Promote Sign in Sign up

Text model

Nomic Embed Text v2

Nomic Embed Text v2 is an open multilingual embedding model and the first to use a mixture-of-experts encoder, with 475M total but only 305M active parameters. It covers roughly 100 languages, supports Matryoshka truncation from 768 to 256 dimensions to cut storage, and ships weights, data and training code under Apache 2.0 for fully local retrieval.

Nomic Text Open weights apache-2.0
Visit model website ↗ Hugging Face
Type
Text
Weights
Open
Downloads
1.3M
Likes
501
Pipeline
sentence similarity
License
apache-2.0

Model hub

nomic-ai/nomic-embed-text-v2-moe

Repo
nomic-ai/nomic-embed-text-v2-moe
Library
sentence-transformers
Access
Public
Technical tags and languages
en es fr de it pt pl nl tr ja vi ru id ar cs ro sv el uk zh hu da no hi fi bg ko sk th he ca lt fa ms sentence-transformers safetensors nomic_bert sentence-similarity feature-extraction custom_code
Open on Hugging Face

More from Nomic

3