lightonai/mLateOn

Reference

https://huggingface.co/lightonai/mLateOn

Languages

ArabicEnglishFrenchGermango-Code (Code)Italianjava-Code (Code)javascript-Code (Code)Norwegian Bokmålphp-Code (Code)Portuguesepython-Code (Code) +3 more Show fewer

ruby-Code (Code)SpanishSwedish

License

apache-2.0

Training code

https://github.com/lightonai/mdenseon-mlateon/blob/main/scripts/finetune/multilingual_late_interaction.py

Training data

https://huggingface.co/datasets/lightonai/embeddings-fine-tuning-multilingual-unfiltered

Adapted from

lightonai/mLateOn-unsupervised

Trained on

AppsRetrievalCOIRCodeSearchNetRetrievalCQADupstackRetrievalClimateFEVERCodeEditSearchRetrievalCodeFeedbackMTCodeFeedbackSTCodeSearchNetCCRetrieval +21 more Show fewer

CodeSearchNetRetrievalCodeTransOceanContestCodeTransOceanDLCosQADBPediaFEVERFiQA2018HotpotQAMIRACLRerankingMIRACLRetrievalMIRACLRetrievalHardNegativesMSMARCOMultiLongDocRetrievalNQQuoraRetrievalSCIDOCSSciFactStackOverflowQASyntheticText2SQLTRECDL2019TRECDL2020

@misc{sourty2026denseonlateonfullyopen,
  title         = {DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search},
  author        = {Raphaël Sourty and Antoine Chaffin and Paulo Roberto Moura Junior and Amélie Chatelain},
  year          = {2026},
  eprint        = {2607.27178},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2607.27178},
}