SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.01320 · ICLR · 2024

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

Tao Lin, Hao Zhao, Haobo Song, Soumajit Majumder, Lora Propetl, Adapter Propetl, Padapter, Propetl Lora, Capaboost Lora

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures 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/2407.01320.json · badge: /api/ran/2407.01320.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
LINs-lab/CapaBoost canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
lins-lab/capaboost canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
check_number_comma Ran
ran, violated the contract we drafted
LINs-lab/CapaBoost/src/transformers/convert_slow_tokenizer.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from UW-Madison-Lee-Lab/looped-tf, is pointer only (licence: NONE) · get_code("a727df5fd2f5599a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from UW-Madison-Lee-Lab/looped-tf, and GitHub detected no licence in that repository 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.

ensure_valid_input Ran
ran; our contract draft was wrong, not the code
LINs-lab/CapaBoost/src/transformers/convert_graph_to_onnx.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from UW-Madison-Lee-Lab/looped-tf, is pointer only (licence: NONE) · get_code("d770e1dd1d799a47")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from UW-Madison-Lee-Lab/looped-tf, and GitHub detected no licence in that repository 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.

gelu_fast Ran
ran, honoured the contract we drafted
LINs-lab/CapaBoost/src/transformers/activations_tf.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("37a5eed2dbd663ca")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from VITA-Group/READ-ME, and GitHub detected no licence in that repository 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.

generate_identified_filename Ran
ran; our contract draft was wrong, not the code
LINs-lab/CapaBoost/src/transformers/convert_graph_to_onnx.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from UW-Madison-Lee-Lab/looped-tf, is pointer only (licence: NONE) · get_code("7efe3db5c9e2f94d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from UW-Madison-Lee-Lab/looped-tf, and GitHub detected no licence in that repository 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.

kronecker_product Ran
ran; our contract draft was wrong, not the code
lins-lab/capaboost/src/transformers/adapters/modeling.py
code served (permissive licence) · get_code("54fa343f001c7cff")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 15, 24) 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)

# Create two tensors with batch dimensions and different matrix sizes
# a: shape (2, 3, 4) - batch size 2, matrix 3x4
# b: shape (2, 5, 6) - batch size 2, matrix 5x6
a = torch.randn(2, 3, 4)
b = torch.randn(2, 5, 6)

ARGS = {
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 3, dtype family float, shape (2, 15, 24) — shape (2, 15, 24) 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
mish Ran
ran, honoured the contract we drafted
LINs-lab/CapaBoost/src/transformers/activations_tf.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("cc8c8c3ebf0c343f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from VITA-Group/READ-ME, and GitHub detected no licence in that repository 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.

quick_gelu Ran
ran, honoured the contract we drafted
LINs-lab/CapaBoost/src/transformers/activations_tf.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("e2d56cb91f999bef")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from VITA-Group/READ-ME, and GitHub detected no licence in that repository 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.

convert_slow_tokenizer Not yet run
unverified (harvested, no recorded run)
LINs-lab/CapaBoost/src/transformers/convert_slow_tokenizer.py
code served (permissive licence) · get_code("561495a2688b60b1")
How it ran

no invocation recorded.

get_configuration_file Not yet run
unverified (harvested, no recorded run)
LINs-lab/CapaBoost/src/transformers/configuration_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("dd3166a87bc972ff")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from VITA-Group/READ-ME, and GitHub detected no licence in that repository 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.

infer_shapes Not yet run
unverified (harvested, no recorded run)
LINs-lab/CapaBoost/src/transformers/convert_graph_to_onnx.py
code served (permissive licence) · get_code("0da835817b8a57bc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 3 the same month, 10 later) and 0 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
mish 25 other papers
20 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2106.00420 (2021-06)
Dialogue-oriented Pre-training
and 22 more not named here
gelu_fast 19 other papers
14 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2110.04366 (2021-10)
Towards a Unified View of Parameter-Efficient Transfer Learning
2111.00160 (2021-11)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
and 16 more not named here
quick_gelu 16 other papers
11 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2202.00666 (2022-02)
Locally Typical Sampling
2211.05392 (2022-11)
EVENTS REALM: Event Reasoning of Entity States via Language Models
and 13 more not named here
ensure_valid_input 14 other papers
13 dated earlier, 1 later
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2107.00910 (2021-07)
Learned Token Pruning for Transformers
2111.00160 (2021-11)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
and 11 more not named here
generate_identified_filename 14 other papers
13 dated earlier, 1 later
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2107.00910 (2021-07)
Learned Token Pruning for Transformers
2111.00160 (2021-11)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
and 11 more not named here
infer_shapes 14 other papers
13 dated earlier, 1 later
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2107.00910 (2021-07)
Learned Token Pruning for Transformers
2111.00160 (2021-11)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
and 11 more not named here
check_number_comma 13 other papers
12 dated earlier, 1 later
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2107.00910 (2021-07)
Learned Token Pruning for Transformers
2111.00160 (2021-11)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
and 10 more not named here
convert_slow_tokenizer 13 other papers
12 dated earlier, 1 later
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2107.00910 (2021-07)
Learned Token Pruning for Transformers
2111.00160 (2021-11)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
and 10 more not named here
get_configuration_file 11 other papers
9 dated earlier, 2 later
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2202.00666 (2022-02)
Locally Typical Sampling
2211.05392 (2022-11)
EVENTS REALM: Event Reasoning of Entity States via Language Models
and 8 more not named here
kronecker_product 5 other papers
4 dated earlier, 1 later
2106.04647 (2021-06)
Efficient Low-Rank Hypercomplex Adapter Layers
2301.12132 (2023-01)
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
2305.17682 (2023-05)
One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning
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

Fine-tuning large pre-trained foundation models, such as the 175B GPT-3, have attracted more attention for downstream tasks recently. While parameter-efficient fine-tuning methods have been proposed and proven effective without retraining all model parameters, their performance is limited by the capacity of incremental modules, especially under constrained parameter budgets. To overcome this challenge, we propose CAPABOOST, a simple yet effective strategy that enhances model capacity by leveraging low-rank updates through parallel weight modules in target layers. By applying static random masks to the shared weight matrix, CAPABOOST constructs a diverse set of weight matrices, effectively increasing the rank of incremental weights without adding parameters. Notably, our approach can be seamlessly integrated into various existing parameter-efficient fine-tuning methods. We extensively validate the efficacy of CAPABOOST through experiments on diverse downstream tasks, including natural language understanding, question answering, and image classification. Our results demonstrate significant improvements over baselines, without incurring additional computation or storage costs. Our code is available at https://github.com/LINs-lab/CapaBoost.

For agents

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

get_harvested_code_for_paper("2407.01320")
get_code_for_paper("2407.01320")
have("2407.01320")

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

curl https://syntology.ai/api/ran/2407.01320.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.01320.svg)](https://syntology.ai/paper/2407.01320)

Connect an agent — have() is free.