E

E5 Small Unsupervised

Developed by intfloat
The unsupervised version of E5-small, generating text embeddings through weakly supervised contrastive pre-training, suitable for tasks like text similarity calculation
Downloads 2,093
Release Time : 1/31/2023

Model Overview

This model is a contrastive learning-based text embedding model capable of converting text into vector representations, primarily used for sentence similarity computation and information retrieval tasks

Model Features

Unsupervised Pre-training
Uses weakly supervised contrastive learning for pre-training without requiring labeled data
Efficient Embedding
Generates compact 384-dimensional text embeddings
Prefix-sensitive
Supports distinguishing different text types via 'query:' and 'passage:' prefixes

Model Capabilities

Text vectorization
Sentence similarity calculation
Information retrieval
Semantic search

Use Cases

Information Retrieval
Document Retrieval
Find relevant document passages based on queries
Performs well on the BEIR benchmark
Semantic Analysis
Sentence Similarity Calculation
Compute semantic similarity between two sentences
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase