{"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/mambapeft-exploring-parameter-efficient-fine","title":"MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba","arxiv_id":"2411.03855","date":"2024-11-06","proceeding":null,"authors":["Masakazu Yoshimura","Teruaki Hayashi","Yota Maeda"],"abstract":"An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost while achieving effective performance. Recently, Mamba, a State Space Model (SSM)-based model, has attracted attention as a potential alternative to Transformers. While many large-scale Mamba-based models have been proposed, efficiently adapting pre-trained Mamba-based models to downstream tasks remains unexplored. In this paper, we conduct an exploratory analysis of PEFT methods for Mamba. We investigate the effectiveness of existing PEFT methods for Transformers when applied to Mamba. We also modify these methods to better align with the Mamba architecture. Additionally, we propose new Mamba-specific PEFT methods that leverage the distinctive structure of Mamba. Our experiments indicate that PEFT performs more effectively for Mamba than Transformers. Lastly, we demonstrate how to effectively combine multiple PEFT methods and provide a framework that outperforms previous works. To ensure reproducibility, we will release the code after publication.","url_abs":"https://arxiv.org/abs/2411.03855v3","url_pdf":"https://arxiv.org/pdf/2411.03855v3.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":"mambapeft-exploring-parameter-efficient-fine","repo_url":"https://github.com/sony/MambaPEFT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"mamba","method_name":"Mamba"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.03855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03855"}},"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/sony/MambaPEFT","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"56e674752db00649","entry":"generate_prompt","repo":"sony/MambaPEFT","repo_kind":"official","path":"language/commonsense_reasoning/finetune.py","file_url":"https://github.com/sony/MambaPEFT/blob/HEAD/language/commonsense_reasoning/finetune.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56e674752db00649"}},{"code_sha256_prefix":"ac6e2e3d7b4fe003","entry":"create_block","repo":"sony/MambaPEFT","repo_kind":"official","path":"vision/personal_lib/mmpretrain/models/backbones/vim.py","file_url":"https://github.com/sony/MambaPEFT/blob/HEAD/vision/personal_lib/mmpretrain/models/backbones/vim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac6e2e3d7b4fe003"}},{"code_sha256_prefix":"38dd3347bffbf9be","entry":"forward_features_visionmamba_peft","repo":"sony/MambaPEFT","repo_kind":"official","path":"vision/personal_lib/mmpretrain/models/peft/vim_peft_all.py","file_url":"https://github.com/sony/MambaPEFT/blob/HEAD/vision/personal_lib/mmpretrain/models/peft/vim_peft_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38dd3347bffbf9be"}},{"code_sha256_prefix":"5ab86311e9a660c2","entry":"forward_mamba_peft","repo":"sony/MambaPEFT","repo_kind":"official","path":"vision/personal_lib/mmpretrain/models/peft/vim_peft_all.py","file_url":"https://github.com/sony/MambaPEFT/blob/HEAD/vision/personal_lib/mmpretrain/models/peft/vim_peft_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5ab86311e9a660c2"}},{"code_sha256_prefix":"7f5a4d972fbdf561","entry":"forward_vimblock_peft","repo":"sony/MambaPEFT","repo_kind":"official","path":"vision/personal_lib/mmpretrain/models/peft/vim_peft_all.py","file_url":"https://github.com/sony/MambaPEFT/blob/HEAD/vision/personal_lib/mmpretrain/models/peft/vim_peft_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f5a4d972fbdf561"}},{"code_sha256_prefix":"e5a8e65efe137e3f","entry":"forwardv2_peft","repo":"sony/MambaPEFT","repo_kind":"official","path":"vision/personal_lib/mmpretrain/models/peft/vmamba_peft_all.py","file_url":"https://github.com/sony/MambaPEFT/blob/HEAD/vision/personal_lib/mmpretrain/models/peft/vmamba_peft_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e5a8e65efe137e3f"}},{"code_sha256_prefix":"ef7026ee8b73635d","entry":"vssblock_forward","repo":"sony/MambaPEFT","repo_kind":"official","path":"vision/personal_lib/mmpretrain/models/peft/vmamba_peft_all.py","file_url":"https://github.com/sony/MambaPEFT/blob/HEAD/vision/personal_lib/mmpretrain/models/peft/vmamba_peft_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ef7026ee8b73635d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}