EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.

49
/ 100
Emerging

If you're working with large language models (LLMs) or multimodal LLMs and want to combine the strengths of several specialized models without retraining them from scratch, this resource helps you. It takes various pre-trained models and shows you how to 'merge' their knowledge, resulting in a single, more capable model. This is for machine learning practitioners, researchers, and engineers who build or deploy advanced AI systems.

689 stars. Actively maintained with 20 commits in the last 30 days.

Use this if you need to integrate diverse capabilities from multiple large language models or other machine learning models into a single unified model efficiently.

Not ideal if you are looking for a tool to train models from scratch or if your primary need is general-purpose model optimization unrelated to combining expertise.

large-language-models multimodal-ai continual-learning machine-learning-engineering model-optimization
No License No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

689

Forks

40

Language

License

Last pushed

Mar 13, 2026

Commits (30d)

20

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications"

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