ModelRefs / Model Merging — AI Glossary
Model Merging — AI Glossary
Combining the weights of multiple fine-tuned models into a single model that inherits capabilities from each, without additional training.
Overview
Model merging methods (SLERP, TIES-merging, DARE, Model Stock) interpolate or selectively combine weight tensors. Frankenmerges on HuggingFace combine models with different specialties (coding + instruction-following). No GPU needed for merging; the result may outperform individual components on combined benchmarks.
Reference details
| Topic | training |
|---|---|
| Also known as | weight merging, model soup, frankenmerge |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Model Merging — AI Glossary.
Frequently asked questions
What is Model Merging?
Combining the weights of multiple fine-tuned models into a single model that inherits capabilities from each, without additional training.
Is Model Merging the same as weight merging?
Yes — weight merging, model soup, frankenmerge are common aliases for Model Merging.
What concepts are related to Model Merging?
Closely related concepts include model soup, lora, adapter.