Overview

mxbai-embed-large-v1 is a high-performance embedding model designed for developers building RAG pipelines and semantic search applications. Unlike general-purpose models, it is optimized for retrieval tasks, offering a strong balance between dimensionality and retrieval accuracy. It excels at converting unstructured text into dense vectors that maintain high semantic similarity, making it a viable open-source alternative to proprietary embedding APIs. Integration is straightforward via standard libraries like Sentence-Transformers or Hugging Face, allowing for local deployment to reduce latency and ensure data privacy. For developers, this means better document retrieval precision and a more robust context window for LLM generation without relying on closed-source ecosystems.

Highlights

Optimized for high-accuracy RAG and semantic search tasks
Open-source Apache-2.0 license for flexible commercial deployment
Seamless integration with Hugging Face and Sentence-Transformers
Strong performance alternative to proprietary embedding models

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("mixedbread-ai/mxbai-embed-large-v1")
tokenizer = AutoTokenizer.from_pretrained("mixedbread-ai/mxbai-embed-large-v1")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download mixedbread-ai/mxbai-embed-large-v1

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download mixedbread-ai/mxbai-embed-large-v1 config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('mixedbread-ai/mxbai-embed-large-v1')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('mixedbread-ai/mxbai-embed-large-v1')
tokenizer = AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-embed-large-v1')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model mixedbread-ai/mxbai-embed-large-v1

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model mixedbread-ai/mxbai-embed-large-v1 README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('mixedbread-ai/mxbai-embed-large-v1')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/mixedbread-ai/mxbai-embed-large-v1.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/mixedbread-ai/mxbai-embed-large-v1.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'mixedbread-ai/mxbai-embed-large-v1')

Full Documentation

来源: HuggingFace

---
tags:

mteb

transformers.js

transformers

model-index:

name: mxbai-angle-large-v1

results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 75.044776119403
- type: ap
value: 37.7362433623053
- type: f1
value: 68.92736573359774
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 93.84025000000001
- type: ap
value: 90.93190875404055
- type: f1
value: 93.8297833897293
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 49.184
- type: f1
value: 48.74163227751588
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 41.252
- type: map_at_10
value: 57.778
- type: map_at_100
value: 58.233000000000004
- type: map_at_1000
value: 58.23700000000001
- type: map_at_3
value: 53.449999999999996
- type: map_at_5
value: 56.376000000000005
- type: mrr_at_1
value: 41.679
- type: mrr_at_10
value: 57.92699999999999
- type: mrr_at_100
value: 58.389
- type: mrr_at_1000
value: 58.391999999999996
- type: mrr_at_3
value: 53.651
- type: mrr_at_5
value: 56.521
- type: ndcg_at_1
value: 41.252
- type: ndcg_at_10
value: 66.018
- type: ndcg_at_100
value: 67.774
- type: ndcg_at_1000
value: 67.84400000000001
- type: ndcg_at_3
value: 57.372
- type: ndcg_at_5
value: 62.646
- type: precision_at_1
value: 41.252
- type: precision_at_10
value: 9.189
- type: precision_at_100
value: 0.991
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 22.902
- type: precision_at_5
value: 16.302
- type: recall_at_1
value: 41.252
- type: recall_at_10
value: 91.892
- type: recall_at_100
value: 99.14699999999999
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 68.706
- type: recall_at_5
value: 81.50800000000001
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 48.97294504317859
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 42.98071077674629
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 65.16477858490782
- type: mrr
value: 78.23583080508287
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 89.6277629421789
- type: cos_sim_spearman
value: 88.4056288400568
- type: euclidean_pearson
value: 87.94871847578163
- type: euclidean_spearman
value: 88.4056288400568
- type: manhattan_pearson
value: 87.73271254229648
- type: manhattan_spearman
value: 87.91826833762677
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 87.81818181818181
- type: f1
value: 87.79879337316918
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 39.91773608582761
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 36.73059477462478
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 32.745999999999995
- type: map_at_10
value: 43.632
- type: map_at_100
value: 45.206
- type: map_at_1000
value: 45.341
- type: map_at_3
value: 39.956
- type: map_at_5
value: 42.031
- type: mrr_at_1
value: 39.485
- type: mrr_at_10
value: 49.537
- type: mrr_at_100
value: 50.249
- type: mrr_at_1000
value: 50.294000000000004
- type: mrr_at_3
value: 46.757
- type: mrr_at_5
value: 48.481
- type: ndcg_at_1
value: 39.485
- type: ndcg_at_10
value: 50.058
- type: ndcg_at_100
value: 55.586
- type: ndcg_at_1000
value: 57.511
- type: ndcg_at_3
value: 44.786
- type: ndcg_at_5
value: 47.339999999999996
- type: precision_at_1
value: 39.485
- type: precision_at_10
value: 9.557
- type: precision_at_100
value: 1.552
- type: precision_at_1000
value: 0.202
- type: precision_at_3
value: 21.412
- type: precision_at_5
value: 15.479000000000001
- type: recall_at_1
value: 32.745999999999995
- type: recall_at_10
value: 62.056
- type: recall_at_100
value: 85.088
- type: recall_at_1000
value: 96.952
- type: recall_at_3
value: 46.959
- type: recall_at_5
value: 54.06999999999999
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 31.898
- type: map_at_10
value: 42.142
- type: map_at_100
value: 43.349
- type: map_at_1000
value: 43.483
- type: map_at_3
value: 39.18
- type: map_at_5
value: 40.733000000000004
- type: mrr_at_1
value: 39.617999999999995
- type: mrr_at_10
value: 47.922
- type: mrr_at_100
value: 48.547000000000004
- type: mrr_at_1000
value: 48.597
- type: mrr_at_3
value: 45.86
- type: mrr_at_5
value: 46.949000000000005
- type: ndcg_at_1
value: 39.617999999999995
- type: ndcg_at_10
value: 47.739
- type: ndcg_at_100
value: 51.934999999999995
- type: ndcg_at_1000
value: 54.007000000000005
- type: ndcg_at_3
value: 43.748
- type: ndcg_at_5
value: 45.345
- type: precision_at_1
value: 39.617999999999995
- type: precision_at_10
value: 8.962
- type: precision_at_100
value: 1.436
- type: precision_at_1000
value: 0.192
- type: precision_

mxbai embed large v1

Overview

Highlights

Usage

Hugging Face Download

CLI Download

SDK Download

Git Download

PyTorch / Transformers Usage

Model Download

CLI Download

SDK Download

Git Download

Notebook Quickstart

Full Documentation