Instructions to use huberm/ModernBERT-medium-custom-corp-eu-WordLevel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huberm/ModernBERT-medium-custom-corp-eu-WordLevel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="huberm/ModernBERT-medium-custom-corp-eu-WordLevel")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("huberm/ModernBERT-medium-custom-corp-eu-WordLevel") model = AutoModelForMaskedLM.from_pretrained("huberm/ModernBERT-medium-custom-corp-eu-WordLevel") - Notebooks
- Google Colab
- Kaggle
Model Card for Model ID
Medium-sized ModernBERT trained on a Basque custom corpus using WordLevel tokenization (equivalently, tokenization determined by the corpus files). The custom corpus consists of the first third of the EusCrawl corpus and the entire Basque UD corpus.
- Downloads last month
- 2