zjunlp/ModelKinship
Exploring Model Kinship for Merging Large Language Models
This tool helps AI researchers and practitioners who merge large language models (LLMs) to understand how different models relate to each other. It takes two fine-tuned LLMs and their common base model, then calculates a 'kinship' score. This score indicates the similarity in how the models learned, helping users choose optimal models for merging to achieve better performance and reduce trial-and-error.
No commits in the last 6 months.
Use this if you are iteratively merging large language models and want to make more informed decisions about which models to combine for optimal results.
Not ideal if you are looking for a general-purpose LLM evaluation or merging toolkit, as this focuses specifically on analyzing model relatedness.
Stars
27
Forks
3
Language
Python
License
MIT
Category
Last pushed
Apr 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zjunlp/ModelKinship"
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