Tools for merging pretrained large language models.

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.

Code release for Dataless Knowledge Fusion by Merging Weights of Language Models (https://openreview.net/forum?id=FCnohuR6AnM)

FusionBench: A Comprehensive Benchmark/Toolkit of Deep Model Fusion

AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.

ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse

Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

Representation Surgery for Multi-Task Model Merging. ICML, 2024.

All-in-one UI for merged LLMs in Hugging Face

Exploring Model Kinship for Merging Large Language Models

[ECCV'24] MaxFusion: Plug & Play multimodal generation in text to image diffusion models

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

flow-merge is a powerful Python library that enables seamless merging of multiple transformer-based language models using the most popular merge methods such as model soups, SLERP, ties-MERGING or DARE.

[ECCV 2024] MagMax: Leveraging Model Merging for Seamless Continual Learning (official repository)

A model merging project for generalizing Featured Finite State Machines (FFSMs) to unify behaviors across Software Product Lines (SPLs)

Merge transformers without using like a bajillion GB of RAM

An easy-to-use Python library for merging PyTorch models.

SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery. Arxiv, 2024.

This repository serves as a template for creating new projects based on FusionBench. It includes all the necessary configurations and boilerplate code to get started quickly.