rdenadai/BR_BERTo

Portuguese (Brazil) model for text inference . Trained on a corpus of 6_993_330 sentences . Time to train: ~10 days (on GCP with a Nvidia T4) I follow the great tutorial from HuggingFace team: How to train a new language model from scratch using Transformers and Tokenizers using Transformers . The model is based on a large corpus of 150_000 sentences and is trained on a GCP-powered T4 . It is now being used to train new language models from scratch . For more information on this article visit: http://www.br_BERTo.com/news/br_berber/Portuguese-language-inform,