dense Open weights ST compatible text
BAAI/bge-m3
- Reference
- https://huggingface.co/BAAI/bge-m3
- Languages
AfrikaansAmharicAsturianBelarusianBengaliBulgarianCatalanCebuanoCentral KurdishChineseDanishEnglish +16 more
EstonianFinnishFrenchGalicianGermanGujaratiHebrewHindiItalianJapaneseKoreanModern Greek (1453-)North AzerbaijaniRussianThaiUkrainian- License
- mit
- Training data
- https://huggingface.co/datasets/cfli/bge-full-data
- Trained on
CMedQAv1-rerankingCMedQAv2-rerankingCodeSearchNetDuRetrievalHotpotQAHotpotQA-NLHotpotQA-PLHotpotQAHardNegatives +18 more
LeCaRDv2MIRACLRerankingMIRACLRetrievalMIRACLRetrievalHardNegativesMMarcoRerankingMSMARCOMSMARCO-PLMSMARCOHardNegativesMrTidyRetrievalNQNQ-NLNQ-PLNQHardNegativesNanoMSMARCORetrievalNanoNQRetrievalT2RerankingT2RetrievalmMARCO-NL
Cite this model
Citation (BibTeX)
@misc{bge-m3,
title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
year={2024},
eprint={2402.03216},
archivePrefix={arXiv},
primaryClass={cs.CL}
}Parameters 568M
Active parameters 312M
Embedding dim 1,024
Max tokens 8,192
Memory 2.1 GB
Released 2024-06-28
Openness
5/6
- Open weights
- Open license
- Training code
- Training data
- Paper
- Model card