dense Open weights Instruction-tuned ST compatible text
Snowflake/snowflake-arctic-embed-l-v2.0
- Languages
AfrikaansAlbanianArabicArmenianAzerbaijaniBasqueBelarusianBengaliBulgarianBurmeseCatalanCebuano +62 more
ChineseCroatianCzechDanishDutchEnglishEstonianFinnishFrenchGalicianGeorgianGermanGujaratiHaitianHebrewHindiHungarianIcelandicIndonesianItalianJapaneseJavaneseKannadaKazakhKhmerKirghizKoreanLaoLatvianLithuanianMacedonianMalay (macrolanguage)MalayalamMarathiModern Greek (1453-)MongolianNepali (macrolanguage)PanjabiPersianPolishPortugueseQuechua (Latin)RomanianRussianSerbianSinhalaSlovakSlovenianSomaliSpanishSwahili (macrolanguage)SwedishTagalogTamilTeluguThaiTurkishUkrainianUrduVietnameseWelshYoruba- License
- apache-2.0
- Adapted from
- BAAI/bge-m3-retromae
- Trained on
FEVERFEVER-NLFEVERHardNegativesHotPotQAHotPotQA-PLHotPotQAHardNegativesHotpotQA-NLMIRACLReranking +6 more
MIRACLRetrievalMIRACLRetrievalHardNegativesNQNQ-NLNQ-PLNQHardNegatives
Cite this model
Citation (BibTeX)
@article{yu2024arctic,
title={Arctic-Embed 2.0: Multilingual Retrieval Without Compromise},
author={Yu, Puxuan and Merrick, Luke and Nuti, Gaurav and Campos, Daniel},
journal={arXiv preprint arXiv:2412.04506},
year={2024},
eprint={2412.04506},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2412.04506}
}Parameters 568M
Active parameters 312M
Embedding dim 1,024
Max tokens 8,192
Memory 2.1 GB
Released 2024-12-04
Openness
4/6
- Open weights
- Open license
- Training code
- Training data
- Paper
- Model card