Papers › VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

24 May 2024arXiv:2405.15179archive 2025-07-28

Yang Li, Shaobo Han, Shihao Ji

As the adoption of large language models increases and the need for per-user or per-task model customization grows, the parameter-efficient fine-tuning (PEFT) methods, such as low-rank adaptation (LoRA) and its variants, incur substantial storage and transmission costs. To further reduce stored parameters, we introduce a "divide-and-share" paradigm that breaks the barriers of low-rank decomposition across matrix dimensions, modules, and layers by sharing parameters globally via a vector bank. As an instantiation of the paradigm to LoRA, our proposed VB-LoRA composites all the low-rank matrices of LoRA from a shared vector bank with a differentiable top-k admixture module. VB-LoRA achieves extreme parameter efficiency while maintaining comparable or better performance compared to state-of-the-art PEFT methods. Extensive experiments demonstrate the effectiveness of VB-LoRA on natural language understanding, natural language generation, instruction tuning, and mathematical reasoning tasks. When fine-tuning the Llama2-13B model, VB-LoRA only uses 0.4% of LoRA's stored parameters, yet achieves superior results. Our source code is available at https://github.com/leo-yangli/VB-LoRA. This method has been merged into the Hugging Face PEFT package.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.15179")

Code

Syntology Ran 16 of 17 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · violated contract; 6 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 16 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

leo-yangli/vb-lora officialmentioned in papermentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 16 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
6ran · our draft was wrong
9ran
1unverified

Licence: 17 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from leo-yangli/VB-LoRA. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

is_number leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/gsm8k_eval.py official repository ran · violated contract no licence file found · pointer only · 0fe9cf6c00ef56ea · report
VBLoRA leo-yangli/vb-lora/NLU/vblora/vblora.py official repository ran fingerprinted no licence file found · pointer only · e6de664c4943a7e0 · report
batch_data leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/MATH_eval.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 66b3b5450182da3a · report
extract_unnatural_instructions_data leo-yangli/VB-LoRA/instruction_tuning/qlora.py official repository ran · our draft was wrong no licence file found · pointer only · f82430123a91cf21 · report
find_all_linear_names leo-yangli/VB-LoRA/math_instruction_tuning/utils/merge_adapter_to_base_model.py official repository ran · our draft was wrong no licence file found · pointer only · 649fc48067a48529 · report
gelu_fast leo-yangli/VB-LoRA/NLU/NLU/src/transformers/activations.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · a4475703ff58ecf9 · report
gelu_new leo-yangli/VB-LoRA/NLU/NLU/src/transformers/activations.py official repository ran fingerprinted no licence file found · pointer only · 45bb87451230d5e8 · report
is_digit leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/grader.py official repository ran no licence file found · pointer only · 8ae8c583b21633b3 · report
last_boxed_only leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/utils.py official repository ran no licence file found · pointer only · e9a9686489ca49a9 · report
last_boxed_only_string leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/utils.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 90b5c896e5eaea5e · report
math_equal leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/grader.py official repository ran no licence file found · pointer only · 65c738adb08e913c · report
math_equal_process leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/grader.py official repository ran fingerprinted no licence file found · pointer only · f63c83de2a26f67c · report
mish leo-yangli/VB-LoRA/NLU/NLU/src/transformers/activations.py official repository ran fingerprinted no licence file found · pointer only · f889d53c68539013 · report
preprocess leo-yangli/VB-LoRA/math_instruction_tuning/intruction_tuning_vblora.py official repository ran no licence file found · pointer only · ec6403ff3372ffa2 · report
remove_boxed leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/MATH_eval.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · f3bbe264b05aadd3 · report
train_tokenize_function leo-yangli/VB-LoRA/math_instruction_tuning/intruction_tuning_vblora.py official repository ran no licence file found · pointer only · 86efa2d5fbd39bf6 · report
only_until_first_boxed_from_tokens leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/utils.py official repository unverified no licence file found · pointer only · 0bbf876ced018c83 · report

Tasks

Mathematical ReasoningNatural Language UnderstandingText Generationparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections