{"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/owlore-outlier-weighed-layerwise-sampled-low","title":"OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning","arxiv_id":"2405.18380","date":"2024-05-28","proceeding":null,"authors":["Pengxiang Li","Lu Yin","Xiaowei Gao","Shiwei Liu"],"abstract":"The rapid advancements in Large Language Models (LLMs) have revolutionized various natural language processing tasks. However, the substantial size of LLMs presents significant challenges in training or fine-tuning. While parameter-efficient approaches such as low-rank adaptation (LoRA) have gained popularity, they often compromise performance compared to full-rank fine-tuning. In this paper, we propose Outlier-weighed Layerwise Sampled Low-Rank Projection (OwLore), a new memory-efficient fine-tuning approach, inspired by the layerwise outlier distribution of LLMs. Unlike LoRA, which adds extra adapters to all layers, OwLore strategically assigns higher sampling probabilities to layers with more outliers, selectively sampling only a few layers and fine-tuning their pre-trained weights. To further increase the number of fine-tuned layers without a proportional rise in memory costs, we incorporate gradient low-rank projection, further boosting the approach's performance. Our extensive experiments across various architectures, including LLaMa2, LLaMa3, and Mistral, demonstrate that OwLore consistently outperforms baseline approaches, including full fine-tuning. Specifically, it achieves up to a 1.1% average accuracy gain on the Commonsense Reasoning benchmark, a 3.0% improvement on MMLU, and a notable 10% boost on MT-Bench, while being more memory efficient. OwLore allows us to fine-tune LLaMa2-7B with only 21GB of memory. Code is available at https://github.com/pixeli99/OwLore.","url_abs":"https://arxiv.org/abs/2405.18380v2","url_pdf":"https://arxiv.org/pdf/2405.18380v2.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":"owlore-outlier-weighed-layerwise-sampled-low","repo_url":"https://github.com/pixeli99/owlore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"owlore-outlier-weighed-layerwise-sampled-low","repo_url":"https://github.com/qiaoxiao7282/seft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mmlu","task_name":"MMLU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.18380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18380"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pixeli99/owlore","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qiaoxiao7282/seft","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"c12b55ef635e9947","entry":"pattern_match","repo":"pixeli99/owlore","repo_kind":"official","path":"utils/lm_evaluator.py","file_url":"https://github.com/pixeli99/owlore/blob/HEAD/utils/lm_evaluator.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c12b55ef635e9947"}},{"code_sha256_prefix":"adae74cb9afc983c","entry":"str2bool","repo":"qiaoxiao7282/seft","repo_kind":"listed","path":"lora_ft/finetune_split.py","file_url":"https://github.com/qiaoxiao7282/seft/blob/HEAD/lora_ft/finetune_split.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"adae74cb9afc983c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}