uiuctml/Localize-and-Stitch

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

33
/ 100
Emerging

This project helps machine learning engineers and researchers combine the specialized knowledge from several fine-tuned models into a single, more versatile model without losing performance. It takes multiple fine-tuned models, identifies the key skill regions in each, and integrates only those essential parts into a base model, resulting in a unified model with broad capabilities. This is for professionals managing large AI models who need to consolidate multiple task-specific models efficiently.

Use this if you need to merge the distinct abilities of several fine-tuned large language or vision models into one without performance degradation and with reduced computational overhead.

Not ideal if you are working with models that require global parameter adjustments for merging or if you do not have pre-trained and fine-tuned models to combine.

model-optimization large-language-models computer-vision machine-learning-engineering model-deployment
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

32

Forks

Language

Python

License

MIT

Last pushed

Feb 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/uiuctml/Localize-and-Stitch"

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