Luke

Visit Tool

LUKE is an open-source language understanding model that uses knowledge-based embeddings. It achieves state-of-the-art results on NLP benchmarks by representing both words and entities in context, and is available on Hugging Face Transformers.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is luke?

LUKE (Language Understanding with Knowledge-based Embeddings) is a cutting-edge pretrained contextualized representation model for words and entities, built upon a transformer architecture. It incorporates entity-aware self-attention to achieve state-of-the-art performance across various NLP benchmarks, including SQuAD v1.1 for extractive question answering, CoNLL-2003 for named entity recognition, ReCoRD for cloze-style question answering, TACRED for relation classification, and Open Entity for entity typing. The repository provides source code for both pretraining the model and fine-tuning it for downstream tasks. LUKE models, including Japanese versions and lite versions with reduced memory footprint, are readily available on the Hugging Face Model Hub, making them accessible for researchers and developers.

Best used for

Ideal for AI researchers and machine learning engineers who need to implement state-of-the-art natural language understanding models, fine-tune them for specific tasks like named entity recognition or question answering, and leverage pre-trained models for various NLP applications. Especially valuable for those working with entity-centric tasks and requiring high performance on established benchmarks.

Common actions

understand language

extract entities

classify relations

answer questions

fine-tune models

"AI Agents"github copilotopen-sourcelow-code/no-codecollaborationdeepfakeface swappingautomated workflowworkflows

Capabilities

Key features

Contextualized word embeddings
Contextualized entity embeddings
Entity-aware self-attention
Pretraining code available
Fine-tuning code available
Hugging Face Transformers integration
Japanese language models

Target Audience

AI researchermachine learning engineerprofessor

Integrations

hugging-face-transformers

Pricing & Plans

Open Source

Free

FAQs

What kind of NLP tasks can LUKE be used for?

LUKE excels in various NLP tasks, including extractive question answering (SQuAD), named entity recognition (CoNLL-2003), cloze-style question answering (ReCoRD), relation classification (TACRED), and fine-grained entity typing (Open Entity). It provides strong performance across these entity-related tasks.

Are there different versions of LUKE available?

Yes, LUKE is available in base and large versions, as well as Japanese-specific models. Additionally, 'lite' versions are offered, which have fewer parameters and a smaller memory footprint, making them suitable for fine-tuning on GPUs with limited memory, while maintaining performance.

How can I use LUKE with the Hugging Face Transformers library?

LUKE has been integrated into the Hugging Face Transformers library, allowing easy access to its pre-trained models. You can load models and tokenizers using `LukeTokenizer.from_pretrained()` and `LukeForEntityPairClassification.from_pretrained()` (or similar for other tasks) and then use them for inference or fine-tuning.

Trending

Subcategories trending in Coding & Development

Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Also listed in

This tool also appears in

Research & Education › Academic Research AI Agents & Automation › Chatbots & Conversational AI AI Agents & Automation › RAG & Document AI

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce