Papers › Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models

Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models

5 Jun 2024arXiv:2406.02924archive 2025-07-28

Peijie Dong, Lujun Li, Zhenheng Tang, Xiang Liu, Xinglin Pan, Qiang Wang, Xiaowen Chu

Despite the remarkable capabilities, Large Language Models (LLMs) face deployment challenges due to their extensive size. Pruning methods drop a subset of weights to accelerate, but many of them require retraining, which is prohibitively expensive and computationally demanding. Recently, post-training pruning approaches introduced novel metrics, enabling the pruning of LLMs without retraining. However, these metrics require the involvement of human experts and tedious trial and error. To efficiently identify superior pruning metrics, we develop an automatic framework for searching symbolic pruning metrics using genetic programming. In particular, we devise an elaborate search space encompassing the existing pruning metrics to discover the potential symbolic pruning metric. We propose an opposing operation simplification strategy to increase the diversity of the population. In this way, Pruner-Zero allows auto-generation of symbolic pruning metrics. Based on the searched results, we explore the correlation between pruning metrics and performance after pruning and summarize some principles. Extensive experiments on LLaMA and LLaMA-2 on language modeling and zero-shot tasks demonstrate that our Pruner-Zero obtains superior performance than SOTA post-training pruning methods. Code at: \url{https://github.com/pprp/Pruner-Zero}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2406.02924")

Code

Syntology Ran 8 of 17 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pprp/pruner-zero officialmentioned in papermentioned on GitHubpytorchMIT 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.

Code Syntology ran Syntology

17 samples harvested; 8 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
5ran
9unverified

Licence: 0 of the 17 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 pprp/pruner-zero. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

add pprp/pruner-zero/lib/gptree.py official repository ran fingerprinted MIT (permissive) · 28f088bf9d4cf797 · report
check_sparsity pprp/pruner-zero/lib/prune.py official repository ran MIT (permissive) · ac28c555c0ec0815 · report
find_layers pprp/pruner-zero/lib/prune.py official repository ran · our draft was wrong MIT (permissive) · 2ed16fcdc14ad951 · report
find_layers pprp/pruner-zero/lora_ft/evaluate_ppl.py official repository ran · our draft was wrong MIT (permissive) · a9e7f2cdf016b88b · report
find_layers pprp/pruner-zero/lib/gradient_computation.py official repository ran · our draft was wrong MIT (permissive) · 14fab8e91e876c60 · report
get_llm pprp/pruner-zero/main_opt.py official repository ran MIT (permissive) · 612df986c51330d9 · report
mul pprp/pruner-zero/lib/gptree.py official repository ran fingerprinted MIT (permissive) · dff0648acd37c706 · report
sub pprp/pruner-zero/lib/gptree.py official repository ran fingerprinted MIT (permissive) · fa506a51274c7eac · report
check_sparsity pprp/pruner-zero/lib/prune_opt.py official repository unverified MIT (permissive) · 4cf1dd5e7d4e2ca9 · report
evaluate_ppl pprp/pruner-zero/lora_ft/evaluate_ppl.py official repository unverified MIT (permissive) · 1fa25202a1526a5f · report
get_c4 pprp/pruner-zero/lib/data.py official repository unverified MIT (permissive) · a271ec700d8df453 · report
get_loaders pprp/pruner-zero/lib/data.py official repository unverified MIT (permissive) · b6ec51bc8a06ee71 · report
get_loaders pprp/pruner-zero/lib/gradient_computation.py official repository unverified MIT (permissive) · 35a6bbc8f64f77b7 · report
get_wikitext2 pprp/pruner-zero/lib/data.py official repository unverified MIT (permissive) · 07cb1fc598db64e8 · report
get_wikitext2 pprp/pruner-zero/lib/gradient_computation.py official repository unverified MIT (permissive) · 3a97b0120e186c09 · report
prepare_calibration_input pprp/pruner-zero/lib/prune.py official repository unverified MIT (permissive) · 298323fc64be86fa · report
prepare_calibration_input pprp/pruner-zero/lib/prune_opt.py official repository unverified MIT (permissive) · 6530251d1f1a7f4e · report

Tasks

DiversityLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LLaMAPruning

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