AI engineering glossary · LLM training alignment
What is model merging?
Model merging (also called Weight merging): Combining the weights of several fine-tuned models that share a base into one model, for example by averaging or by adding weight differences, without extra training. It can blend skills cheaply, though results depend on how compatible the models are.
Model merging: an example
Averaging a coding-tuned and a maths-tuned version of the same base yields one model with both abilities.
Related terms
More LLM training alignment terms
- Next-token prediction
- NormalFloat 4-bit
- Odds ratio preference optimisation
- Overtrained model
- Paged optimisers
- Parameter-efficient fine-tuning
- PEFT library
- Pipeline parallelism
Where you learn it
Model merging is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.