PeLLE: Encoder-based language models for Brazilian Portuguese based on open data
Abstrak
In this paper we present PeLLE, a family of large language models based on the RoBERTa architecture, for Brazilian Portuguese, trained on curated, open data from the Carolina corpus. Aiming at reproducible results, we describe details of the pretraining of the models. We also evaluate PeLLE models against a set of existing multilingual and PT-BR refined pretrained Transformer-based LLM encoders, contrasting performance of large versus smaller-but-curated pretrained models in several downstream tasks. We conclude that several tasks perform better with larger models, but some tasks benefit from smaller-but-curated data in its pretraining.
Topik & Kata Kunci
Penulis (7)
Guilherme Lamartine de Mello
Marcelo Finger
and Felipe Serras
Miguel de Mello Carpi
Marcos Menon Jose
Pedro Henrique Domingues
Paulo Cavalim
Akses Cepat
- Tahun Terbit
- 2024
- Bahasa
- en
- Sumber Database
- arXiv
- Akses
- Open Access ✓