Papers › QLoRA: Efficient Finetuning of Quantized LLMs

QLoRA: Efficient Finetuning of Quantized LLMs

23 May 2023NeurIPS 2023 11arXiv:2305.14314archive 2025-07-28

Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer

We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance. QLoRA backpropagates gradients through a frozen, 4-bit quantized pretrained language model into Low Rank Adapters (LoRA). Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99.3% of the performance level of ChatGPT while only requiring 24 hours of finetuning on a single GPU. QLoRA introduces a number of innovations to save memory without sacrificing performance: (a) 4-bit NormalFloat (NF4), a new data type that is information theoretically optimal for normally distributed weights (b) double quantization to reduce the average memory footprint by quantizing the quantization constants, and (c) paged optimziers to manage memory spikes. We use QLoRA to finetune more than 1,000 models, providing a detailed analysis of instruction following and chatbot performance across 8 instruction datasets, multiple model types (LLaMA, T5), and model scales that would be infeasible to run with regular finetuning (e.g. 33B and 65B parameter models). Our results show that QLoRA finetuning on a small high-quality dataset leads to state-of-the-art results, even when using smaller models than the previous SoTA. We provide a detailed analysis of chatbot performance based on both human and GPT-4 evaluations showing that GPT-4 evaluations are a cheap and reasonable alternative to human evaluation. Furthermore, we find that current chatbot benchmarks are not trustworthy to accurately evaluate the performance levels of chatbots. A lemon-picked analysis demonstrates where Guanaco fails compared to ChatGPT. We release all of our models and code, including CUDA kernels for 4-bit training.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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):

Code

Syntology 26 code samples: 22 from 8 repositories linked to this paper, 4 identical to code harvested from another paper's repository. Across all 26: 18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 10 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: official repository: 3 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 13 samples from 4 repositories, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed); community: 6 samples from 3 repositories, 5 ran (0 with no instrument failure; 5 where Syntology's instrument failed); 4 identical to code first harvested elsewhere. 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 12 of its repositories that Syntology harvested for other papers:

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. 11 of the 18 samples that ran have no recorded date.

20 repositories listed; official and paper-mentioned ones first.

artidoro/qlora officialmentioned in paperpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
timdettmers/bitsandbytes officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale (arXiv:2208.07339; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified), BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (arXiv:2211.05100; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified), Stable and low-precision training for large-scale vision-language models (arXiv:2304.13013; that paper's own run record: 0 ran · 3 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
12kimih/hicupid mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis (arXiv:2506.01262; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
BatsResearch/LexC-Gen mentioned on GitHubSyntology: not harvested report
Luohh5/Chain-of-Exemplar mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
QwenLM/Qwen-7B mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen Technical Report (arXiv:2309.16609; that paper's own run record: 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) · 2 unverified); nothing checks that they implement this paper's method. report
Rain9876/ShareLoRA mentioned on GitHubpytorchSyntology: 9 samples, 4 ran (2 instrument-failed) · 5 unverified report
brandon3964/multimodal-task-vector mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text... (arXiv:2308.12966; that paper's own run record: 0 ran · 2 unverified) and Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning (arXiv:2406.15334; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 5 honoured, 2 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
cornell-zhang/llm-datatypes mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers (arXiv:2210.17323; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
daniel-furman/sft-demos mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
erikaawang/probing-multilingual-dynamics mentioned on GitHubpytorchSyntology: not harvested report
flagai-open/aquila2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685; that paper's own run record: 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); nothing checks that they implement this paper's method. report
huggingface/text-generation-inference mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers (arXiv:2210.17323; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
internlm/xtuner mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685; that paper's own run record: 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); nothing checks that they implement this paper's method. report
ist-daslab/rosa mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation (arXiv:2401.04679; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
jerrywu-code/susgen mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Common 7B Language Models Already Possess Strong Math Capabilities (arXiv:2403.04706; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
openmedlab/pulse mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
pilancilab/caldera mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
qwenlm/qwen mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685; that paper's own run record: 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), Qwen Technical Report (arXiv:2309.16609; that paper's own run record: 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) · 2 unverified) and arXiv:2507.11953 (its page on Syntology; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
qwenlm/qwen-vl mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685; that paper's own run record: 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); nothing checks that they implement this paper's method. 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.

