Instructions to use EuroBERT/EuroBERT-2.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EuroBERT/EuroBERT-2.1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="EuroBERT/EuroBERT-2.1B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("EuroBERT/EuroBERT-2.1B", trust_remote_code=True) model = AutoModelForMaskedLM.from_pretrained("EuroBERT/EuroBERT-2.1B", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Only 9 European languages?
#4
by Neman - opened
EuroBERT: Scaling Multilingual Encoders for European Languages - 9 European (15 total) languages
google-bert/bert-base-multilingual-uncased (from 2019) - 102 languages
I don't understand...
Hey @Neman ,
Regarding language selection, we chose to minimize the number of languages to avoid the curse of multilinguality and to scale step by step, gaining knowledge before working on the next version with more languages.
hgissbkh changed discussion status to closed