late-interaction Open weights text
mixedbread-ai/mxbai-edge-colbert-v0-17m
- Languages
- English
- License
- apache-2.0
- Adapted from
- https://huggingface.co/jhu-clsp/ettin-encoder-17m
- Trained on
- AmazonQACornStackHotpotQALoTTEMSMARCOMultiLongDocRetrievalNQ
Cite this model
Citation (BibTeX)
@misc{takehi2025fantasticsmallretrieverstrain,
title={Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report},
author={Rikiya Takehi and Benjamin Clavié and Sean Lee and Aamir Shakir},
year={2025},
eprint={2510.14880},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2510.14880},
}Parameters 17M
Active parameters 4M
Embedding dim —
Max tokens 7,999
Memory 64 MB
Released 2025-10-16
Openness
4/6
- Open weights
- Open license
- Training code
- Training data
- Paper
- Model card