OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

GreekBERT

GreekBERT is a Greek-language edition of the BERT pretrained language model, released as bert-base-greek-uncased-v1. Its documented training corpora include Greek Wikipedia, Greek European Parliament proceedings and Greek text from OSCAR. The model is distributed under the MIT license and can be loaded through Hugging Face Transformers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

GreekBERT — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use GreekBERT when building a Greek-language NLP workflow and you can provide the required preprocessing and downstream task-specific components.

Who it is for

  • Developers building Greek-language NLP applications.
  • Researchers and practitioners who need a pretrained Greek text model as a foundation for downstream work.

Documented uses

  • Load a pretrained tokenizer and model for Greek text.
  • Generate masked-word predictions from Greek text.
  • Use Greek text representations as a foundation for classification, named-entity recognition, search or feature extraction.
Before you choose

Requirements & limits

The repository is public and identifies the model as MIT-licensed.

  • The uncased model requires Greek input to be lowercased and stripped of diacritics.
  • The documented loading path uses Hugging Face Transformers with PyTorch or TensorFlow 2.
  • The README describes the model architecture as 12 layers, 768 hidden units, 12 attention heads and 110 million parameters.
  • The repository's downstream-task evaluation section is marked TBA.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Load GreekBERT with Transformers

Load the pretrained Greek uncased model and tokenizer in a Python environment.

Before you start

  • Python environment
  • Hugging Face Transformers
  • PyTorch or TensorFlow 2

Steps

  1. Install Transformers and either PyTorch or TensorFlow 2.

  2. Use AutoTokenizer.from_pretrained with nlpaueb/bert-base-greek-uncased-v1.

  3. Use AutoModel.from_pretrained with the same model identifier.

Expected outcome

A tokenizer and pretrained model object are loaded for use in a Greek NLP workflow.

Guide limitations

  • The repository requires Greek text for this uncased model to be lowercased and stripped of Greek diacritics before use.
  • The guide covers model loading, not a downstream task or deployment.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
nlpaueb/greek-bert · Official homepage title · retained in its source language
How we review sourcesSuggest a correction