nomic-embed-text-v2-moe

2,876 3 days ago

nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.

embedding

Models

View all →

1 model

nomic-embed-text-v2-moe:latest

958MB · 512 context window · Text · 3 days ago

Readme

nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.

  • High Performance: SoTA Multilingual performance compared to ~300M parameter models, competitive with models 2x in size
  • Multilinguality: Supports ~100 languages and trained on over 1.6B pairs
  • Flexible Embedding Dimension: Trained with Matryoshka Embeddings with 3x reductions in storage cost with minimal performance degradations
  • Fully Open-Source: Model weights, code, and training data
Model Params (M) Emb Dim BEIR MIRACL Pretrain Data Finetune Data Code
Nomic Embed v2 305 768 52.86 65.80 ✅ ✅ ✅
mE5 Base 278 768 48.88 62.30 ❌ ❌ ❌
mGTE Base 305 768 51.10 63.40 ❌ ❌ ❌
Arctic Embed v2 Base 305 768 55.40 59.90 ❌ ❌ ❌
BGE M3 568 1024 48.80 69.20 ❌ ✅ ❌
Arctic Embed v2 Large 568 1024 55.65 66.00 ❌ ❌ ❌
mE5 Large 560 1024 51.40 66.50 ❌ ❌ ❌

Best practices

  • Add appropriate prefixes to your text:
    • For queries: “search_query: “
    • For documents: “search_document: “- Maximum input length is 512 tokens
  • For optimal efficiency, consider using the 256-dimension embeddings if storage/compute is a concern

Model Architecture

  • Total Parameters: 475M
  • Active Parameters During Inference: 305M
  • Architecture Type: Mixture of Experts (MoE)
  • MoE Configuration: 8 experts with top-2 routing
  • Embedding Dimensions: Supports flexible dimension from 768 to 256 through Matryoshka representation learning
  • Maximum Sequence Length: 512 tokens
  • Languages: See below for supported languages and its training pairs per different languages

image.png