Downloads · 30 days
22
0% of all-time downloads
BR_BERTo
rdenadai/BR_BERTo
BR_BERTo is a fill-mask model from rdenadai. Use it when you need the model to fill a missing word. It is set up for transformers.
Portuguese (Brazil) model for text inference.
All-time downloads
44.1K
Public
Parameters
174M
2.1 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin695 MB · 33%
Parameter types
How the weights are stored.
F32174M · 100%
Try a prompt
Model card
From the Hugging Face model README
BR_BERTo
Portuguese (Brazil) model for text inference.
Params
Trained on a corpus of 6_993_330 sentences.
- Vocab size: 150_000
- RobertaForMaskedLM size : 512
- Num train epochs: 3
- Time to train: ~10days (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
More infor here:
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Languages
- pt
- Created
- Mar 2, 2022
- Updated
- Jun 25, 2023