metadata

base_model: nomic-ai/nomic-embed-text-v2-moe
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
license: apache-2.0
language:
  - 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
  - sl
  - lv
  - mr
  - bn
  - sq
  - cy
  - be
  - ml
  - kn
  - mk
  - ur
  - fy
  - te
  - eu
  - sw
  - so
  - sd
  - uz
  - co
  - hr
  - gu
  - ce
  - eo
  - jv
  - la
  - zu
  - mn
  - si
  - ga
  - ky
  - tg
  - my
  - km
  - mg
  - pa
  - sn
  - ha
  - ht
  - su
  - gd
  - ny
  - ps
  - ku
  - am
  - ig
  - lo
  - mi
  - nn
  - sm
  - yi
  - st
  - tl
  - xh
  - yo
  - af
  - ta
  - tn
  - ug
  - az
  - ba
  - bs
  - dv
  - et
  - gl
  - gn
  - gv
  - hy

nomic-embed-text-v2-moe: Multilingual Mixture of Experts Text Embeddings

Model Overview

nomic-embed-text-v2-moe is SoTA multilingual MoE text embedding model:

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 (see code repo) released

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	❌	❌	❌

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: Supports dozens of languages (see Performance section)

Usage Guide

Installation

The model can be used through SentenceTransformers and Transformers.

For best performance on GPU, please install

pip install torch transformers einops git+https://github.com/nomic-ai/megablocks.git

Important: the text prompt must include a task instruction prefix, instructing the model which task is being performed.

For queries/questions, please use search_query: and search_document: for the corresponding document

Transformers

If using Transformers, make sure to prepend the task instruction prefix

import torch
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("nomic-ai/nomic-embed-text-v2-moe")
model = AutoModel.from_pretrained("nomic-ai/nomic-embed-text-v2-moe", trust_remote_code=True)

sentences = ['search_document: Hello!', 'search_document: ¡Hola!']

def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
model.eval()
with torch.no_grad():
    model_output = model(**encoded_input)
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
embeddings = F.normalize(embeddings, p=2, dim=1)

SentenceTransformers

With SentenceTransformers, you can specify the prompt_name (query or passage)

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v2-moe", trust_remote_code=True)
sentences = ["Hello!", "¡Hola!"]
embeddings = model.encode(sentences, prompt_name="passage")

Performance

nomic-embed-text-v2-moe performance on BEIR and MIRACL compared to other open-weights embedding models:

nomic-embed-text-v2-moe performance on BEIR at 768 dimension and truncated to 256 dimensions:

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

Limitations

Performance may vary across different languages
Resource requirements may be higher than traditional dense models due to MoE architecture
Must have trust_remote_code=True when loading the model

Training Details

Trained on 1.6 billion high-quality pairs across multiple languages
Uses consistency filtering to ensure high-quality training data
Incorporates Matryoshka representation learning for dimension flexibility
Training includes both weakly-supervised contrastive pretraining and supervised finetuning

nomic-ai
/

nomic-embed-text-v2-moe