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

26 samples harvested: 18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · violated contract
10ran · our draft was wrong
2ran; the contract check could not run
2ran
8unverified

Licence: 17 of the 26 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 8 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. 4 samples are listed last, in a group without a repository. “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”. “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.

artidoro/qlora official repository 3 samples, 3 ran (1 instrument-failed) · 0 unverified
get_last_checkpoint in 22 papers examples/guanaco_generate.py ran · our draft was wrong fingerprinted MIT (permissive) · 89ce33341af66037 · report fixture: signature checkpoint_dir:str/0/str · returned tuple · level recorded, date not recorded
parse_score in 49 papers eval/eval_gpt_review.py ran · violated contract fingerprinted MIT (permissive) · 8049b382893c73dd · report fixture: signature review:str/0/str · returned list · level recorded, date not recorded
parse_three_class_score eval/eval_gpt_review.py ran · honoured contract fingerprinted MIT (permissive) · 2155c3b1b19d8ab9 · report fixture: signature review:str/0/str · returned int · level recorded, date not recorded
Rain9876/ShareLoRA community (archive-listed) 9 samples, 4 ran (2 instrument-failed) · 5 unverified
dequantize_module_weight sharelora/peft/tuners/lora/layer.py ran · honoured contract no licence file found · pointer only · 21811f6ec0830792 · report fixture: signature module:callable/0/? · returned Parameter · level recorded 2026-09-22
gather_params_ctx sharelora/peft/tuners/lora/layer.py ran; the contract check could not run (DEP_MISSING) no licence file found · pointer only · 1c29706f4a8bd965 · report fixture: signature param:Tensor/2/float, modifier_rank:int/0/int, fwd_module:callable/0/? · returned _GeneratorContextManager · level recorded 2026-09-22
get_bnb_param_type sharelora/peft/tuners/lora/layer.py ran · violated contract fingerprinted no licence file found · pointer only · 1386e6b11e2ef9e0 · report fixture: signature param:Tensor/2/float · returned bool · level recorded 2026-09-22
transpose in 53 papers
census: 6 implementations from 13 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
sharelora/peft/tuners/lora/layer.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 5aaa7db51b41253b · report fixture: signature weight:Tensor/2/float, fan_in_fan_out:bool/0/bool · returned Tensor · level recorded 2026-09-22
BaseTunerLayer sharelora/peft/tuners/lora/layer.py unverified no licence file found · pointer only · c75ab97e2e86199a · report
BufferDict sharelora/peft/tuners/lora/layer.py unverified no licence file found · pointer only · d628ec92a2bbbdd3 · report
DoraLinearLayer sharelora/peft/tuners/lora/layer.py unverified no licence file found · pointer only · 9eb99d2625ca1e2f · report
LoraLayer in 5 papers sharelora/peft/tuners/lora/layer.py unverified no licence file found · pointer only · d2729dc566040484 · report
dequantize_bnb_weight sharelora/peft/tuners/lora/layer.py unverified no licence file found · pointer only · 221e70695f549713 · report
daniel-furman/sft-demos community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
formatting_prompts_func in 14 papers _peft/falcon/peft_falcon_180b_instruct.py ran Apache-2.0 (permissive) · ba51656a6aaea3b7 · report fixture: signature dataset:dict/0/? · returned list · level recorded 2026-09-24
openmedlab/pulse community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
parse_text in 15 papers web_demo_gradio.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 826ceb601fb31250 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
pilancilab/caldera community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
LowMemoryQuantizer src/caldera/utils/quantization.py ran no licence file found · pointer only · cec1d4e0b363b8b0 · report fixture: returned LowMemoryQuantizer · level recorded 2026-09-22
AbstractQuantizer src/caldera/utils/quantization.py unverified no licence file found · pointer only · a4ade271d27a6b35 · report
georgesung/llm_qlora community 3 samples, 2 ran (2 instrument-failed) · 1 unverified
read_yaml_file in 7 papers inference.py ran · our draft was wrong MIT (permissive) · 38a41485b6f05e08 · report fixture: signature file_path:str/0/str · returned dict · level recorded, date not recorded
get_prompt in 99 papers inference.py ran · our draft was wrong fingerprinted MIT (permissive) · 8bdd290bac0f9c85 · report fixture: signature human_prompt:str/0/str · returned str · level recorded, date not recorded
get_llm_response in 8 papers inference.py unverified MIT (permissive) · 0798e321dcc227ed · report
KohakuBlueleaf/guanaco-lora community 1 sample, 1 ran (1 instrument-failed) · 0 unverified
generate_prompt in 110 papers finetune.py ran · our draft was wrong Apache-2.0 (permissive) · a87961e99cab3b49 · report fixture: signature data_point:dict/0/? · returned str · level recorded, date not recorded
shuxueslpi/chatGLM-6B-QLoRA community 2 samples, 2 ran (2 instrument-failed) · 0 unverified
quantize in 70 papers
census: 8 implementations from 11 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
merge_lora_and_quantize.py ran · our draft was wrong no licence file found · pointer only · 9b9c46fa571c5690 · report fixture: signature model:callable/0/?, qbits:int/0/int · returned MockQuantizableModel · level recorded, date not recorded
tokenize_func train_qlora.py ran · our draft was wrong no licence file found · pointer only · f63e332bb59704df · report fixture: signature example:dict/0/?, tokenizer:MockTokenizer/0/?, global_args:MockGlobalArgs/0/?, ignore_label_id:int/0/int · returned dict · level recorded, date not recorded
Repository not located 4 samples, 3 ran (3 instrument-failed) · 1 unverified
4 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
extract_alpaca_dataset in 10 papers repository not located ran · our draft was wrong licence of this copy not recorded · b5445674ab17410f · report fixture: signature example:dict/0/? · returned dict · level recorded, date not recorded
extract_unnatural_instructions_data in 8 papers repository not located ran · our draft was wrong licence of this copy not recorded · f82430123a91cf21 · report fixture: signature examples:dict/0/?, extract_reformulations:bool/0/bool · returned dict · level recorded, date not recorded
generate_prompt in 110 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · b9c4c8084f5cc40a · report fixture: signature n_garbage:int/0/int · returned tuple · level recorded, date not recorded
local_dataset in 5 papers repository not located unverified licence of this copy not recorded · ec8bb649218d4f43 · report

