Leeroo-AI/mergoo

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

49
/ 100
Emerging

This is a library designed for machine learning engineers and researchers who work with large language models. It helps combine the specialized knowledge of multiple existing LLM experts into a single, more versatile model. You provide several pre-trained LLMs (like those specialized in math or coding) as input, and it outputs a new, merged LLM that can perform well across different domains, which can then be further fine-tuned.

507 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to create a single LLM that leverages the distinct strengths of several specialized models without starting from scratch.

Not ideal if you are looking for a no-code solution or primarily work with traditional machine learning models outside of the LLM ecosystem.

large-language-models model-fine-tuning model-composition ai-research machine-learning-engineering
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

507

Forks

33

Language

Python

License

LGPL-3.0

Last pushed

Aug 26, 2024

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Leeroo-AI/mergoo"

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