{"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/light-peft-lightening-parameter-efficient","title":"Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning","arxiv_id":"2406.03792","date":"2024-06-06","proceeding":null,"authors":["Naibin Gu","Peng Fu","Xiyu Liu","Bowen Shen","Zheng Lin","Weiping Wang"],"abstract":"Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inadequate training efficiency. Firstly, the utilization of large-scale foundation models during the training process is excessively redundant for certain fine-tuning tasks. Secondly, as the model size increases, the growth in trainable parameters of empirically added PEFT modules becomes non-negligible and redundant, leading to inefficiency. To achieve task-specific efficient fine-tuning, we propose the Light-PEFT framework, which includes two methods: Masked Early Pruning of the Foundation Model and Multi-Granularity Early Pruning of PEFT. The Light-PEFT framework allows for the simultaneous estimation of redundant parameters in both the foundation model and PEFT modules during the early stage of training. These parameters can then be pruned for more efficient fine-tuning. We validate our approach on GLUE, SuperGLUE, QA tasks, and various models. With Light-PEFT, parameters of the foundation model can be pruned by up to over 40%, while still controlling trainable parameters to be only 25% of the original PEFT method. Compared to utilizing the PEFT method directly, Light-PEFT achieves training and inference speedup, reduces memory usage, and maintains comparable performance and the plug-and-play feature of PEFT.","url_abs":"https://arxiv.org/abs/2406.03792v1","url_pdf":"https://arxiv.org/pdf/2406.03792v1.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":"light-peft-lightening-parameter-efficient","repo_url":"https://github.com/gccnlp/light-peft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.03792","atlas_url":"https://app.syntology.ai/?focus=2406.03792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03792"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/gccnlp/light-peft","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":6,"samples":[{"code_sha256_prefix":"ecf94b05123201e3","entry":"bloom_model_postprocess_past_key_value","repo":"gccnlp/light-peft","repo_kind":"official","path":"peft/src/peft/utils/other.py","file_url":"https://github.com/gccnlp/light-peft/blob/HEAD/peft/src/peft/utils/other.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecf94b05123201e3"}},{"code_sha256_prefix":"f3ce42648e83a4dd","entry":"prepare_model_for_int8_training","repo":"gccnlp/light-peft","repo_kind":"official","path":"peft/src/peft/utils/other.py","file_url":"https://github.com/gccnlp/light-peft/blob/HEAD/peft/src/peft/utils/other.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3ce42648e83a4dd"}},{"code_sha256_prefix":"9d6a7aa341c6be64","entry":"prune_linear_layer","repo":"gccnlp/light-peft","repo_kind":"official","path":"peft/src/peft/tuners/lora.py","file_url":"https://github.com/gccnlp/light-peft/blob/HEAD/peft/src/peft/tuners/lora.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d6a7aa341c6be64"}},{"code_sha256_prefix":"5af2b785cc55d3ea","entry":"shift_tokens_right","repo":"gccnlp/light-peft","repo_kind":"official","path":"peft/src/peft/utils/other.py","file_url":"https://github.com/gccnlp/light-peft/blob/HEAD/peft/src/peft/utils/other.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5af2b785cc55d3ea"}},{"code_sha256_prefix":"6405b3acf7821b9d","entry":"get_peft_model_state_dict","repo":"gccnlp/light-peft","repo_kind":"official","path":"peft/src/peft/utils/save_and_load.py","file_url":"https://github.com/gccnlp/light-peft/blob/HEAD/peft/src/peft/utils/save_and_load.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6405b3acf7821b9d"}},{"code_sha256_prefix":"fbb3cd1c8af5bf8e","entry":"set_peft_model_state_dict","repo":"gccnlp/light-peft","repo_kind":"official","path":"peft/src/peft/utils/save_and_load.py","file_url":"https://github.com/gccnlp/light-peft/blob/HEAD/peft/src/peft/utils/save_and_load.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbb3cd1c8af5bf8e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}