Instructions to use pablocosta/bertabaporu-large-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pablocosta/bertabaporu-large-uncased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="pablocosta/bertabaporu-large-uncased")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("pablocosta/bertabaporu-large-uncased") model = AutoModelForMaskedLM.from_pretrained("pablocosta/bertabaporu-large-uncased") - Notebooks
- Google Colab
- Kaggle
Introduction
BERTabaporu is a Brazilian Portuguese BERT model in the Twitter domain. The model has been built from a collection of 238 million tweets written by over 100 thousand unique Twitter users, and conveying over 2.9 billion tokens in total.
Available models
| Model | Arch. | #Layers | #Params |
|---|---|---|---|
pablocosta/bertabaporu-base-uncased |
BERT-Base | 12 | 110M |
pablocosta/bertabaporu-large-uncased |
BERT-Large | 24 | 335M |
Usage
from transformers import AutoTokenizer # Or BertTokenizer
from transformers import AutoModelForPreTraining # Or BertForPreTraining for loading pretraining heads
from transformers import AutoModel # or BertModel, for BERT without pretraining heads
model = AutoModelForPreTraining.from_pretrained('pablocosta/bertabaporu-large-uncased')
tokenizer = AutoTokenizer.from_pretrained('pablocosta/bertabaporu-large-uncased')
- Downloads last month
- 145