Hugging Face Blog·· 2026-08-26
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
AI summary
Sentence Transformers v6.0 adds a fourth model type, MultiVectorEncoder, for ColBERT-style late-interaction retrieval, with a complete training approach.
Selection record
Threshold 60Official, first-handFirst 62Second 62
AdmittedSum of both 124 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：Sentence Transformers训练多向量嵌入模型教程
- Why it was chosen
- A complete fine-tuning recipe and measured comparisons provide a way to train retrieval models for domain-specific data on a single GPU.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co