uiuctml/Localize-and-Stitch
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
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.
Stars
32
Forks
—
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
ZHZisZZ/dllm
dLLM: Simple Diffusion Language Modeling
pengzhangzhi/Open-dLLM
Open diffusion language model for code generation — releasing pretraining, evaluation,...
EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM...
THUDM/LongWriter
[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
AIoT-MLSys-Lab/SVD-LLM
[ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2