declare-lab/della
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
This tool helps AI engineers combine several specialized large language models (LLMs) into a single, more versatile model without needing extensive new training. You input your existing, fine-tuned LLMs that excel in specific areas (like math, coding, or general instructions), and it outputs a new, merged LLM capable of handling multiple tasks effectively. This is for machine learning practitioners or researchers who manage and deploy LLMs.
No commits in the last 6 months.
Use this if you need to consolidate multiple domain-specific large language models into one efficient model to reduce deployment costs or improve multi-task performance.
Not ideal if you're looking for a tool to train a large language model from scratch or to fine-tune a model on a completely new dataset.
Stars
36
Forks
3
Language
Python
License
—
Category
Last pushed
Jul 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/declare-lab/della"
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