apanariello4/merge-and-rebase
Model merging, task-vector rebasin, and fine-tuning for vision and LLM models.
This project helps machine learning researchers and practitioners combine the knowledge from several specialized AI models into a single, more capable model. You provide multiple fine-tuned vision or language models, and it outputs a merged model that can perform tasks from all of them. This is for AI developers, researchers, and ML engineers working with large language models and vision models.
Use this if you need to merge multiple fine-tuned AI models (like vision models or LLMs) to create a new model that can handle a broader set of tasks or improve performance on specific ones.
Not ideal if you are looking for a simple, no-code solution for basic model deployment or if you are not comfortable working with model checkpoints and configuration files.
Stars
18
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/apanariello4/merge-and-rebase"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
arcee-ai/mergekit
Tools for merging pretrained large language models.
changyeyu/LLM-RL-Visualized
๐100+ ๅๅ LLM / RL ๅ็ๅพ๐๏ผใๅคงๆจกๅ็ฎๆณใไฝ่ ๅทจ็ฎ๏ผ๐ฅ๏ผ100+ LLM/RL Algorithm Maps ๏ผ
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM