Meet the team that turns your ideas into work.

Discover EightBots
EIGHTBOTS
Contact salesSign up
TurkuNLPFinnish ModernBERT

Finnish ModernBERT Base EDU

Finnish ModernBERT Base EDU is a multilingual masked-language encoder with 143 million parameters. Its final training stage uses multilingual educational data.

Training and configuration

The card identifies a separate educational-data annealing release. It reports 404.7 billion training tokens. This release keeps the 143M-parameter size-specific-vocabulary architecture; it is not a quantized format of the baseline model.Finnish ModernBERT Base EDU: model card and weightsFinnish ModernBERT Base EDU: released configuration

Practical assessment

Practical guidance. An educational-data training stage is a data-selection choice, not a guarantee that output is factual. Check the labels and language mix of your use case before selecting this release over Base.

Specifications & access

Finnish ModernBERT Base EDU specifications
DetailValue and conditions
AccessDownloadable
Model identifiersfinnish-modernbert-base-edu
Context window16,000 tokens

max_position_embeddings in this release's configuration; theoretical extrapolation is not recorded as an established input limit.

Finnish ModernBERT Base EDU: released configuration
LicenseApache 2.0.Finnish ModernBERT Base EDU: model card and weights
Architecture22 layers, hidden width 768 and 12 attention heads.Finnish ModernBERT Base EDU: released configuration
Vocabulary42,240 entries in the released configuration.Finnish ModernBERT Base EDU: released configuration
Training volume404.7 billion tokens, as stated by this release's card.Finnish ModernBERT Base EDU: model card and weights

Related models

  • Finnish ModernBERT Base

    TurkuNLP ยท Finnish ModernBERT

    Finnish ModernBERT Base provides 16,000-token encoder inputs with 143 million parameters.

    Launch date not confirmedDownloadable