Home Projects GraphGPT
GraphGPT
Python

GraphGPT

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

by HKUDS · GitHub
Stars
Forks
License
Created
Last commit
Language
graph-learninggraph-neural-networksinstruction-tuningApache-2.0Python
View on GitHub
In plain words

Train and fine-tune a language model using graph-based instructions with provided code and data.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
GraphGPT — GitHub preview card
📈 Star history
835832
2026-07-202026-08-31
📈 Track GraphGPT

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

GraphGPT has 832 stars on GitHub. It has been forked 85 times. GraphGPT is written mainly in Python. It has been in active development since 2023. GraphGPT is available under the Apache-2.0 license. Its main topics are graph-learning, graph-neural-networks, instruction-tuning, large-language-models.

Frequently asked questions

What is GraphGPT?

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

Is GraphGPT open source?

GraphGPT is an open-source project. It is released under the Apache-2.0 license.

Is GraphGPT free?

Yes. GraphGPT is free and open source — you can use, modify and self-host it.

What license does GraphGPT use?

GraphGPT is available under the Apache-2.0 license.

What language is GraphGPT written in?

GraphGPT is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — GraphGPT

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=hkuds-graphgpt)](https://olud.ai/project/hkuds-graphgpt.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.