AnswerDotAI/ModernBERT

Bringing BERT into modernity via both architecture changes and scaling

55
/ 100
Established

This is a research repository for pre-training and evaluating advanced language models, specifically ModernBERT. It takes large text datasets and outputs a trained language model and its performance evaluations, which can then be used for various natural language understanding tasks. Machine learning researchers and practitioners who want to experiment with cutting-edge language model architectures and training methods would use this.

1,642 stars.

Use this if you are a machine learning researcher or engineer interested in experimenting with and pre-training advanced BERT-like language models for natural language processing tasks, and you are comfortable with a research-focused codebase.

Not ideal if you are looking for a plug-and-play language model for immediate use in an application; for that, you should head to the ModernBERT Collection on HuggingFace.

natural-language-processing large-language-models deep-learning-research text-analysis model-pretraining
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,642

Forks

144

Language

Python

License

Apache-2.0

Last pushed

Mar 01, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/AnswerDotAI/ModernBERT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.