Meet the team that turns your ideas into work.

Discover EightBots
EIGHTBOTS
Contact salesSign up
AI provider

TurkuNLP

TurkuNLP is an interdisciplinary language research group at the University of Turku. Its researchers develop Finnish language technology, large language models, text representations and methods for analysing large text collections. It is a university group, not a separate model-hosting company.

Explore models

Models & tools

  • FinBERT Base Cased is a Finnish masked-language encoder with a dedicated WordPiece vocabulary.

    Launch date Downloadable

  • FinBERT Base Uncased is a Finnish masked-language encoder with a dedicated WordPiece vocabulary.

    Launch date Downloadable

  • This register classifier adapts BGE-M3 RetroMAE and publishes a specific trained cross-validation fold.

    Launch date not confirmedDownloadable
  • BGE Subregister Classifier Heads

    TurkuNLP · Web register classification

    This bundle contains 17 trained classifiers for subregister labels over precomputed BGE-style vectors.

    Launch date not confirmedResearch releaseDownloadable

  • BLUUMI adds Finnish capability to BigScience's multilingual BLOOM 176B model through continued pretraining.

    Launch date not confirmedDownloadable

  • ECCO-BERT is an English encoder trained on digitized eighteenth-century documents from the United Kingdom.

    Launch date not confirmedDownloadable
  • English Web Register Classifier

    TurkuNLP · Web register classification

    The English Web Register Classifier uses a 24-label scheme trained on English CORE data.

    Launch date not confirmedDownloadable

  • FinBERT Finnish SQuAD 2.0 extracts answer spans from supplied text and can handle unanswerable questions.

    Launch date not confirmedDownloadable

  • FinBERT Large Cased increases encoder depth and width while using the same Finnish training data as FinBERT Base.

    Launch date not confirmedDownloadable

  • FinBERT Large Toxicity assigns six overlapping toxicity labels to Finnish text.

    Launch date not confirmedDownloadable
  • FinerWeb Quality Classifier

    TurkuNLP · Web quality classification

    FinerWeb predicts line-level quality classes for English web text and includes a clean-score calibration component.

    Launch date not confirmedDownloadable

  • FinGPT 13B is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.

    Launch date not confirmedDownloadable

  • FinGPT 3B is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.

    Launch date not confirmedDownloadable

  • FinGPT 8B is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.

    Launch date not confirmedDownloadable

  • FinGPT Large is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.

    Launch date not confirmedDownloadable

  • FinGPT Medium is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.

    Launch date not confirmedDownloadable

  • FinGPT Small is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.

    Launch date not confirmedDownloadable

  • FinGPT XL is a Finnish text-generation base model in TurkuNLP's Finnish GPT-3 series.

    Launch date not confirmedDownloadable
  • Finnish ModernBERT Base

    TurkuNLP · Finnish ModernBERT

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

    Launch date not confirmedDownloadable

  • Finnish ModernBERT Base EDU provides 16,000-token encoder inputs with 143 million parameters and educational-data annealing.

    Launch date not confirmedDownloadable

  • Finnish ModernBERT Base Short provides 8,192-token encoder inputs with 209 million parameters.

    Launch date not confirmedDownloadable

  • Finnish ModernBERT Base Short EDU provides 8,192-token encoder inputs with 209 million parameters and educational-data annealing.

    Launch date not confirmedDownloadable
  • Finnish ModernBERT Large

    TurkuNLP · Finnish ModernBERT

    Finnish ModernBERT Large provides 16,000-token encoder inputs with 401 million parameters.

    Launch date not confirmedDownloadable

  • This Finnish ModernBERT research release isolates annealing before context extension.

    Launch date not confirmedResearch releaseDownloadable

  • Finnish ModernBERT Large EDU provides 16,000-token encoder inputs with 401 million parameters and educational-data annealing.

    Launch date not confirmedDownloadable

  • This sentence encoder adapts TurkuNLP's Finnish ModernBERT Large Short for retrieval.

    Launch date not confirmedResearch releaseDownloadable

  • Finnish ModernBERT Large Short provides 8,192-token encoder inputs with 475 million parameters.

    Launch date not confirmedDownloadable

  • Finnish ModernBERT Large Short EDU provides 8,192-token encoder inputs with 475 million parameters and educational-data annealing.

    Launch date not confirmedDownloadable
  • Finnish ModernBERT Tiny

    TurkuNLP · Finnish ModernBERT

    Finnish ModernBERT Tiny provides 16,000-token encoder inputs with 51 million parameters.

    Launch date not confirmedDownloadable

  • Finnish ModernBERT Tiny EDU provides 16,000-token encoder inputs with 51 million parameters and educational-data annealing.

    Launch date not confirmedDownloadable

  • Finnish ModernBERT Tiny Short provides 8,192-token encoder inputs with 129 million parameters.

    Launch date not confirmedDownloadable

  • Finnish ModernBERT Tiny Short EDU provides 8,192-token encoder inputs with 129 million parameters and educational-data annealing.

    Launch date not confirmedDownloadable

  • This FinBERT-based named-entity model marks 18 OntoNotes entity categories in Finnish text.

    Launch date not confirmedResearch releaseDownloadable
  • Finnish Sentence-BERT Cased

    TurkuNLP · Finnish Sentence-BERT

    This Finnish sentence embedding model adapts the cased FinBERT checkpoint for paraphrase similarity.

    Launch date not confirmedDownloadable
  • Finnish Sentence-BERT Uncased

    TurkuNLP · Finnish Sentence-BERT

    This Finnish sentence embedding model adapts the uncased FinBERT checkpoint for paraphrase similarity.

    Launch date not confirmedDownloadable
  • HPLT3 Persian Quality Classifier

    TurkuNLP · Web quality classification

    This downloadable Persian-named quality classifier has sparse documentation and an XLM-RoBERTa Large ancestry tag.

    Launch date not confirmedResearch releaseDownloadable

  • Megatron FinBERT is a 1.3-billion-parameter Finnish encoder with a wider Megatron-BERT architecture.

    Launch date not confirmedDownloadable
  • Multilingual Web Register Classifier

    TurkuNLP · Web register classification

    This XLM-RoBERTa Large classifier assigns hierarchical text-type labels to web documents.

    Launch date not confirmedDownloadable
  • Register Ablation Models

    TurkuNLP · Register ablations

    These research models compare training on different web text types through separate repository branches.

    Launch date not confirmedResearch releaseDownloadable

  • WikiBERT provides separately trained Wikipedia-based encoders for 44 published language identifiers.

    Launch date not confirmedDownloadable

  • The English QA Extractor is a separate token classifier for locating question and answer spans.

    Launch date not confirmedDownloadable

  • The Finnish QA Extractor labels question and answer spans within source documents.

    Launch date not confirmedDownloadable

  • The QA Register Selector identifies documents likely to contain question-and-answer material.

    Launch date not confirmedDownloadable