{"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/bitfit-simple-parameter-efficient-fine-tuning","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","arxiv_id":"2106.10199","date":"2021-06-18","proceeding":"ACL 2022 5","authors":["Elad Ben Zaken","Shauli Ravfogel","Yoav Goldberg"],"abstract":"We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. We show that with small-to-medium training data, applying BitFit on pre-trained BERT models is competitive with (and sometimes better than) fine-tuning the entire model. For larger data, the method is competitive with other sparse fine-tuning methods. Besides their practical utility, these findings are relevant for the question of understanding the commonly-used process of finetuning: they support the hypothesis that finetuning is mainly about exposing knowledge induced by language-modeling training, rather than learning new task-specific linguistic knowledge.","url_abs":"https://arxiv.org/abs/2106.10199v5","url_pdf":"https://arxiv.org/pdf/2106.10199v5.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":"bitfit-simple-parameter-efficient-fine-tuning","repo_url":"https://github.com/benzakenelad/BitFit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bitfit-simple-parameter-efficient-fine-tuning","repo_url":"https://github.com/Aradhye2002/selective-peft-toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bitfit-simple-parameter-efficient-fine-tuning","repo_url":"https://github.com/cloudygoose/fewshot_lama","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"bitfit-simple-parameter-efficient-fine-tuning","repo_url":"https://github.com/mkshing/DiffFit-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bitfit-simple-parameter-efficient-fine-tuning","repo_url":"https://github.com/piero2c/BitInfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bitfit-simple-parameter-efficient-fine-tuning","repo_url":"https://github.com/uds-lsv/llmft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.10199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10199"}},"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/cloudygoose/fewshot_lama","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Aradhye2002/selective-peft-toolkit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/benzakenelad/BitFit","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/piero2c/BitInfer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mkshing/DiffFit-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uds-lsv/llmft","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"listed":{"samples":13,"ran":4,"repositories":3}},"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":"fd7783a0f859595f","entry":"BitAdditiveBias","repo":"piero2c/BitInfer","repo_kind":"listed","path":"bitinfer/wrappers/bert_modeling.py","file_url":"https://github.com/piero2c/BitInfer/blob/HEAD/bitinfer/wrappers/bert_modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd7783a0f859595f"}},{"code_sha256_prefix":"fc4cbb21fd52d41e","entry":"LoRALinearLayer","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc4cbb21fd52d41e"}},{"code_sha256_prefix":"99828ec14262bca0","entry":"SlicedAttnAddedKVProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99828ec14262bca0"}},{"code_sha256_prefix":"3e842c5dc40c0417","entry":"get_bitfit","repo":"Aradhye2002/selective-peft-toolkit","repo_kind":"listed","path":"selective_optimizers/optimizers/bitfit.py","file_url":"https://github.com/Aradhye2002/selective-peft-toolkit/blob/HEAD/selective_optimizers/optimizers/bitfit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e842c5dc40c0417"}},{"code_sha256_prefix":"5936bf677f1ca5e6","entry":"AttnAddedKVProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5936bf677f1ca5e6"}},{"code_sha256_prefix":"2772c67fd48b070d","entry":"AttnProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2772c67fd48b070d"}},{"code_sha256_prefix":"22a4995cd018342d","entry":"AttnProcessor2_0","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22a4995cd018342d"}},{"code_sha256_prefix":"9dc8c249e25cc758","entry":"DiffFitAttnProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9dc8c249e25cc758"}},{"code_sha256_prefix":"f986040d6b978c1a","entry":"DiffFitXFormersAttnProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f986040d6b978c1a"}},{"code_sha256_prefix":"b684827fec968595","entry":"LoRAAttnProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b684827fec968595"}},{"code_sha256_prefix":"7886240878f393a4","entry":"LoRAXFormersAttnProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7886240878f393a4"}},{"code_sha256_prefix":"63bf91f1802952a1","entry":"SlicedAttnProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63bf91f1802952a1"}},{"code_sha256_prefix":"921edfd779ddeac7","entry":"XFormersAttnProcessor","repo":"mkshing/DiffFit-pytorch","repo_kind":"listed","path":"difffit_pytorch/diffusers_models/attention_processor.py","file_url":"https://github.com/mkshing/DiffFit-pytorch/blob/HEAD/difffit_pytorch/diffusers_models/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"921edfd779ddeac7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}