SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.16286 · 2024

A deeper look at depth pruning of LLMs

arXiv · PDF · Open in the Atlas

Code that ran

12 of 12 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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 9 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2407.16286.json · badge: /api/ran/2407.16286.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
shoaibahmed/llm_depth_pruning canonical (classifier label)
classifier basis: census
12 ran · 0 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shoaibahmed/llm_depth_pruning/block_influence/llama_model.py
pointer only (licence: NONE) · get_code("30d7eec482ebf6b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shoaibahmed/llm_depth_pruning/block_influence/mistral_model.py
pointer only (licence: NONE) · get_code("d61c483a3c2b3156")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shoaibahmed/llm_depth_pruning/block_influence/llama_model.py
pointer only (licence: NONE); the stored copy get_code serves, from Beomi/BitNet-Transformers, is pointer only (licence: NONE) · get_code("37fc3129c3d06e0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

compute_log_probs Ran
ran; our contract draft was wrong, not the code
shoaibahmed/llm_depth_pruning/layer_influence/evaluate_layer_influence.py
pointer only (licence: NONE) · get_code("4106d51ae63372d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

compute_log_probs Ran
ran; our contract draft was wrong, not the code
shoaibahmed/llm_depth_pruning/block_influence_mmlu_shapley/evaluate_mmlu_block_influence.py
pointer only (licence: NONE) · get_code("1c9e8c69cdf2e054")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

format_example Ran
ran; our contract draft was wrong, not the code
shoaibahmed/llm_depth_pruning/evals/mmlu.py
pointer only (licence: NONE) · get_code("cd763eaf1ac287e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

format_subject Ran
ran; our contract draft was wrong, not the code
shoaibahmed/llm_depth_pruning/evals/mmlu.py
pointer only (licence: NONE) · get_code("6ab745408cb8648b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

gen_prompt Ran
ran; our contract draft was wrong, not the code
shoaibahmed/llm_depth_pruning/evals/mmlu.py
pointer only (licence: NONE) · get_code("3383488ea82b6c15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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_dataloader Ran
ran on a synthesized input
shoaibahmed/llm_depth_pruning/dataset.py
pointer only (licence: NONE) · get_code("19beb43140294f1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

is_main_proc Ran
ran, violated the contract we drafted
shoaibahmed/llm_depth_pruning/dist_utils.py
pointer only (licence: NONE) · get_code("d847a98806d5812d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

reduce_tensor Ran
ran, honoured the contract we drafted
shoaibahmed/llm_depth_pruning/dist_utils.py
pointer only (licence: NONE) · get_code("8ca3bc5af5d77698")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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.

rotate_half Ran
ran; our contract draft was wrong, not the code
shoaibahmed/llm_depth_pruning/block_influence/llama_model.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shoaibahmed/llm_depth_pruning 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 3 the same month, 6 later) and 4 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
rotate_half 360 other papers
157 dated earlier, 12 the same month, 182 later, 6 same year, order not determinable, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv 243 other papers
96 dated earlier, 8 the same month, 135 later, 2 same year, order not determinable, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
apply_rotary_pos_emb 75 other papers
36 dated earlier, 3 the same month, 36 later · 2 only as an assembly brick
2309.11499 (2023-09)
DreamLLM: Synergistic Multimodal Comprehension and Creation
2312.02051 (2023-12)
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
2312.03414 (2023-12)
Compressed Context Memory For Online Language Model Interaction
and 72 more not named here
format_subject 21 other papers
14 dated earlier, 7 later
2009.03300 (2020-09)
Measuring Massive Multitask Language Understanding
2304.12986 (2023-04)
Measuring Massive Multitask Chinese Understanding
2305.17306 (2023-05)
Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
and 18 more not named here
format_example 16 other papers
10 dated earlier, 6 later
2009.03300 (2020-09)
Measuring Massive Multitask Language Understanding
2305.17306 (2023-05)
Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
2310.05736 (2023-10)
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
and 13 more not named here
gen_prompt 10 other papers
7 dated earlier, 3 later
2009.03300 (2020-09)
Measuring Massive Multitask Language Understanding
2305.17306 (2023-05)
Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
2310.05736 (2023-10)
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
and 7 more not named here
apply_rotary_pos_emb 5 other papers
5 dated earlier
2308.10882 (2023-08)
Giraffe: Adventures in Expanding Context Lengths in LLMs
2310.11453 (2023-10)
BitNet: Scaling 1-bit Transformers for Large Language Models
2312.15166 (2023-12)
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
and 2 more not named here

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

Large Language Models (LLMs) are not only resource-intensive to train but even more costly to deploy in production. Therefore, recent work has attempted to prune blocks of LLMs based on cheap proxies for estimating block importance, effectively removing 10% of blocks in well-trained LLaMa-2 and Mistral 7b models without any significant degradation of downstream metrics. In this paper, we explore different block importance metrics by considering adaptive metrics such as Shapley value in addition to static ones explored in prior work. We show that adaptive metrics exhibit a trade-off in performance between tasks i.e., improvement on one task may degrade performance on the other due to differences in the computed block influences. Furthermore, we extend this analysis from a complete block to individual self-attention and feed-forward layers, highlighting the propensity of the self-attention layers to be more amendable to pruning, even allowing removal of upto 33% of the self-attention layers without incurring any performance degradation on MMLU for Mistral 7b (significant reduction in costly maintenance of KV-cache). Finally, we look at simple performance recovery techniques to emulate the pruned layers by training lightweight additive bias or low-rank linear adapters. Performance recovery using emulated updates avoids performance degradation for the initial blocks (up to 5% absolute improvement on MMLU), which is either competitive or superior to the learning-based technique.

For agents

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

get_harvested_code_for_paper("2407.16286")
get_code_for_paper("2407.16286")
have("2407.16286")

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

curl https://syntology.ai/api/ran/2407.16286.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.16286.svg)](https://syntology.ai/paper/2407.16286)

Connect an agent — have() is free.