Model reference · open weights

NV-Embed

Available as managed deployment Licence fee Embeddings nvidia Embeddings 1 variants 20k dl/mo

NV-Embed is an open-weight embedding model from nvidia. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byNVIDIA
TypeEmbedding models
TaskEmbeddings
Parameters (lead)7.9B
Context32k tokens
Runs withtransformers
Released2024-08-29
Popularity20k downloads / month
LicenceCommercial licence needed

About

What NV-Embed is

Introduction

We present NV-Embed-v2, a generalist embedding model that ranks No. 1 on the Massive Text Embedding Benchmark (MTEB benchmark)(as of Aug 30, 2024) with a score of 72.31 across 56 text embedding tasks. It also holds the No. 1 in the retrieval sub-category (a score of 62.65 across 15 tasks) in the leaderboard, which is essential to the development of RAG technology.

NV-Embed-v2 presents several new designs, including having the LLM attend to latent vectors for better pooled embedding output, and demonstrating a two-staged instruction tuning method to enhance the accuracy of both retrieval and non-retrieval tasks. Additionally, NV-Embed-v2 incorporates a novel hard-negative mining methods that take into account the positive relevance score for better false negatives removal.

Read the full model card

For more technical details, refer to our paper: NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

Model Details

  • Base Decoder-only LLM: Mistral-7B-v0.1
  • Pooling Type: Latent-Attention
  • Embedding Dimension: 4096

How to use

Here is an example of how to encode queries and passages using Huggingface-transformer and Sentence-transformer. Please find the required package version here.

Usage (HuggingFace Transformers)

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

# Each query needs to be accompanied by an corresponding instruction describing the task.
task_name_to_instruct = {"example": "Given a question, retrieve passages that answer the question",}

query_prefix = "Instruct: "+task_name_to_instruct["example"]+"\nQuery: "
queries = [
    'are judo throws allowed in wrestling?',
    'how to become a radiology technician in michigan?'
    ]

# No instruction needed for retrieval passages
passage_prefix = ""
passages = [
    "Since you're reading this, you are probably someone from a judo background or someone who is just wondering how judo techniques can be applied under wrestling rules. So without further ado, let's get to the question. Are Judo throws allowed in wrestling? Yes, judo throws are allowed in freestyle and folkstyle wrestling. You only need to be careful to follow the slam rules when executing judo throws. In wrestling, a slam is lifting and returning an opponent to the mat with unnecessary force.",
    "Below are the basic steps to becoming a radiologic technologist in Michigan:Earn a high school diploma. As with most careers in health care, a high school education is the first step to finding entry-level employment. Taking classes in math and science, such as anatomy, biology, chemistry, physiology, and physics, can help prepare students for their college studies and future careers.Earn an associate degree. Entry-level radiologic positions typically require at least an Associate of Applied Science. Before enrolling in one of these degree programs, students should make sure it has been properly accredited by the Joint Review Committee on Education in Radiologic Technology (JRCERT).Get licensed or certified in the state of Michigan."
]

# load model with tokenizer
model = AutoModel.from_pretrained('nvidia/NV-Embed-v2', trust_remote_code=True)

# get the embeddings
max_length = 32768
query_embeddings = model.encode(queries, instruction=query_prefix, max_length=max_length)
passage_embeddings = model.encode(passages, instruction=passage_prefix, max_length=max_length)

# normalize embeddings
query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
passage_embeddings = F.normalize(passage_embeddings, p=2, dim=1)

# get the embeddings with DataLoader (spliting the datasets into multiple mini-batches)
# batch_size=2
# query_embeddings = model._do_encode(queries, batch_size=batch_size, instruction=query_prefix, max_length=max_length, num_workers=32, return_numpy=True)
# passage_embeddings = model._do_encode(passages, batch_size=batch_size, instruction=passage_prefix, max_length=max_length, num_workers=32, return_numpy=True)

scores = (query_embeddings @ passage_embeddings.T) * 100
print(scores.tolist())
# [[87.42693328857422, 0.46283677220344543], [0.965264618396759, 86.03721618652344]]

Usage (Sentence-Transformers)

import torch
from sentence_transformers import SentenceTransformer

# Each query needs to be accompanied by an corresponding instruction describing the task.
task_name_to_instruct = {"example": "Given a question, retrieve passages that answer the question",}

query_prefix = "Instruct: "+task_name_to_instruct["example"]+"\nQuery: "
queries = [
    'are judo throws allowed in wrestling?',
    'how to become a radiology technician in michigan?'
    ]

# No instruction needed for retrieval passages
passages = [
    "Since you're reading this, you are probably someone from a judo background or someone who is just wondering how judo techniques can be applied under wrestling rules. So without further ado, let's get to the question. Are Judo throws allowed in wrestling? Yes, judo throws are allowed in freestyle and folkstyle wrestling. You only need to be careful to follow the slam rules when executing judo throws. In wrestling, a slam is lifting and returning an opponent to the mat with unnecessary force.",
    "Below are the basic steps to becoming a radiologic technologist in Michigan:Earn a high school diploma. As with most careers in health care, a high school education is the first step to finding entry-level employment. Taking classes in math and science, such as anatomy, biology, chemistry, physiology, and physics, can help prepare students for their college studies and future careers.Earn an associate degree. Entry-level radiologic positions typically require at least an Associate of Applied Science. Before enrolling in one of these degree programs, students shou

From the published model card. Full card on the HuggingFace links in the sidebar.

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
ClassificationMTEB AmazonCounterfactualClassification (en)accuracy94.284
ClassificationMTEB AmazonCounterfactualClassification (en)accuracy_stderr0.401
ClassificationMTEB AmazonCounterfactualClassification (en)ap76.491
ClassificationMTEB AmazonCounterfactualClassification (en)ap_stderr1.242
ClassificationMTEB AmazonCounterfactualClassification (en)f191.420
ClassificationMTEB AmazonCounterfactualClassification (en)f1_stderr0.504
ClassificationMTEB AmazonCounterfactualClassification (en)main_score94.284
ClassificationMTEB AmazonPolarityClassificationaccuracy97.742
ClassificationMTEB AmazonPolarityClassificationaccuracy_stderr0.074
ClassificationMTEB AmazonPolarityClassificationap96.474
ClassificationMTEB AmazonPolarityClassificationap_stderr0.298
ClassificationMTEB AmazonPolarityClassificationf197.742
ClassificationMTEB AmazonPolarityClassificationf1_stderr0.074
ClassificationMTEB AmazonPolarityClassificationmain_score97.742
ClassificationMTEB AmazonReviewsClassification (en)accuracy63.960
ClassificationMTEB AmazonReviewsClassification (en)accuracy_stderr1.816
ClassificationMTEB AmazonReviewsClassification (en)f162.494
ClassificationMTEB AmazonReviewsClassification (en)f1_stderr2.829
ClassificationMTEB AmazonReviewsClassification (en)main_score63.960
RetrievalMTEB ArguAnamap_at_146.515
RetrievalMTEB ArguAnamap_at_1062.392
RetrievalMTEB ArguAnamap_at_10062.732
RetrievalMTEB ArguAnamap_at_100062.733
RetrievalMTEB ArguAnamap_at_358.701

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys nv-embed for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nv-embed below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nv-embed","input":"text to embed"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms