AIbase
EN
Home
Tao 8k
T

Tao 8k

Developed by Amu
tao-8k-origin is a model focused on sentence similarity calculation, supporting multiple similarity measurement methods and excelling in various Chinese evaluation datasets.
Text Embedding
PyTorch
 ChineseOpen Source License:Apache-2.0#Chinese Sentence Similarity#Medical QA Re-ranking#Multi-task Evaluation
Downloads 639
Release Time : 11/4/2023

Model Overview

This model is primarily used to calculate the similarity between sentences, supporting various measurement methods such as cosine similarity, Euclidean distance, and Manhattan distance. It is suitable for scenarios like text matching and information retrieval.

Model Features

Multi-metric Similarity Calculation
Supports multiple similarity measurement methods such as cosine similarity, Euclidean distance, and Manhattan distance.
Chinese Optimization
Optimized for Chinese text, demonstrating excellent performance on multiple Chinese evaluation datasets.
Broad Task Support
Supports various tasks including sentence similarity, classification, clustering, re-ranking, and retrieval.

Model Capabilities

Sentence Similarity Calculation
Text Classification
Text Clustering
Information Retrieval
Re-ranking

Use Cases

Text Matching
QA Matching
Used to match the similarity between questions and answers, improving the accuracy of QA systems.
Achieved an average accuracy of over 85% on the CMedQAv1 and CMedQAv2 datasets.
Semantic Similarity Calculation
Calculates the semantic similarity between two sentences for use in recommendation systems or search ranking.
Performed exceptionally well on the AFQMC and ATEC datasets.
Information Retrieval
Document Retrieval
Used to retrieve the most relevant documents for a query.
Performed well on the CmedqaRetrieval and CovidRetrieval datasets.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase