SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.04768 · 2020

Linformer: Self-Attention with Linear Complexity

Sinong Wang, Hao Ma, Han Fang, Madian Khabsa, Belinda Li

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2006.04768.json · badge: /api/ran/2006.04768.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
tatp22/linformer-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
kuixu/Linear-Multihead-Attention reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
gen_causal_mask Ran
ran, violated the contract we drafted
tatp22/linformer-pytorch/linformer_pytorch/linformer_pytorch.py
code served (permissive licence) · get_code("4ed834b7676d8783")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "input_size": 5,
    "dim_k": 3,
    "full_attention": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (5, 3) — shape (5, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_act Ran
ran; our contract draft was wrong, not the code
tatp22/linformer-pytorch/linformer_pytorch/linformer_pytorch.py
code served (permissive licence) · get_code("289eea67db7520a9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned builtin_function_or_method. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function get_act takes an activation parameter and returns a callable
# or None based on string matching. We'll test with each case.

# Test case 1: 'gelu' activation
activation_gelu = 'gelu'

# Test case 2: 'relu' activation  
activation_relu = 'relu'

# Test case 3: unknown activation
activation_unknown = 'unknown'

# We'll use the 'gelu' case as the primary argument
ARGS = {
    'activation': 'gelu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type builtin_function_or_method — a builtin_function_or_method output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a builtin_function_or_method output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
identity Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/marge-pytorch
pointer only · get_code("caeb28d34b34bc2a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

linear_multi_head_attention_forward Not yet run
unverified (harvested, no recorded run)
kuixu/Linear-Multihead-Attention/linear_multihead_attention.py
pointer only (licence: NONE) · get_code("7255bb9dcda93e92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kuixu/Linear-Multihead-Attention 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 1 later) and 1 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
identity 5 other papers
3 dated earlier, 1 the same month, 1 later
1912.11554 (2019-12)
Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
2002.05202 (2020-02)
GLU Variants Improve Transformer
2003.05997 (2020-03)
Efficient Content-Based Sparse Attention with Routing Transformers
and 2 more not named here
gen_causal_mask 1 other paper
1 dated earlier
1706.03762 (2017-06)
Attention Is All You Need
get_act 1 other paper
1 dated earlier
1706.03762 (2017-06)
Attention Is All You Need

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 2026-11-21.

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 transformer models have shown extraordinary success in achieving state-ofthe-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences, as the standard self-attention mechanism of the Transformer uses O(n 2 ) time and space with respect to sequence length. In this paper, we demonstrate that the self-attention mechanism can be approximated by a low-rank matrix. We further exploit this finding to propose a new self-attention mechanism, which reduces the overall self-attention complexity from O(n 2 ) to O(n) in both time and space. The resulting linear transformer, the Linformer, performs on par with standard Transformer models, while being much more memory-and time-efficient. Preprint. Under review.

For agents

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

get_harvested_code_for_paper("2006.04768")
get_code_for_paper("2006.04768")
have("2006.04768")

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

curl https://syntology.ai/api/ran/2006.04768.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.04768.svg)](https://syntology.ai/paper/2006.04768)

Connect an agent — have() is free.