Veol-CZ/czech-semantic-embeddings

Czech Semantic Embeddings (GGUF, Non-Commercial)

GGUF conversions of Czech semantic embedding models from Seznam with non-commercial license terms.

Included Models

• —Seznam__dist-mpnet-czeng-cs-en.f16.gguf
• —Seznam__dist-mpnet-czeng-cs-en.q8_0.gguf
• —Seznam__simcse-dist-mpnet-czeng-cs-en.f16.gguf
• —Seznam__simcse-dist-mpnet-czeng-cs-en.q8_0.gguf

Upstream Sources

• —https://github.com/seznam/czech-semantic-embedding-models
• —https://huggingface.co/Seznam/dist-mpnet-czeng-cs-en
• —https://huggingface.co/Seznam/simcse-dist-mpnet-czeng-cs-en

Citation

If you use this model, please cite the original Seznam paper:

• —Bednar et al., 2024, Some Like It Small: Czech Semantic Embedding Models for Industry Applications
• —https://arxiv.org/abs/2311.13921

@inproceedings{bednavr2024some,
  title={Some Like It Small: Czech Semantic Embedding Models for Industry Applications},
  author={Bedn{\'a}{\v{r}}, Ji{\v{r}}{\'\i} and N{\'a}plava, Jakub and Baran{\v{c}}{\'\i}kov{\'a}, Petra and Lisick{\`y}, Ond{\v{r}}ej},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={38},
  number={21},
  pages={22734--22742},
  year={2024}
}

Usage (llama.cpp)

llama-server -m Seznam__dist-mpnet-czeng-cs-en.q8_0.gguf --embedding --pooling cls

File Integrity

SHA256 checksums are in checksums.txt.

License

This package contains converted checkpoints from upstream models. Respect original model license and terms:

• —dist-mpnet-czeng-cs-en: CC-BY-NC-SA-4.0
• —simcse-dist-mpnet-czeng-cs-en: CC-BY-NC-SA-4.0

Non-commercial use only. Attribution to Seznam and original model card is required.