SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.05445 · 2024

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2402.05445.json · badge: /api/ran/2402.05445.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
htqin/ir-qlora canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
extract_unnatural_instructions_data Ran
ran; our contract draft was wrong, not the code
htqin/ir-qlora/irlora.py
pointer only (licence: NONE) · get_code("f82430123a91cf21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, htqin/ir-qlora 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.

prod Ran
ran, violated the contract we drafted
htqin/ir-qlora/utils.py
pointer only (licence: NONE) · get_code("6d5acfb0087d1ee7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, htqin/ir-qlora 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.

quantize_tensor Ran
ran; our contract draft was wrong, not the code
htqin/ir-qlora/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from macaronlin/llama3-quantization, is pointer only (licence: NONE) · get_code("632792cb21b226ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, htqin/ir-qlora 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 3 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
extract_unnatural_instructions_data 7 other papers
6 dated earlier, 1 later
2305.14314 (2023-05)
QLORA: Efficient Finetuning of Quantized LLMs
2305.16300 (2023-05)
Random-Access Infinite Context Length for Transformers
2307.09288 (2023-07)
Llama 2: Open Foundation and Fine-Tuned Chat Models
and 4 more not named here
prod 7 other papers
4 dated earlier, 1 the same month, 2 later
1904.08489 (2019-04)
Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers
1906.06818 (2019-06)
Stacked Capsule Autoencoders
2106.02081 (2021-06)
Solving Schrödinger Bridges via Maximum Likelihood
and 4 more not named here
quantize_tensor 1 other paper
1 later
2404.14047 (2024-04)
An empirical study of LLaMA3 quantization: from LLMs to MLLMs

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 2026-11-22.

Repositories linked to this paper

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

Abstract

The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate yet compact LLMs for deployment on resource-constrained hardware. However, existing methods cause the quantized LLM to severely degrade and even fail to benefit from the finetuning of LoRA. This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention. The proposed IR-QLoRA mainly relies on two technologies derived from the perspective of unified information: (1) statistics-based Information Calibration Quantization allows the quantized parameters of LLM to retain original information accurately; (2) finetuning-based Information Elastic Connection makes LoRA utilizes elastic representation transformation with diverse information. Comprehensive experiments show that IR-QLoRA can significantly improve accuracy across LLaMA and LLaMA2 families under 2-4 bit-widths, e.g., 4- bit LLaMA-7B achieves 1.4% improvement on MMLU compared with the state-of-the-art methods. The significant performance gain requires only a tiny 0.31% additional time consumption, revealing the satisfactory efficiency of our IR-QLoRA. We highlight that IR-QLoRA enjoys excellent versatility, compatible with various frameworks (e.g., NormalFloat and Integer quantization) and brings general accuracy gains. The code is available at https://github.com/htqin/ir-qlora.

For agents

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

get_harvested_code_for_paper("2402.05445")
get_code_for_paper("2402.05445")
have("2402.05445")

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

curl https://syntology.ai/api/ran/2402.05445.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.05445.svg)](https://syntology.ai/paper/2402.05445)

Connect an agent — have() is free.