Home › Code › find_layers

find_layers

Syntologyentry name in harvested coderead from the graph 2026-09-24

find_layers appears in the code Syntology harvested for 68 papers, as 17 distinct code bodies found in 71 places (a place is one code body under one paper). At least one of them ran in 65 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named find_layers do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 14 of the 17 distinct code bodies named find_layers; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
8ran · our draft was wrong
0ran · fixture could not drive it
6ran
3unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 25 of the 71 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

68 papers shown of 68, newest first; 71 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 7 papers added by Syntology; 11 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration added by Syntology 2026-06 (from id) pietrotrope/Dont_Go_Breaking_My_LLM/track_block_activations.py 088898428fc14c3e ran no licence file found · pointer only
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization added by Syntology 2026-06 (from id) Superone77/AlphaQ/modelutils.py 42a68e1344b46dfb ran no licence file found · pointer only
3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs added by Syntology 2026-03 (from id) mazumder-lab/3BASiL/pipeline.py a27cec0b3dcb1fec unverified Apache-2.0 (permissive)
SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models added by Syntology 2026-02 (from id) Nkniexin/SFMP/GPTQ/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Fine-Grained Expert Merging and Bit-packed Inference added by Syntology 2025-11 (from id) Supercomputing-System-AI-Lab/PuzzleMoE/puzzlemoe/utils/merge_experts_function.py 14fab8e91e876c60 ran · our draft was wrong Apache-2.0 (permissive)
PT$^2$-LLM: Post-Training Ternarization for Large Language Models added by Syntology 2025-10 (from id) XIANGLONGYAN/PT2-LLM/pt2_llm/model_utils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM added by Syntology 2025-10 (from id) log-postech/elsa/lib/utils.py 6644b68819429769 ran · our draft was wrong no licence file found · pointer only
arXiv:2506.09351 2025-06 (from id) yuchenblah/DIVE/prune/lib/prune_mlp_unif.py 2ed16fcdc14ad951 ran · our draft was wrong Apache-2.0 (permissive)
SAFE: Finding Sparse and Flat Minima to Improve Pruning 7 Jun 2025 LOG-postech/safe-torch/language/lib/prune.py 6644b68819429769 ran · our draft was wrong MIT (permissive)
arXiv:2506.03781 2025-06 (from id) OpenGVLab/OmniQuant/models/models_utils.py 904cd61df2fe8fb9 ran MIT (permissive)
An Empirical Study of Qwen3 Quantization 4 May 2025 efficient-ml/qwen3-quantization/BiLLM/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning 17 Dec 2024 xinykou/nlsr/src/prune_regions/prune.py 2ed16fcdc14ad951 ran · our draft was wrong no licence file found · pointer only
Squeezed Attention: Accelerating Long Context Length LLM Inference 14 Nov 2024 SqueezeAILab/SqueezedAttention/utils/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization 8 Nov 2024 georgia-tech-synergy-lab/microscopiq-llm-quantization/utils/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models 12 Oct 2024 vengdeng/darex/utils/getwx.py 2ed16fcdc14ad951 ran · our draft was wrong no licence file found · pointer only
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning 9 Oct 2024 abx393/llm-pruning-calibration-data/lib/prune.py 2ed16fcdc14ad951 ran · our draft was wrong Apache-2.0 (permissive)
MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More 8 Oct 2024 Aaronhuang-778/MC-MoE/modelutils.py 42a68e1344b46dfb ran no licence file found · pointer only
Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization 27 Sep 2024 usamec/double_sparse/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models 25 Sep 2024 microsoft/vptq/vptq/layers/utils.py 6886c53e21133de1 ran MIT (permissive)
OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition 20 Sep 2024 stephenqz/oats/OATS/pruning_utils.py 14fab8e91e876c60 ran · our draft was wrong no licence file found · pointer only
Eigen Attention: Attention in Low-Rank Space for KV Cache Compression 10 Aug 2024 utkarshsaxena1/eigenattn/models/models_utils.py 904cd61df2fe8fb9 ran no licence file found · pointer only
LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid 14 Jul 2024 LeanModels/LeanQuant/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs 24 Jun 2024 kiddyboots216/lottery-ticket-adaptation/rlaif/save_mask.py 2ed16fcdc14ad951 ran · our draft was wrong Apache-2.0 (permissive)
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization 10 Jun 2024 gatech-eic/shiftaddllm/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models 5 Jun 2024 pprp/pruner-zero/lib/prune.py 2ed16fcdc14ad951 ran · our draft was wrong MIT (permissive)
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models 5 Jun 2024 pprp/pruner-zero/lora_ft/evaluate_ppl.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models 5 Jun 2024 pprp/pruner-zero/lib/gradient_computation.py 14fab8e91e876c60 ran · our draft was wrong MIT (permissive)
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs 3 Jun 2024 Hsu1023/DuQuant/models/models_utils.py 904cd61df2fe8fb9 ran MIT (permissive)
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization 2 Jun 2024 AozhongZhang/MagR/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
Sparse Expansion and Neuronal Disentanglement 24 May 2024 shavit-lab/sparse-expansion/utils/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models 23 May 2024 Aaronhuang-778/SliM-LLM/slim-llm/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models 23 May 2024 Aaronhuang-778/SliM-LLM/slim-llm-plus/models/models_utils.py 904cd61df2fe8fb9 ran no licence file found · pointer only
