AIbase
EN
Home
Granite Embedding 30m English
G

Granite Embedding 30m English

Developed by ibm-granite
IBM Granite Embedding 30M English is a transformer-based English text embedding model developed and released by IBM.
Text Embedding
Transformers
 EnglishOpen Source License:Apache-2.0#English Text Embedding#Multi-task Evaluation#Classification Optimization
Downloads 78.53k
Release Time : 12/4/2024

Model Overview

This model is primarily used for generating high-quality English text embeddings, suitable for various natural language processing tasks such as text classification and information retrieval.

Model Features

High-Quality Text Embeddings
Capable of generating high-quality English text embeddings, suitable for various downstream tasks.
Multi-Task Support
Performs well on multiple natural language processing tasks, including text classification and information retrieval.
Lightweight
With a model parameter size of 30M, it is relatively lightweight and suitable for resource-constrained environments.

Model Capabilities

Text Embedding Generation
Text Classification
Information Retrieval

Use Cases

E-commerce
Amazon Review Classification
Used for classifying Amazon product reviews to identify positive and negative feedback.
Achieved an accuracy of 62.98% on the MTEB AmazonPolarityClassification dataset.
Information Retrieval
App Retrieval
Used for retrieving relevant applications to improve search result relevance.
Achieved an NDCG@10 of 6.20 on the MTEB AppsRetrieval dataset.
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