IXA IT1570-22.
- The Spanish Ministry of Science and Innovation, MCIN/AEI/ 10.13039/501100011033/FEDER projects:
Model Details
Training Data
Limitation and Bias
Biases
Disclaimer
Citing information
@misc{delaiglesia2023eriberta,
title={{EriBERTa: A Bilingual Pre-Trained Language Model for Clinical Natural Language Processing}},
author={Iker De la Iglesia and Aitziber Atutxa and Koldo Gojenola and Ander Barrena},
year={2023},
eprint={2306.07373},
archivePrefix={arXiv},
primaryClass={cs.CL}
}