Swahili News Classification with BERT
This model was trained using HuggingFace's Flax framework and is part of the JAX/Flax Community Week organized by HuggingFace. All training was done on a TPUv3-8 VM sponsored by the Google Cloud team.
This model was used as the base and fine-tuned for this task.
How to use
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("flax-community/bert-swahili-news-classification")
model = AutoModelForSequenceClassification.from_pretrained("flax-community/bert-swahili-news-classification")
Eval metrics (10% valid set): {'accuracy': 0.9114740008594757}