ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models
Paper • 2602.16609 • Published • 7
ColBERT-Zero 🐶
First large-scale fully pre-trained ColBERT model using only public data, outperforming GTE-ModernColBERT and GTE-ModernBERT
-
-
lightonai/ColBERT-Zero
Sentence Similarity • 0.1B • Updated • 3.33k • • 37 -
lightonai/ColBERT-Zero-supervised
Sentence Similarity • 0.1B • Updated • 145 • 3 -
lightonai/ColBERT-Zero-unsupervised
Sentence Similarity • 0.1B • Updated • 58 • 2 -
lightonai/ModernColBERT-embed-base
Sentence Similarity • 0.1B • Updated • 13 -
lightonai/ModernColBERT-embed-base-supervised
Sentence Similarity • 0.1B • Updated • 20 -
lightonai/ModernColBERT-embed-base-kd-only
Sentence Similarity • 0.1B • Updated • 28 • 1 -
lightonai/ColBERT-Zero-noprompts
Sentence Similarity • 0.1B • Updated • 74 • 2 -
lightonai/ColBERT-Zero-supervised-noprompts
Sentence Similarity • 0.1B • Updated • 12 -
lightonai/ColBERT-Zero-unsupervised-noprompts
Sentence Similarity • 0.1B • Updated • 154