Skip to main content
Accessibility
← Back to feed
Official announcementHugging Face Blog

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Pexels (free commercial use)

[

Alibaba-NLP/gte-modernbert-base Sentence Similarity • 0.1B • Updated Jul 4, 2025 • 205k • 201

](/Alibaba-NLP/gte-modernbert-base)[

Qwen/Qwen3-Embedding-4B Feature Extraction • 4B • Updated Jun 20, 2025 • 3.41M • 313

](/Qwen/Qwen3-Embedding-4B)[

lightonai/GTE-ModernColBERT-v1 Sentence Similarity • 0.1B • Updated 10 days ago • 365k • 175

](/lightonai/GTE-ModernColBERT-v1)[

lightonai/LateOn Sentence Similarity • 0.1B • Updated 10 days ago • 5.93k • 53

](/lightonai/LateOn)[

lightonai/LateOn-Code Sentence Similarity • 0.1B • Updated 10 days ago • 662 • 35

](/lightonai/LateOn-Code)[

lightonai/LateOn-unsupervised Sentence Similarity • 0.1B • Updated May 21 • 848 • 8

](/lightonai/LateOn-unsupervised)[

lightonai/mLateOn Sentence Similarity • 0.3B • Updated 10 days ago • 8.58k • 31

](/lightonai/mLateOn)[

lightonai/mLateOn-unsupervised Sentence Similarity • 0.3B • Updated 28 days ago • 477 • 5

](/lightonai/mLateOn-unsupervised)[

multi-vector-encoder/mLateOn-medical Feature Extraction • 0.3B • Updated 2 days ago • 15 • 2

](/multi-vector-encoder/mLateOn-medical)[

voyageai/voyage-4-nano Feature Extraction • 0.3B • Updated Mar 2 • 238k • 140

](/voyageai/voyage-4-nano)
## Datasets mentioned in this article 3

More Articles from our Blog

[

nlpguidecommunity

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

-

-

-

-

95
August 18, 2026

](/blog/multi-vector-encoder)
[

Hot
## Welcome EmbeddingGemma, Google's new efficient embedding model

-

-

-

-

  • +2

277
September 4, 2025

](/blog/embeddinggemma)

Community

EditPreview

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

Comment · [Sign up](/join?next=%2Fblog%2Ftrain-multi-vector-encoder) or [log in](/login?next=%2Fblog%2Ftrain-multi-vector-encoder) to comment

[ Upvote 55

](/login?next=%2Fblog%2Ftrain-multi-vector-encoder) - [

  • ](/kalyan-ks)
  • [
  • ](/sugatoray)
  • [
  • ](/davanstrien)
  • [
  • ](/Lauler)
  • [
  • ](/raphaelsty)
  • [
  • ](/samforeman)
  • [
  • ](/hotchpotch)
  • [
  • ](/joe32140)
  • [
  • ](/Nicolas-BZRD)
  • [
  • ](/stephabio)
  • [
  • ](/erikkaum)
  • [
  • ](/tomaarsen)
  • +43

Models mentioned in this article 10

Datasets mentioned in this article 3

[ lightonai/ms-marco-en-bge Viewer • Updated Sep 11, 2025 • 11.3M • 194 • 7

](/datasets/lightonai/ms-marco-en-bge)[ miriad/miriad-4.4M Viewer • Updated Jun 11, 2025 • 4.49M • 566 • 37

](/datasets/miriad/miriad-4.4M)[ tomaarsen/miriad-4.4M-split Viewer • Updated 1 day ago • 8.98M • 542 • 4

](/datasets/tomaarsen/miriad-4.4M-split)

Anthropic pushes into physical world with new standard to help AI agents operate machines - CNBC
News summary

Anthropic pushes into physical world with new standard to help AI agents operate machines - CNBC

Anthropic News

Anthropic pushes into physical world with new standard to help AI agents operate machines CNBC

AWS Elastic Disaster Recovery introduces Recovery Plans for orchestrated application recovery
Official announcement

AWS Elastic Disaster Recovery introduces Recovery Plans for orchestrated application recovery

AWS What’s New

AWS Elastic Disaster Recovery (AWS DRS) now offers Recovery Plans, a capability that automates the sequential launch of multi-server applications during recovery and drills. Instead of launching servers one at a time and tracking dependencies manually, you define the recovery seq

Giga-Scale AI and the Ethernet Evolution: How Spectrum-X Ethernet Rewrites the Rules
Official announcement

Giga-Scale AI and the Ethernet Evolution: How Spectrum-X Ethernet Rewrites the Rules

NVIDIA Developer Blog

The massive growth of generative AI has fundamentally altered data center design. As distributed model training scales to span hundreds of thousands of GPUs,... The massive growth of generative AI has fundamentally altered data center design. As distributed model training scales

How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit
Official announcement

How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit

NVIDIA Developer Blog

Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the... Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and ac

Samsung Introduces New Odyssey Lineup for Fast-Paced Gaming at Gamescom 2026
Official announcement

Samsung Introduces New Odyssey Lineup for Fast-Paced Gaming at Gamescom 2026

Samsung Newsroom

Samsung Electronics today announced its 2027 Odyssey gaming monitor lineup at Gamescom 2026, the world’s largest gaming event, being held in Cologne, Germany from Aug. 26-30. The new lineup introduces multiple Odyssey models that feature world-first innovations, empowering player

How we saved 100 terabytes of memory by optimizing 1.1.1.1’s DNS cache
Official announcement

How we saved 100 terabytes of memory by optimizing 1.1.1.1’s DNS cache

Sebastiaan Neuteboom

Big Pineapple , the platform behind 1.1.1.1 , Gateway DNS , DNS Firewall , AS112 , and several other Cloudflare DNS services, stores over 250 billion DNS cache entries at any given time. At that scale, wasting a single byte per entry costs more than 250 gigabytes of memory across