// ⚙ Fine-tuning & PEFT
Model Merging & Task Arithmetic
Combines fine-tuned models by adding, subtracting or averaging weights.
模型合并与任务算术 2022 Intermediate core
IN PLAIN WORDS
Fine-tuned minus base weights gives a task vector; adding combines skills, subtracting removes behaviors. Model soups show averaging fine-tunes improves accuracy at no inference cost.
Used in: Community merged models (mergekit)
01Original paper
Editing Models with Task Arithmetic
Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, et al. · 2022
arXiv ↗ ✓ Verified · arXiv API
Note: Model Soups：arXiv:2203.05482（2022）
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
- Nothing in the atlas builds on it yet
Related:Knowledge Distillation
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Reference code
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
model-merging)