ROUBERTa cased

This is a RoBERTa-base LM trained from scratch exclusively on Uruguayan press [1].

Cite this work

@inproceedings{rouberta2024,
  title={A Language Model Trained on Uruguayan Spanish News Text},
  author={Filevich, Juan Pablo and Marco, Gonzalo and Castro, Santiago and Chiruzzo, Luis and Ros{\'a}, Aiala},
  booktitle={Proceedings of the Second International Workshop Towards Digital Language Equality (TDLE): Focusing on Sustainability@ LREC-COLING 2024},
  pages={53--60},
  year={2024}
}

[1] huggingface.co/datasets/pln-udelar/uy22

Downloads last month
25
Safetensors
Model size
110M params
Tensor type
I64
·
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train pln-udelar/rouberta-base-uy22-cased