Instructions to use patrickvonplaten/norwegian-roberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use patrickvonplaten/norwegian-roberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="patrickvonplaten/norwegian-roberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("patrickvonplaten/norwegian-roberta-base") model = AutoModelForMaskedLM.from_pretrained("patrickvonplaten/norwegian-roberta-base") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Roberta-Base
This repo trains roberta-base from scratch on the Norwegian training subset of Oscar containing roughly 4.7 GB of data according to this example.
Training is done on a TPUv3-8 in Flax. More statistics on the training run can be found under tf.hub.
- Downloads last month
- 3