SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02834 · ICLR · 2024

Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods

Bo-Kyeong Kim, Shinkook Choi, Geonmin Kim, Tae-Ho Kim, Thibault Castells, Junho Shin, Hyoung-Kyu Song

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 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/2402.02834.json · badge: /api/ran/2402.02834.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
nota-netspresso/shortened-llm canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
b2mb Ran
ran, honoured the contract we drafted
nota-netspresso/shortened-llm/src/gen_batch_eval_vram.py
pointer only (licence: NONE) · get_code("32380a050ca033d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nota-netspresso/shortened-llm 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.

llama_eval Ran
ran; our contract draft was wrong, not the code
nota-netspresso/shortened-llm/src/eval_ppl.py
pointer only (licence: NONE); the stored copy get_code serves, from Nota-NetsPresso/shortened-llm, is pointer only (licence: NONE) · get_code("9012ddbbaf4ee64f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nota-netspresso/shortened-llm 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.

process_data Ran
ran, honoured the contract we drafted
nota-netspresso/shortened-llm/src/dataset.py
pointer only (licence: NONE); the stored copy get_code serves, from Nota-NetsPresso/shortened-llm, is pointer only (licence: NONE) · get_code("8a69aa6e08dc65a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nota-netspresso/shortened-llm 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_examples Not yet run
unverified (harvested, no recorded run)
nota-netspresso/shortened-llm/src/dataset.py
pointer only (licence: NONE) · get_code("dda7f6122e4d1904")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nota-netspresso/shortened-llm 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.

get_gpu_metrics Not yet run
unverified (harvested, no recorded run)
nota-netspresso/shortened-llm/src/gen_batch_eval_time_gpuutil.py
pointer only (licence: NONE); the stored copy get_code serves, from Nota-NetsPresso/shortened-llm, is pointer only (licence: NONE) · get_code("f8178f1b0c33cf48")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nota-netspresso/shortened-llm 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.

get_loaders Not yet run
unverified (harvested, no recorded run)
nota-netspresso/shortened-llm/src/dataset.py
pointer only (licence: NONE) · get_code("4ef386ce30344069")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nota-netspresso/shortened-llm 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, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 2 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
b2mb 11 other papers
2 dated earlier, 9 later
2303.18223 (2023-03)
A Survey of Large Language Models
2401.16405 (2024-01)
Scaling Sparse Fine-Tuning to Large Language Models
2403.08370 (2024-03)
SMART: Submodular Data Mixture Strategy for Instruction Tuning
and 8 more not named here
get_gpu_metrics 1 other paper
1 later
2605.15491 (2026-05)
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
llama_eval 1 other paper
1 later
2605.15491 (2026-05)
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
process_data 1 other paper
1 later
2605.15491 (2026-05)
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

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

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining the number of layers. Depth pruning, in contrast, removes entire layers or blocks, while keeping the size of the remaining weights unchanged. Most current research focuses on either width-only or a blend of width and depth pruning, with little comparative analysis between the two units (width vs. depth) concerning their impact on LLM inference efficiency. In this work, we show that simple depth pruning can effectively compress LLMs while achieving comparable or superior performance to recent width pruning studies. Our pruning method boosts inference speeds, especially under memory-constrained conditions that require limited batch sizes for running LLMs, where width pruning is ineffective. In retraining pruned models for quality recovery, continued pretraining on a large corpus markedly outperforms LoRA-based tuning, particularly at severe pruning ratios. We hope this work can help build compact yet capable LLMs.

For agents

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

get_harvested_code_for_paper("2402.02834")
get_code_for_paper("2402.02834")
have("2402.02834")

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

curl https://syntology.ai/api/ran/2402.02834.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.02834.svg)](https://syntology.ai/paper/2402.02834)

Connect an agent — have() is free.