Instructor-base Open-source Universal Embedding Model - Supports Instruction Guidance, Suitable for Various Text Processing Tasks

Instructor Base

Developed by hku-nlp

This is a general-purpose embedding model capable of generating domain-specific and task-aware embedding vectors through instruction guidance, suitable for various text processing tasks.

Text Embedding

Transformers

EnglishOpen Source License:Apache-2.0 #Instruction-guided Embedding #Domain-specific #Task-aware Vectors

Downloads 56

Release Time : 12/17/2022

Model Overview

This model is a sentence transformer that maps any text fragment into a fixed-length vector, achieving domain specificity and task awareness through instruction guidance.

Model Features

Instruction-guided Embedding

Generates domain-specific and task-aware embedding vectors through instruction guidance, adapting to different domains and tasks without additional training.

Generality

Capable of processing any text fragment, including titles, sentences, and documents, generating fixed-length vector representations.

Domain-specific

The generated embedding vectors are optimized for specific domains (e.g., science, finance).

Task-aware

Embedding vectors can be customized for different tasks (e.g., classification, information retrieval).

Model Capabilities

Text embedding generation

Sentence similarity calculation

Feature extraction

Use Cases

Scientific Research

Scientific Literature Title Similarity Calculation

Calculates the similarity between scientific literature titles for literature retrieval or recommendation systems.

Financial Analysis

Financial News Similarity Analysis

Analyzes the similarity between financial news for market trend prediction or news classification.

🚀 hku-nlp/instructor-base

This is a general embedding model that maps any text (such as a title, sentence, or document) to a fixed-length vector during testing without further training. With instructions, the embeddings are domain-specific (e.g., specialized for science, finance, etc.) and task-aware (e.g., customized for classification, information retrieval, etc.). The model is easily used with the sentence-transformer library.

🚀 Quick Start

This model simplifies the process of generating domain - specific and task - aware embeddings. You can quickly get started with the installation and usage steps below.

✨ Features

General Embedding: Capable of embedding any text into a fixed - length vector without additional training.
Domain - Specific and Task - Aware: Produces embeddings tailored to specific domains and tasks with the use of instructions.
Easy to Use: Compatible with the sentence - transformer library.

📦 Installation

git clone https://github.com/HKUNLP/instructor-embedding
cd sentence-transformers
pip install -e .

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer
sentence = "3D ActionSLAM: wearable person tracking in multi-floor environments"
instruction = "Represent the Science title; Input:"
model = SentenceTransformer('hku-nlp/instructor-base')
embeddings = model.encode([[instruction,sentence,0]])
print(embeddings)

Advanced Usage

from sklearn.metrics.pairwise import cosine_similarity
sentences_a = [['Represent the Science sentence; Input: ','Parton energy loss in QCD matter',0], 
               ['Represent the Financial statement; Input: ','The Federal Reserve on Wednesday raised its benchmark interest rate.',0]]
sentences_b = [['Represent the Science sentence; Input: ','The Chiral Phase Transition in Dissipative Dynamics', 0],
               ['Represent the Financial statement; Input: ','The funds rose less than 0.5 per cent on Friday',0]]
embeddings_a = model.encode(sentences_a)
embeddings_b = model.encode(sentences_b)
similarities = cosine_similarity(embeddings_a,embeddings_b)
print(similarities)

📄 License

This project is licensed under the Apache 2.0 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