late-interaction Open weights ST compatible text
lightonai/ColBERT-Zero-unsupervised
- Languages
- English
- License
- apache-2.0
- Training code
- https://github.com/lightonai/pylate/blob/main/examples/train/ColBERT-zero/unsupervised.py
- Adapted from
- answerdotai/ModernBERT-base
- Trained on
- COIRCodeSearchNetRetrievalCodeSearchNetCCRetrievalCodeSearchNetRetrievalQuoraRetrieval
Cite this model
Citation (BibTeX)
@misc{chaffin2026colbertzeropretrainpretraincolbert,
title = {ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models},
author = {Antoine Chaffin and Luca Arnaboldi and Amélie Chatelain and Florent Krzakala},
year = {2026},
eprint = {2602.16609},
archivePrefix = {arXiv},
primaryClass = {cs.CL},
url = {https://arxiv.org/abs/2602.16609},
}Parameters 149M
Active parameters 110M
Embedding dim 128
Max tokens 8,192
Memory 568 MB
Released 2026-02-19
Openness
6/6
- Open weights
- Open license
- Training code
- Training data
- Paper
- Model card