AIbase
EN
Home
Conan Embedding V1 Q4 K M GGUF
C

Conan Embedding V1 Q4 K M GGUF

Developed by KenLi315
Conan-embedding-v1 is a Chinese text embedding model developed by the Tencent BAC team, focusing on semantic representation and similarity calculation for Chinese text.
Text Embedding Chinese#Chinese Text Embedding#Multi-task Evaluation#High-precision Semantic Similarity
Downloads 48
Release Time : 1/28/2025

Model Overview

This model is primarily used for semantic embedding representation of Chinese text, supporting various natural language processing tasks such as text similarity calculation, classification, clustering, and retrieval.

Model Features

Chinese Optimization
Specifically optimized for Chinese text, capable of better capturing Chinese semantic features.
Multi-task Support
Supports various natural language processing tasks, including text similarity calculation, classification, clustering, and retrieval.
High Performance
Outperforms in multiple Chinese benchmark tests, especially in semantic similarity tasks.

Model Capabilities

Text embedding
Semantic similarity calculation
Text classification
Text clustering
Information retrieval
Re-ranking

Use Cases

Information Retrieval
Medical Q&A Retrieval
Used in medical Q&A retrieval systems to help users quickly find relevant medical information.
Performs well on the CMedqaRetrieval dataset, achieving a map@100 of 42.495
Text Similarity
Q&A Pair Matching
Determines the semantic relevance between questions and answers.
Achieves a cos_sim_spearman of 74.507 on the BQ dataset
Text Classification
Product Review Classification
Performs sentiment classification on product reviews from e-commerce platforms.
Achieves an accuracy of 90.319% on the JDReview classification task
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