SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.03792 · 2024

Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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; 4 failures of our instrument; 2 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/2406.03792.json · badge: /api/ran/2406.03792.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
gccnlp/light-peft canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
bloom_model_postprocess_past_key_value Ran
ran; our contract draft was wrong, not the code
gccnlp/light-peft/peft/src/peft/utils/other.py
pointer only (licence: NONE) · get_code("ecf94b05123201e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gccnlp/light-peft 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.

prepare_model_for_int8_training Ran
ran; our contract draft was wrong, not the code
gccnlp/light-peft/peft/src/peft/utils/other.py
pointer only (licence: NONE) · get_code("f3ce42648e83a4dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gccnlp/light-peft 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.

prune_linear_layer Ran
ran; our contract draft was wrong, not the code
gccnlp/light-peft/peft/src/peft/tuners/lora.py
pointer only (licence: NONE) · get_code("9d6a7aa341c6be64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gccnlp/light-peft 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.

shift_tokens_right Ran
ran; our contract draft was wrong, not the code
gccnlp/light-peft/peft/src/peft/utils/other.py
pointer only (licence: NONE) · get_code("5af2b785cc55d3ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gccnlp/light-peft 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_peft_model_state_dict Not yet run
unverified (harvested, no recorded run)
gccnlp/light-peft/peft/src/peft/utils/save_and_load.py
pointer only (licence: NONE) · get_code("6405b3acf7821b9d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gccnlp/light-peft 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.

set_peft_model_state_dict Not yet run
unverified (harvested, no recorded run)
gccnlp/light-peft/peft/src/peft/utils/save_and_load.py
pointer only (licence: NONE) · get_code("fbb3cd1c8af5bf8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gccnlp/light-peft 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 5 the same month, 2 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
prune_linear_layer 29 other papers
28 dated earlier, 1 same year, order not determinable
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.08230 (2019-06)
Evaluating Protein Transfer Learning with TAPE
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
and 26 more not named here
shift_tokens_right 18 other papers
12 dated earlier, 2 the same month, 4 later · 1 only as an assembly brick
2021.acl-demo.21 (2021 (year only))
KuiLeiXi: a Chinese Open-Ended Text Adventure Game
2203.07836 (2022-03)
Graph Pre-training for AMR Parsing and Generation
2203.11239 (2022-03)
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization
and 15 more not named here
bloom_model_postprocess_past_key_value 5 other papers
1 dated earlier, 1 the same month, 3 later
2405.12130 (2024-05)
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
2406.00132 (2024-06)
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
2409.10673 (2024-09)
A Bayesian Interpretation of Adaptive Low-Rank Adaptation
and 2 more not named here
get_peft_model_state_dict 1 other paper
1 the same month
2406.00132 (2024-06)
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
prepare_model_for_int8_training 1 other paper
1 the same month
2406.00132 (2024-06)
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
set_peft_model_state_dict 1 other paper
1 the same month
2406.00132 (2024-06)
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation

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

Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inadequate training efficiency. Firstly, the utilization of large-scale foundation models during the training process is excessively redundant for certain fine-tuning tasks. Secondly, as the model size increases, the growth in trainable parameters of empirically added PEFT modules becomes non-negligible and redundant, leading to inefficiency. To achieve task-specific efficient fine-tuning, we propose the Light-PEFT framework, which includes two methods: Masked Early Pruning of the Foundation Model and Multi-Granularity Early Pruning of PEFT. The Light-PEFT framework allows for the simultaneous estimation of redundant parameters in both the foundation model and PEFT modules during the early stage of training. These parameters can then be pruned for more efficient fine-tuning. We validate our approach on GLUE, SuperGLUE, QA tasks, and various models. With Light-PEFT, parameters of the foundation model can be pruned by up to over 40%, while still controlling trainable parameters to be only 25% of the original PEFT method. Compared to utilizing the PEFT method directly, Light-PEFT achieves training and inference speedup, reduces memory usage, and maintains comparable performance and the plug-and-play feature of PEFT.

For agents

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

get_harvested_code_for_paper("2406.03792")
get_code_for_paper("2406.03792")
have("2406.03792")

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

curl https://syntology.ai/api/ran/2406.03792.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.03792.svg)](https://syntology.ai/paper/2406.03792)

Connect an agent — have() is free.