PeLLE: Encoder-based language models for Brazilian Portuguese based on open data

arXiv:2402.19204v1 Announce Type: new
Abstract: 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 …

abstract architecture arxiv cs.cl data encoder family language language models large language large language models paper pretraining results roberta type