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.

2 assemblies on this paper: 2 harvested, 0 generated.

harvested Assembly for 4-bit NormalFloat (NF4) (graph method: 4-bit NormalFloat (NF4)). 2 bricks; 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. LowMemoryQuantizer entry · level 1 · ran · cec1d4e0b363b8b0
  2. AbstractQuantizer helper · level 0 · unverified · a4ade271d27a6b35

harvested Assembly for QLORA (graph method: QLORA). 9 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. LoraLayer entry · level 0 · unverified · d2729dc566040484
  2. BaseTunerLayer helper · level 0 · unverified · c75ab97e2e86199a
  3. DoraLinearLayer helper · level 0 · unverified · 9eb99d2625ca1e2f
  4. dequantize_module_weight helper · level 1 · ran · honoured contract · 21811f6ec0830792
  5. gather_params_ctx helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 1c29706f4a8bd965
  6. get_bnb_param_type helper · level 1 · ran · violated contract · 1386e6b11e2ef9e0
  7. transpose helper · level 1 · ran; the contract check could not run (RAISES) · 5aaa7db51b41253b
  8. BufferDict helper · level 0 · unverified · d628ec92a2bbbdd3
  9. dequantize_bnb_weight helper · level 0 · unverified · 221e70695f549713

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="2305.14314") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ChatbotInstruction FollowingLanguage ModellingQuantizationparameter-efficient fine-tuning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
parameter-efficient fine-tuning BoolQ LLaMA2-7b Accuracy (% ) 82.63 #1 of 4 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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