Mergenetic: a Simple Evolutionary Model Merging Library

• URL: http://arxiv.org/abs/2505.11427v1
• Date: Fri, 16 May 2025 16:43:23 GMT
• Title: Mergenetic: a Simple Evolutionary Model Merging Library
• Abstract summary: We introduce Mergenetic, an open-source library for evolutionary model merging.<n>We show that Mergenetic produces competitive results across tasks and languages using modest hardware.
• Score: 14.791853860278914
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has made it increasingly popular thanks to its low cost and the availability of libraries that support merging on consumer GPUs. Recent work shows that pairing merging with evolutionary algorithms can boost performance, but no framework currently supports flexible experimentation with such strategies in language models. We introduce Mergenetic, an open-source library for evolutionary model merging. Mergenetic enables easy composition of merging methods and evolutionary algorithms while incorporating lightweight fitness estimators to reduce evaluation costs. We describe its design and demonstrate that Mergenetic produces competitive results across tasks and languages using modest hardware.

Related papers

• EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization [27.31325788417927]
  We propose Evolutionary Generative Merging (EvoGM), a framework that employs learnable generative modeling to optimize merging coefficients.<n>EvoGM features a dual-generator architecture with cycle-consistent learning to adaptively sample and refine promising merging candidates.<n>Experiments across diverse benchmarks demonstrate that EvoGM significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-28T03:22:54Z)
• Competition and Attraction Improve Model Fusion [17.83054848742515]
  Model merging is a powerful technique for integrating the specialized knowledge of multiple machine learning models into a single model.<n>We propose Model Merging of Natural Niches (M2N2), an evolutionary algorithm with three key features.<n>M2N2 scales to merge specialized language and image generation models, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-08-22T08:24:02Z)
• NAN: A Training-Free Solution to Coefficient Estimation in Model Merging [61.36020737229637]
  We show that the optimal merging weights should scale with the amount of task-specific information encoded in each model.<n>We propose NAN, a simple yet effective method that estimates model merging coefficients via the inverse of parameter norm.<n>NAN is training-free, plug-and-play, and applicable to a wide range of merging strategies.
  arXiv  Detail & Related papers  (2025-05-22T02:46:08Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs [14.791853860278914]
  We introduce MERGE$3$, an efficient framework that makes evolutionary merging feasible on a single GPU.<n>MerGE$3$ achieves this by Extracting a reduced dataset for evaluation, Estimating model abilities using Item Response Theory (IRT), and Evolving optimal merges via IRT-based performance estimators.<n>Our method enables state-of-the-art multilingual and cross-lingual merging, transferring knowledge across languages with significantly lower computational overhead.
  arXiv  Detail & Related papers  (2025-02-09T14:24:16Z)
• Exploring Model Kinship for Merging Large Language Models [52.01652098827454]
  We introduce model kinship, the degree of similarity or relatedness between Large Language Models. We find that there is a certain relationship between model kinship and the performance gains after model merging. We propose a new model merging strategy: Top-k Greedy Merging with Model Kinship, which can yield better performance on benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-16T14:29:29Z)
• Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automation [0.9084344604313794]
  This paper explores model merging techniques across a spectrum of complexity. We introduce Differentiable Adaptive Merging (DAM), an efficient, adaptive merging approach. Our findings reveal that even simple averaging methods, like Model Soups, perform competitively when model similarity is high.
  arXiv  Detail & Related papers  (2024-10-10T20:58:29Z)
• Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild [84.57103623507082]
  This paper introduces Model-GLUE, a holistic Large Language Models scaling guideline.<n>We benchmark existing scaling techniques, especially selective merging, and variants of mixture.<n>We then formulate an optimal strategy for the selection and aggregation of a heterogeneous model zoo.<n>Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters.
  arXiv  Detail & Related papers  (2024-10-07T15:55:55Z)
• Knowledge Fusion By Evolving Weights of Language Models [5.354527640064584]
  This paper examines the approach of integrating multiple models into a unified model. We propose a knowledge fusion method named Evolver, inspired by evolutionary algorithms.
  arXiv  Detail & Related papers  (2024-06-18T02:12:34Z)
• Arcee's MergeKit: A Toolkit for Merging Large Language Models [0.6374098147778188]
  MergeKit is a framework to efficiently merge models on any hardware.<n>To date, thousands of models have been merged by the open-source community.
  arXiv  Detail & Related papers  (2024-03-20T02:38:01Z)
• DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence [77.78795329701367]
  We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning. We characterize DARLEI's performance under various conditions, revealing factors impacting diversity of evolved morphologies. We hope to extend DARLEI in future work to include interactions between diverse morphologies in richer environments.
  arXiv  Detail & Related papers  (2023-12-08T16:51:10Z)
• AdaLead: A simple and robust adaptive greedy search algorithm for sequence design [55.41644538483948]
  We develop an easy-to-directed, scalable, and robust evolutionary greedy algorithm (AdaLead) AdaLead is a remarkably strong benchmark that out-competes more complex state of the art approaches in a variety of biologically motivated sequence design challenges.
  arXiv  Detail & Related papers  (2020-10-05T16:40:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.