Jina Embeddings V3 Open-Source Multilingual Model - Free Deployment, Supports Similarity Calculation for Over 100 Languages

Jina Embeddings V3

Developed by koble-ai

Jina Embeddings V3 is a multilingual sentence embedding model supporting over 100 languages, focusing on sentence similarity calculation and feature extraction tasks.

Text Embedding

Transformers

Supports Multiple Languages#Multilingual sentence embeddings #Text similarity calculation #Cross-lingual semantic matching

Downloads 37

Release Time : 1/17/2025

Model Overview

This model is a multilingual sentence embedding model capable of converting text into high-dimensional vector representations for tasks such as sentence similarity calculation, information retrieval, and text classification.

Model Features

Multilingual support

Supports sentence embeddings for over 100 languages, including major languages and various minority languages.

Efficient feature extraction

Quickly converts text into high-dimensional vector representations for subsequent similarity calculations and analysis.

MTEB benchmark testing

Performs well in the MTEB benchmark, suitable for various text-related tasks.

Model Capabilities

Sentence vectorization

Multilingual text processing

Sentence similarity calculation

Text feature extraction

Use Cases

Information retrieval

Multilingual document retrieval

Finding semantically similar documents in a multilingual document library.

Achieved a primary score of 50.12% in the MTEB ArguAna-PL test.

Text classification

Multilingual text classification

Classifying texts in multiple languages.

🚀 jina-embeddings-v3

This is a multilingual model that can be used for feature extraction and sentence similarity tasks. It has been tested on various datasets in the MTEB benchmark.

📚 Documentation

Model Information

Property	Details
Model Type	jina-embeddings-v3
Training Data	Not provided
Library Name	transformers
Supported Languages	af, am, ar, as, az, be, bg, bn, br, bs, ca, cs, cy, da, de, el, en, eo, es, et, eu, fa, fi, fr, fy, ga, gd, gl, gu, ha, he, hi, hr, hu, hy, id, is, it, ja, jv, ka, kk, km, kn, ko, ku, ky, la, lo, lt, lv, mg, mk, ml, mn, mr, ms, my, ne, nl, no, om, or, pa, pl, ps, pt, ro, ru, sa, sd, si, sk, sl, so, sq, sr, su, sv, sw, ta, te, th, tl, tr, ug, uk, ur, uz, vi, xh, yi, zh
Inference	false

Evaluation Results

MTEB AFQMC (default)

Task Type: STS
Dataset Split: validation | Metric | Value | |--------|-------| | cosine_pearson | 41.74237700998808 | | cosine_spearman | 43.4726782647566 | | euclidean_pearson | 42.244585459479964 | | euclidean_spearman | 43.525070045169606 | | main_score | 43.4726782647566 | | manhattan_pearson | 42.04616728224863 | | manhattan_spearman | 43.308828270754645 | | pearson | 41.74237700998808 | | spearman | 43.4726782647566 |

MTEB ArguAna-PL (default)

Task Type: Retrieval
Dataset Split: test | Metric | Value | |--------|-------| | main_score | 50.117999999999995 | | map_at_1 | 24.253 | | map_at_10 | 40.725 | | map_at_100 | 41.699999999999996 | | map_at_1000 | 41.707 | | map_at_20 | 41.467999999999996 | | map_at_3 | 35.467 | | map_at_5 | 38.291 | | mrr_at_1 | 24.751066856330013 | | mrr_at_10 | 40.91063808169072 | | mrr_at_100 | 41.885497923928675 | | mrr_at_1000 | 41.89301098419842 | | mrr_at_20 | 41.653552355442514 | | mrr_at_3 | 35.656709340919775 | | mrr_at_5 | 38.466097676623946 | | ... (other metrics) | ... |

MTEB DBPedia-PL (default)

Task Type: Retrieval
Dataset Split: test | Metric | Value | |--------|-------| | main_score | 34.827000000000005 | | map_at_1 | 7.049999999999999 | | map_at_10 | 14.982999999999999 | | map_at_100 | 20.816000000000003 | | map_at_1000 | 22.33 | | map_at_20 | 17.272000000000002 | | map_at_3 | 10.661 | | map_at_5 | 12.498 | | mrr_at_1 | 57.25 | | mrr_at_10 | 65.81934523809524 | | mrr_at_100 | 66.2564203928212 | | mrr_at_1000 | 66.27993662923856 | | mrr_at_20 | 66.0732139130649 | | mrr_at_3 | 64.08333333333333 | | mrr_at_5 | 65.27083333333333 | | ... (other metrics) | ... |

MTEB FiQA-PL (default)

Task Type: Retrieval
Dataset Split: test | Metric | Value | |--------|-------| | main_score | 38.828 | | map_at_1 | 19.126 | | map_at_10 | 31.002000000000002 | | map_at_100 | 32.736 | | map_at_1000 | 32.933 | | map_at_20 | 31.894 | | map_at_3 | 26.583000000000002 | | map_at_5 | 28.904000000000003 | | mrr_at_1 | 37.808641975308646 | | ... (other metrics) | ... |

📄 License

This model is licensed under the CC BY-NC 4.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご