Papers › LoRA: Low-Rank Adaptation of Large Language Models
LoRA: Low-Rank Adaptation of Large Language Models
Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen
An important paradigm of natural language processing consists of large-scale pre-training on general domain data and adaptation to particular tasks or domains. As we pre-train larger models, full fine-tuning, which retrains all model parameters, becomes less feasible. Using GPT-3 175B as an example -- deploying independent instances of fine-tuned models, each with 175B parameters, is prohibitively expensive. We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks. Compared to GPT-3 175B fine-tuned with Adam, LoRA can reduce the number of trainable parameters by 10,000 times and the GPU memory requirement by 3 times. LoRA performs on-par or better than fine-tuning in model quality on RoBERTa, DeBERTa, GPT-2, and GPT-3, despite having fewer trainable parameters, a higher training throughput, and, unlike adapters, no additional inference latency. We also provide an empirical investigation into rank-deficiency in language model adaptation, which sheds light on the efficacy of LoRA. We release a package that facilitates the integration of LoRA with PyTorch models and provide our implementations and model checkpoints for RoBERTa, DeBERTa, and GPT-2 at https://github.com/microsoft/LoRA.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2106.09685")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2106.09685", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2106.09685")
Code
No sample from the archive's official repository (microsoft/LoRA) is linked to this paper; the 84 samples below come from 24 community repositories. Syntology harvested code from microsoft/LoRA for another paper.
microsoft/LoRA: Syntology's graph links these samples to Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning (arXiv:2202.00535; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.
Syntology 84 code samples harvested from 24 repositories linked to this paper: 51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 where Syntology's instrument failed) · 33 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 84 samples from 24 repositories, 51 ran (43 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 36 of its repositories that Syntology harvested for other papers:
- microsoft/LoRA, official repository: harvested for another paper, listed under the repository
- 12kimih/hicupid, community (archive-listed): harvested for another paper, listed under the repository
- Davidzhangyuanhan/NOAH, community (archive-listed): harvested for another paper, listed under the repository
- Owen-Oertell/rlcm, community (archive-listed): harvested for another paper, listed under the repository
- QwenLM/Qwen-7B, community (archive-listed): harvested for another paper, listed under the repository
- ZhangYuanhan-AI/NOAH, community (archive-listed): harvested for another paper, listed under the repository
- aleemsidra/convlora, community (archive-listed): harvested for another paper, listed under the repository
- arielnlee/Platypus, community (archive-listed): harvested for another paper, listed under the repository
- brandon3964/multimodal-task-vector, community (archive-listed): harvested for 2 other papers, listed under the repository
- clementromac/lamorel, community (archive-listed): harvested for another paper, listed under the repository
- debjitpaul/refiner, community (archive-listed): harvested for another paper, listed under the repository
- facebookresearch/pytorch-dp, community (archive-listed): harvested for another paper, listed under the repository
- facico/chinese-vicuna, community (archive-listed): harvested for another paper, listed under the repository
- flowersteam/lamorel, community (archive-listed): harvested for another paper, listed under the repository
- google-deepmind/thunnini, community (archive-listed): harvested for another paper, listed under the repository
- gt-ripl/selective-projection-decay, community (archive-listed): harvested for another paper, listed under the repository
- heekhero/DTL, community (archive-listed): harvested for another paper, listed under the repository
- hiyouga/llama-efficient-tuning, community (archive-listed): harvested for another paper, listed under the repository
- lif31up/extended-BERT-for-low-rank-adaption, community (archive-listed): harvested for another paper, listed under the repository
- liucongg/chatglm-finetuning, community (archive-listed): harvested for another paper, listed under the repository
- mistralai/mistral-src, community (archive-listed): harvested for another paper, listed under the repository
- oseyosey/ccds, community (archive-listed): harvested for another paper, listed under the repository
- pilancilab/Riemannian_Preconditioned_LoRA, community (archive-listed): harvested for another paper, listed under the repository
- pilancilab/caldera, community (archive-listed): harvested for another paper, listed under the repository
- pytorch/opacus, community (archive-listed): harvested for another paper, listed under the repository
- tatsu-lab/stanford_alpaca, community (archive-listed): harvested for 2 other papers, listed under the repository
- teelinsan/camoscio, community (archive-listed): harvested for another paper, listed under the repository
- thuml/AutoTimes, community (archive-listed): harvested for another paper, listed under the repository
- tloen/alpaca-lora, community (archive-listed): harvested for another paper, listed under the repository
- videocrafter/videocrafter, community (archive-listed): harvested for another paper, listed under the repository
- yjiangcm/lion, community (archive-listed): harvested for another paper, listed under the repository
- yjiangcm/lte, community (archive-listed): harvested for another paper, listed under the repository
- ykwon0407/datainf, community (archive-listed): harvested for another paper, listed under the repository
- zhaolingao/langptune, community (archive-listed): harvested for another paper, listed under the repository
- zjunlp/trice, community (archive-listed): harvested for another paper, listed under the repository
- jackaduma/Alpaca-LoRA-RLHF-PyTorch, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
74 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
84 samples harvested: 51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 where Syntology's instrument failed) · 33 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 30 of the 84 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 24 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 7 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
d4f1b87ebb0746ff · report
fixture: returned LoraInjectedLinear · level recorded 2026-09-22 03b78b050e202a11 · report
fixture: returned LoRALayer · level recorded 2026-09-22 f0826162829e047c · report
fixture: signature module:callable/0/?, parent_name:str/0/str · returned list · level recorded 2026-09-24 adb7541f2edf078e · report
fixture: signature raw_dataset:dict/0/?, split:str/0/str · returned list · level recorded 2026-09-24 8bf57961090630be · report
fixture: signature module:callable/0/?, parent_name:str/0/str · returned list · level recorded 2026-09-24 db888a8265d40f72 · report
ac56d3e7b79dbc18 · report
8c51f5aaf2f659e2 · report
a2a949d390f89698 · report
078030b5193a097e · report
fixture: signature cfg:MockConfig/0/? · returned dict · level recorded 2026-09-24 1db3631aa8a1aa75 · report
fixture: signature cfg:Config/0/?, prompt:str/0/str · returned Config · level recorded 2026-09-24 3a4aed8b19f818f9 · report
fixture: signature t_dy:ndarray/1/float, t_dw:ndarray/1/float, Tq:float/0/float · returned tuple · level recorded 2026-09-24 a6d5b89d9b7d3d00 · report
fixture: signature image_size_arg:int/0/int · returned tuple · level recorded 2026-09-22 e9b9102ba2736955 · report
fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24 b0ef8d0623af5966 · report
fixture: signature path:str/0/str, x_tag:str/0/str, y_tag:str/0/str · returned tuple · level recorded 2026-09-24 5f63441b43fd9611 · report
fixture: signature t_dy:ndarray/1/int, t_dw:ndarray/1/int, I:ndarray/1/float, rho:float/0/float · returned tuple · level recorded 2026-09-24 cfdc29157de085e3 · report
fixture: signature model:callable/0/?, quantization:NoneType/0/? · returned list · level recorded 2026-09-22 a145b7042b65ac5e · report
fixture: signature force_auto_device_map:bool/0/bool, max_memory_MB:int/0/int, use_better_transformer:bool/0/bool · returned tuple · level recorded 2026-09-22 96cb172b7d428b13 · report
fixture: signature model:callable/0/? · returned tuple · level recorded 2026-09-22 60b08148856c99db · report
336b88501d97f8d6 · report
fixture: signature tokenizer:MockTokenizer/0/?, sentence:str/0/str · returned list · level recorded 2026-09-24 47660e151147cb9e · report
fixture: signature force_auto_device_map:bool/0/bool, max_memory_MB:int/0/int, use_better_transformer:bool/0/bool · returned tuple · level recorded 2026-09-24 db50388eace49466 · report
fixture: signature accelerator:Accelerator/0/? · returned str · level recorded 2026-09-24 14548ec0148ab8ec · report
fixture: signature model:callable/0/? · returned tuple · level recorded 2026-09-24 6704486d6cc51ef0 · report
fixture: signature model:callable/0/?, input_ids:Tensor/2/int, decoder_args:dict/0/?, is_encoder_decoder:bool/0/bool · returned tuple · level recorded 2026-09-24 02c2c36a57cb4648 · report
fixture: signature tag_regex:Pattern/0/?, sentence:str/0/str, recursion_limit:int/0/int · returned list · level recorded 2026-09-24 d7678113426bdefa · report
fixture: signature tags:list/1/str · returned list · level recorded 2026-09-24 60b66de5aeee97ce · report
fixture: signature tags:list/1/str · returned list · level recorded 2026-09-24 2ec748940a02967a · report
fixture: signature tags:list/1/str · returned list · level recorded 2026-09-24 7b6da4bad1690c28 · report
f3fdd2b33f8ca63e · report
53281c424cf5891f · report
fixture: signature model:callable/0/? · returned list · level recorded 2026-09-22 6351105db75b9e71 · report
fixture: signature text:str/0/str, tokenizer:callable/0/?, model:callable/0/? · returned Tensor · level recorded 2026-09-24 d8d584f9d3ef1a8f · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24 0fa772920c405ed2 · report
fixture: returned LoRALinear · level recorded 2026-09-22 d91b99d50ee2e13b · report
fixture: returned LoRALinear · level recorded 2026-09-22 census: 7 implementations from 7 papers, 6 distinct outputs on one shared input peft/src/peft/tuners/lora.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) ·
f156ba83a62bfd88 · report
fixture: returned Conv2d · level recorded 2026-09-22 1d022836585085cb · report
fixture: returned Embedding · level recorded 2026-09-22 1f506a3641c40fac · report
fixture: returned Linear · level recorded 2026-09-22 5e92a950d55ba432 · report
fixture: returned ModulesToSaveWrapper · level recorded 2026-09-22 4e130d790f7e7dcd · report
4e64816ecd5d8675 · report
84f4e84719d66f4c · report
b6d5f1638edabb8a · report
fixture: returned LoraWeight · level recorded 2026-09-22 33efd3e3245a8802 · report
fixture: returned LoraArguments · level recorded 2026-09-22 e9170e0ed6d12210 · report
fixture: returned LoraArguments · level recorded 2026-09-22 1bad2db22f04ac99 · report
840d5d0a1e7b3a5e · report
848321f611fd218e · report
fixture: signature model:callable/0/? · returned list · level recorded 2026-09-22 60df31a5803dfdaa · report
fixture: signature model:callable/0/?, args:ArgsConfig/0/? · returned LoraConfig · level recorded 2026-09-22 7a1b3f8b8ad8779a · report
551a5af99158f91b · report
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input peftnew/tuners/lora.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only ·
4025b3aa55f8b3e1 · report
fixture: returned Conv2d · level recorded 2026-09-22 747685b3f553947b · report
fixture: returned Embedding · level recorded 2026-09-22 81d374052d6022b2 · report
fixture: returned Linear · level recorded 2026-09-22 e5f9e40bdb24afdb · report
fixture: returned LoraLayer · level recorded 2026-09-22 7bb2b9cb3064a59c · report
fixture: returned ModulesToSaveWrapper · level recorded 2026-09-22 b368ffa3c3d69f27 · report
fixture: returned PeftConfig · level recorded 2026-09-22 867983846f2ffb06 · report
fixture: returned PeftConfigMixin · level recorded 2026-09-22 1464d2a7f4cf160e · report
fixture: returned QuantLinear · level recorded 2026-09-22 4236f53faf916aa2 · report
fixture: signature model:callable/0/?, method:str/0/str · returned QuantizationConfig · level recorded 2026-09-22 9027fb9844632cf2 · report
fixture: returned bool · level recorded 2026-09-22 7d44a88878819ef3 · report
fixture: returned bool · level recorded 2026-09-22 f877238ebdc262f1 · report
0cf569603c64a959 · report
20fd5846de4854e1 · report
e9fa57bcc18e8142 · report
ad8420238d39e438 · report
258dc95ececd559e · report
cd0246549fc50335 · report
57b8771890dd7b1b · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket labml_nn/lora/gpt2.py ran MIT (permissive) ·
7a1353c5e5ac87b5 · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24 Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
21 assemblies on this paper: 21 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
21 sibling assemblies for Low-Rank Adaptation (LoRA) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 21 sibling assemblies; the other 9 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 22 bricks; individually on a fixture: 14 ran (of which 8 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.
one of 21 siblings
- LoraModel entry · level 0 · unverified ·
e9fa57bcc18e8142 - BaseTuner helper · level 0 · unverified ·
f877238ebdc262f1 - Conv2d model · level 1 · ran ·
4025b3aa55f8b3e1 - Embedding model · level 1 · ran ·
747685b3f553947b - Linear model · level 1 · ran ·
81d374052d6022b2 - LoraConfig helper · level 0 · unverified ·
20fd5846de4854e1 - LoraLayer helper · level 1 · ran ·
e5f9e40bdb24afdb - ModulesToSaveWrapper helper · level 1 · ran ·
7bb2b9cb3064a59c - QuantLinear model · level 1 · ran ·
1464d2a7f4cf160e - _freeze_adapter helper · level 0 · unverified ·
599fe61280ffc433 - _get_submodules helper · level 1 · ran · our draft was wrong ·
127b2b488cacb9c4 - get_auto_gptq_quant_linear helper · level 0 · unverified ·
cd0246549fc50335 - get_quantization_config helper · level 1 · ran · our draft was wrong ·
4236f53faf916aa2 - is_bnb_4bit_available helper · level 1 · ran ·
7d44a88878819ef3 - BaseTunerLayer helper · level 0 · unverified ·
0cf569603c64a959 - PeftConfig helper · level 1 · ran ·
b368ffa3c3d69f27 - transpose helper · level 1 · ran; the contract check could not run ·
8f1a49e9d8b29d83 - PeftType helper · level 0 · unverified ·
ad8420238d39e438 - is_auto_gptq_available helper · level 1 · ran ·
9027fb9844632cf2 - is_bnb_available helper · level 1 · ran ·
d82bb63b6ee3c783 - PeftConfigMixin helper · level 1 · ran ·
867983846f2ffb06 - TaskType helper · level 0 · unverified ·
258dc95ececd559e
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 21 siblings
- LoRALinear entry · level 1 · ran ·
d91b99d50ee2e13b
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 21 siblings
- LoraLinear entry · level 0 · unverified ·
399aed0da4b85280
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 21 siblings
- PeftModelForCausalLM entry · level 0 · unverified ·
551a5af99158f91b
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 12 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 21 siblings
- LoraModel entry · level 0 · unverified ·
4e64816ecd5d8675 - Conv2d model · level 1 · ran ·
f156ba83a62bfd88 - Embedding model · level 1 · ran ·
1d022836585085cb - Linear model · level 1 · ran ·
1f506a3641c40fac - LoraLayer model · level 0 · unverified ·
4e130d790f7e7dcd - ModulesToSaveWrapper helper · level 1 · ran ·
5e92a950d55ba432 - _freeze_adapter helper · level 0 · unverified ·
599fe61280ffc433 - _get_submodules helper · level 1 · ran · our draft was wrong ·
127b2b488cacb9c4 - is_bnb_4bit_available helper · level 1 · ran ·
7d44a88878819ef3 - is_bnb_available helper · level 1 · ran ·
d82bb63b6ee3c783 - mark_only_lora_as_trainable update_rule · level 0 · unverified ·
84f4e84719d66f4c - transpose helper · level 1 · ran; the contract check could not run ·
8f1a49e9d8b29d83
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 21 siblings
- LoRALinear entry · level 1 · ran ·
0fa772920c405ed2
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 21 siblings
- LoRALayer entry · level 1 · ran ·
03b78b050e202a11
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 21 siblings
- LoraArguments entry · level 1 · ran ·
e9170e0ed6d12210
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 21 siblings
- LoraInjectedLinear entry · level 1 · ran ·
d4f1b87ebb0746ff
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 21 siblings
- LoraArguments entry · level 1 · ran ·
33efd3e3245a8802
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 21 siblings
- LoraWeight entry · level 1 · ran ·
b6d5f1638edabb8a
harvested Assembly for Low-Rank Adaptation (LoRA) (graph method: Low-Rank Adaptation (LoRA)). 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 21 siblings
- MultiHeadAttention entry · level 1 · ran ·
7a1353c5e5ac87b5 - Linear helper · level 1 · ran ·
57b8771890dd7b1b
- get_peft_lora_model · c323465a4b5ed133 · 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
- MultiHeadAttention · cdaa08d3bec71273 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
- LinearSuper · d2138626056fee4e · 3 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
- merge_lora_model · d7c85625a6478ea6 · 5 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
- make_diff · da084a3172acebca · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
- find_all_linear_names · eab2a0cf03cbf5e1 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
- LoRALayer · edcb8fde700fddd9 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
- LoraArguments · f33a8cf30e84ace6 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
- LoRA_ViT_timm · fe4a200469f3f3ae · 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.09685") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Mathematical Reasoning | AMC23 | Math-Master | Acc | 82 | #2 of 3 | Archive leaderboard | report |
| parameter-efficient fine-tuning | BoolQ | LLaMA2-7b | Accuracy (% ) | 80.28 | #4 of 4 | Archive leaderboard | report |
| parameter-efficient fine-tuning | HellaSwag | LLaMA2-7b | Accuracy (% ) | 76.67 | #2 of 3 | Archive leaderboard | report |
| parameter-efficient fine-tuning | WinoGrande | LLaMA2-7b | Accuracy (% ) | 69.85 | #3 of 3 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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