A safety realignment framework via subspace-oriented model fusion for large language models 15 May 2024 xinykou/safety_realignment/lm_eval/code_task/modeling.py 3ab3c57755867f9a ran no licence file found · pointer only
An empirical study of LLaMA3 quantization: from LLMs to MLLMs 22 Apr 2024 macaronlin/llama3-quantization/models/models_utils.py 904cd61df2fe8fb9 ran no licence file found · pointer only
AffineQuant: Affine Transformation Quantization for Large Language Models 19 Mar 2024 bytedance/affinequant/models/models_utils.py 904cd61df2fe8fb9 ran Apache-2.0 (permissive)
FrameQuant: Flexible Low-Bit Quantization for Transformers 10 Mar 2024 vsingh-group/framequant/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact 2 Mar 2024 squeezeailab/kvquant/benchmarking/kvquant/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
SparseLLM: Towards Global Pruning for Pre-trained Language Models 28 Feb 2024 BaiTheBest/SparseLLM/pruning_utils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation 18 Feb 2024 linkanonymous/besa/utils/tools.py 14fab8e91e876c60 ran · our draft was wrong no licence file found · pointer only
OneBit: Towards Extremely Low-bit Large Language Models 17 Feb 2024 xuyuzhuang11/OneBit/evaluation/lm_eval/models_utils.py 904cd61df2fe8fb9 ran MIT (permissive)
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers 14 Feb 2024 SamsungLabs/aespa/utils.py 1174e949ac22ea59 ran · our draft was wrong licence not identified · pointer only
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs 6 Feb 2024 aaronhuang-778/billm/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization 31 Jan 2024 SqueezeAILab/KVQuant/deployment/kvquant/modelutils.py 71eb7727feb23c97 ran · our draft was wrong no licence file found · pointer only
Fast and Effective Weight Update for Pruned Large Language Models 1 Jan 2024 fmfi-compbio/admm-pruning/lib/prune.py 2ed16fcdc14ad951 ran · our draft was wrong MIT (permissive)
Fluctuation-based Adaptive Structured Pruning for Large Language Models 19 Dec 2023 casia-iva-lab/flap/lib/prune.py 2ed16fcdc14ad951 ran · our draft was wrong Apache-2.0 (permissive)
ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models 10 Dec 2023 hahnyuan/asvd4llm/quantization.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing 10 Nov 2023 tsa18/PCR/quantization_tools/quantization/quantizer_utils.py 819214853c3d34c7 ran no licence file found · pointer only
Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models 8 Nov 2023 rocktimjyotidas/gblm-pruner/gradient_computation.py 2ed16fcdc14ad951 ran · our draft was wrong MIT (permissive)
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models 25 Oct 2023 ist-daslab/qmoe/switch.py 87506509921686ee ran · our draft was wrong Apache-2.0 (permissive)
One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models 14 Oct 2023 talkking/MixGPT/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs 13 Oct 2023 zyxxmu/dsnot/lib/prune.py 2ed16fcdc14ad951 ran · our draft was wrong no licence file found · pointer only
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models 12 Oct 2023 modeltc/qllm/models/models_utils.py 904cd61df2fe8fb9 ran Apache-2.0 (permissive)
Composite Backdoor Attacks Against Large Language Models 11 Oct 2023 miraclehh/cba/multimodal/llama2_accessory/eval/modeling.py 3ab3c57755867f9a ran no licence file found · pointer only
PB-LLM: Partially Binarized Large Language Models 29 Sep 2023 hahnyuan/binaryllm/gptq_pb/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers 28 Sep 2023 kuleshov-group/llmtools/llmtools/utils.py a9e7f2cdf016b88b ran · our draft was wrong no licence file found · pointer only
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics 13 Sep 2023 ucsc-vlaa/sight-beyond-text/llava/eval/mmlu/mmlu_modeling.py 3ab3c57755867f9a ran Apache-2.0 (permissive)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models 25 Aug 2023 opengvlab/omniquant/models/models_utils.py 904cd61df2fe8fb9 ran MIT (permissive)
ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation 28 Jul 2023 lianjiatech/belle/models/gptq/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
Llama 2: Open Foundation and Fine-Tuned Chat Models 18 Jul 2023 squeezeailab/squeezellm/squeezellm/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
A Simple and Effective Pruning Approach for Large Language Models 20 Jun 2023 locuslab/wanda/lib/prune.py 56ac52f94f2cc872 ran · our draft was wrong MIT (permissive)
RPTQ: Reorder-based Post-training Quantization for Large Language Models 3 Apr 2023 hahnyuan/rptq4llm/models/models_utils.py 904cd61df2fe8fb9 ran MIT (permissive)
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis 25 Mar 2022 openlmlab/moss/models/quantization.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
arXiv:openreview_d3RFDLBw01 AI2C-Lab/STLA/utils.py 1174e949ac22ea59 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:openreview_Im05D8gFFn mazumder-lab/RobOP/RobOP-ALPS/utils_models.py a9e7f2cdf016b88b ran · our draft was wrong MIT (permissive)
arXiv:aaai_28960 CASIA-IVA-Lab/FLAP/lib/prune.py 2ed16fcdc14ad951 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2025.findings-emnlp.1054 IST-DASLab/sparsegpt/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2025.findings-acl.394 TheShineyue/HSR/alignment-attribution-hsr/lib/prune.py 2ed16fcdc14ad951 ran · our draft was wrong MIT (permissive)
arXiv:2025.acl-long.590 ChnQ/SPIN/src/SPIN.py 2ed16fcdc14ad951 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2024.findings-naacl.145 LianjiaTech/BELLE/models/gptq/modelutils.py a9e7f2cdf016b88b ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2024.findings-acl.933 AutoGPTQ/AutoGPTQ/auto_gptq/modeling/_utils.py ac48f2f323eda99e unverified MIT (permissive)
arXiv:2023.emnlp-main.892 SamsungLabs/Z-Fold/zfold.py 602607980dfc128c unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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