SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02446 · 2024

LQER: Low-Rank Quantization Error Reconstruction for LLMs

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 4 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.02446.json · badge: /api/ran/2402.02446.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
chengzhang-98/lqer canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
collect_linear_weights Ran
ran; our contract draft was wrong, not the code
chengzhang-98/lqer/src/lqer/approximate/utils.py
pointer only (licence: NONE) · get_code("9eebde5b4aa47a22")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_none_to_str_na Ran
ran; our contract draft was wrong, not the code
chengzhang-98/lqer/src/lqer/utils.py
pointer only (licence: NONE) · get_code("4c37b3a06f65ec01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_str_na_to_none Ran
ran; our contract draft was wrong, not the code
chengzhang-98/lqer/src/lqer/utils.py
pointer only (licence: NONE) · get_code("a94b082c74445f99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_perplexity Ran
ran; our contract draft was wrong, not the code
chengzhang-98/lqer/src/lqer/evaluate/evaluate_lm.py
pointer only (licence: NONE) · get_code("5f612508fe3af2e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_logger Ran
ran; our contract draft was wrong, not the code
chengzhang-98/lqer/src/lqer/logging.py
pointer only (licence: NONE) · get_code("6221863a7f7985b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_config Ran
ran; our contract draft was wrong, not the code
chengzhang-98/lqer/src/lqer/utils.py
pointer only (licence: NONE) · get_code("0056989332540d95")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

preprocess_data_module_slim_pajama_6b Not yet run
unverified (harvested, no recorded run)
chengzhang-98/lqer/src/lqer/datasets/slim_pajama.py
pointer only (licence: NONE) · get_code("1275677ab4aec925")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

preprocess_data_module_wikitext2 Not yet run
unverified (harvested, no recorded run)
chengzhang-98/lqer/src/lqer/datasets/wikitext2.py
pointer only (licence: NONE) · get_code("8d9b95e38531702b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

run_evaluate_perplexity Not yet run
unverified (harvested, no recorded run)
chengzhang-98/lqer/src/lqer/runners.py
pointer only (licence: NONE) · get_code("97edeccc3fdc2cf3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

run_profiler Not yet run
unverified (harvested, no recorded run)
chengzhang-98/lqer/src/lqer/runners.py
pointer only (licence: NONE) · get_code("4ac18e3bb2866bde")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengzhang-98/lqer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Post-training quantization of Large Language Models (LLMs) is challenging. In this work, we introduce Low-rank Quantization Error Reduction (LQER), which combines quantization and low-rank approximation to recover the model capability. LQER leverages an activation-induced scale matrix to drive the singular value distribution of quantization error towards a desirable distribution, which enables nearly-lossless W4A8 quantization on various LLMs and downstream tasks without the need for knowledge distillation, grid search, or gradient-base iterative optimization. Unlike existing methods, the computation pattern of LQER eliminates the need for specialized Scatter and Gather processes to collect high-precision weights from irregular memory locations. Our W4A8 LLMs achieve near-lossless performance on six popular downstream tasks, while using 1.36$\times$ fewer hardware resources than the leading state-of-the-art method. We open-source our framework at https://github.com/ChengZhang-98/lqer

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.02446")
get_code_for_paper("2402.02446")
have("2402.02446")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.02446.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.02446.svg)](https://syntology.ai/paper/2402.02446)

Connect an agent — have() is free.