{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/model-stock-all-we-need-is-just-a-few-fine","title":"Model Stock: All we need is just a few fine-tuned models","arxiv_id":"2403.19522","date":"2024-03-28","proceeding":null,"authors":["Dong-Hwan Jang","Sangdoo Yun","Dongyoon Han"],"abstract":"This paper introduces an efficient fine-tuning method for large pre-trained models, offering strong in-distribution (ID) and out-of-distribution (OOD) performance. Breaking away from traditional practices that need a multitude of fine-tuned models for averaging, our approach employs significantly fewer models to achieve final weights yet yield superior accuracy. Drawing from key insights in the weight space of fine-tuned weights, we uncover a strong link between the performance and proximity to the center of weight space. Based on this, we introduce a method that approximates a center-close weight using only two fine-tuned models, applicable during or after training. Our innovative layer-wise weight averaging technique surpasses state-of-the-art model methods such as Model Soup, utilizing only two fine-tuned models. This strategy can be aptly coined Model Stock, highlighting its reliance on selecting a minimal number of models to draw a more optimized-averaged model. We demonstrate the efficacy of Model Stock with fine-tuned models based upon pre-trained CLIP architectures, achieving remarkable performance on both ID and OOD tasks on the standard benchmarks, all while barely bringing extra computational demands. Our code and pre-trained models are available at https://github.com/naver-ai/model-stock.","url_abs":"https://arxiv.org/abs/2403.19522v1","url_pdf":"https://arxiv.org/pdf/2403.19522v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"model-stock-all-we-need-is-just-a-few-fine","repo_url":"https://github.com/naver-ai/model-stock","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"model-stock-all-we-need-is-just-a-few-fine","repo_url":"https://github.com/arcee-ai/mergekit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"LGPL-3.0"}}],"tasks":[{"task_slug":"all","task_name":"All"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.19522","atlas_url":"https://app.syntology.ai/?focus=2403.19522","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}