Skip to content

Search by meaning

Embedding models and datasets for searching, comparing, and clustering texts by meaning.

5 resources

Models3

  • ModelBGE-M3

    BGE-M3 is a new embedding model, which is distinguished for its versatility in Multi-Linguality, Multi-Functionality, and Multi-Granularity.

    • University of Science and Technology of China
    • BAAI
    No license specified
  • This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity,…

  • This is a specialized Slovak sentence-transformers model that maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity,…

Datasets2

  • DatasetSkMTEB

    SkMTEB is the first comprehensive MTEB-style text embedding benchmark for Slovak — a low-resource West Slavic language with ~5 million speakers.

    • SlovakNLP Community
    CC BY 4.0
  • This is a synthetic Slovak dataset intended for the semantic textual similarity (STS) task.

    CC BY-NC 4.0