codefuse-ai/GALLa

[ACL 2025] Graph Aligned Large Language Models for Improved Source Code Understanding

31
/ 100
Emerging

This project helps AI developers create more accurate large language models (LLMs) specifically for understanding source code. By aligning LLMs with the structural graphs of code (like how the code flows or its grammatical structure), it enables these models to process raw source code and graph data, producing LLMs that better comprehend and respond to code-related queries. This is designed for AI/ML engineers and researchers who are building or fine-tuning LLMs for software engineering tasks.

No commits in the last 6 months.

Use this if you need to develop or enhance an LLM's ability to accurately understand and analyze source code by incorporating its underlying structural information.

Not ideal if you are looking for a pre-trained, ready-to-use LLM for general text understanding or code generation without needing to delve into model architecture and training.

AI-development large-language-models code-analysis software-engineering-AI machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

43

Forks

2

Language

Python

License

Apache-2.0

Last pushed

May 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/codefuse-ai/GALLa"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.