ritrieve_zh_v1 Open-Source Sentence Embedding Model - Focusing on Chinese Text Similarity Calculation Tasks!

Ritrieve Zh V1

Developed by richinfoai

This model is a sentence embedding model obtained through distillation training from multiple excellent Chinese vector models, focusing on Chinese text similarity calculation tasks.

Text Embedding

Safetensors

ChineseOpen Source License:MIT #Chinese Semantic Similarity #Multi-model Distillation #1792-dimensional Vector

Downloads 827

Release Time : 3/25/2025

Model Overview

This is a Chinese sentence embedding model that learns from multiple excellent models through distillation training methods, used for calculating semantic similarity of Chinese texts.

Model Features

Multi-model Distillation

Enhances model performance by integrating knowledge from multiple excellent Chinese vector models through distillation training

Two-stage Training

First stage uses cosine loss function training, followed by dimensionality reduction in the second stage

High Performance

Demonstrates excellent performance in the MTEB(cmn, v1) benchmark test

Model Capabilities

Chinese Text Embedding

Semantic Similarity Calculation

Text Retrieval

Use Cases

Information Retrieval

Document Similarity Calculation

Calculate semantic similarity between different documents

Effectively identifies semantically similar documents

Q&A Systems

Question Matching

Match user questions with similar questions in the knowledge base

Improves the accuracy of Q&A systems

🚀 Richinfoai Retrieval Model

This model is a sentence similarity model trained by richinfoai, achieving excellent results through distillation learning.

🚀 Quick Start

This model is trained by richinfoai. Following Stella and Jasper models, we conduct distillation training from lier007/xiaobu-embedding-v2, dunzhang/stella-large-zh-v3-1792d, and BAAI/bge-multilingual-gemma2. Thanks to their outstanding performance, our model has achieved excellent results on MTEB(cmn, v1).

We believe this model once again demonstrates the effectiveness of distillation learning. In the future, we will train more bilingual vector models based on various excellent vector training methods.

✨ Features

Trained using distillation learning from multiple excellent models.
Achieved excellent results on MTEB(cmn, v1).
Can be used for sentence similarity tasks.

📦 Installation

There is no specific installation steps provided in the original README. If you want to use this model, you need to have sentence-transformers installed. You can install it using the following command:

pip install sentence-transformers

💻 Usage Examples

Basic Usage

This model does not need instructions and you can use it in SentenceTransformer:

import os

os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
from sentence_transformers import SentenceTransformer

text_encoder = SentenceTransformer("richinfoai/ritrieve_zh_v1")
texts = [
    "什么是人工智能",
    "介绍一下主流的LLM",
    "人工智能（AI）是模拟人类智能的计算机系统，能够执行学习、推理和决策等任务。它通过算法和大数据实现自动化，广泛应用于各行各业。"
]
vectors = text_encoder.encode(texts, normalize_embeddings=True)
print(vectors @ vectors.T)
# [[0.9999999  0.67707014 0.91421044]
#  [0.67707014 0.9999998  0.6353945 ]
#  [0.91421044 0.6353945  1.0000001 ]]

🔧 Technical Details

Stage1

We use BAAI/Infinity-Instruct and opencsg/chinese-fineweb-edu as training data to do a distillation from the above three models. In this stage, we only use cosine-loss.

Stage2

The objective of stage2 is reducing dimensions. We use the same training data as the stage1 with similarity loss. After stage2, the dimensions of our model is 1792.

📄 License

This project is licensed under the MIT 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