SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11295 · NeurIPS · 2024

OneBit: Towards Extremely Low-bit Large Language Models

Shuo Wang, Zonghan Yang, Zhiyuan Liu, Xu Han, Yuzhuang Xu, Qingfu Zhu, Weidong Liu, Wanxiang Che

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 4 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/2402.11295.json · badge: /api/ran/2402.11295.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
xuyuzhuang11/OneBit canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
xuyuzhuang11/onebit community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
find_all_linear_modules Ran
ran; our contract draft was wrong, not the code
xuyuzhuang11/onebit/llama_factory/llamafactory/core.py
code served (permissive licence) · get_code("9cfdc209c76fc7a5")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 as nn
from typing import List, Optional

torch.manual_seed(0)

class SimpleLinearModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
        self.lm_head = nn.Linear(2, 5)
        self.nested = nn.Sequential(
            nn.Linear(5, 4),
            nn.ReLU(),
            nn.Linear(4, 3)
        )
    
    def forward(self, x):
        return x

model = SimpleLinearModel()

ARGS = {
    'model': model,
    'quantization_bit': None,
    'output_layer_name': 'lm_head'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
bitsandbytes, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
find_layers Ran
ran; our contract draft was wrong, not the code
xuyuzhuang11/OneBit/evaluation/lm_eval/models_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from utkarshsaxena1/eigenattn, is pointer only (licence: NONE) · get_code("904cd61df2fe8fb9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from utkarshsaxena1/eigenattn, 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.

get_config_class_from_processor_class Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xuyuzhuang11/OneBit/transformers/utils/create_dummy_models.py
pointer only (licence: MIT); the stored copy get_code serves, from takagi97/OXA-Fine-tuning, is pointer only (licence: NONE) · get_code("3d999b95009c7537")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from takagi97/OXA-Fine-tuning, 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.

get_processor_types_from_config_class Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xuyuzhuang11/OneBit/transformers/utils/create_dummy_models.py
pointer only (licence: MIT); the stored copy get_code serves, from takagi97/OXA-Fine-tuning, is pointer only (licence: NONE) · get_code("0c0b81b081919d8e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from takagi97/OXA-Fine-tuning, 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.

hash_args Ran
ran; our contract draft was wrong, not the code
xuyuzhuang11/OneBit/evaluation/lm_eval/base.py
pointer only (licence: MIT); the stored copy get_code serves, from opengvlab/videochat-r1, is pointer only (licence: NONE) · get_code("ea06eaae4fc1eaf0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from opengvlab/videochat-r1, 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.

make_disjoint_window Ran
ran; our contract draft was wrong, not the code
xuyuzhuang11/OneBit/evaluation/lm_eval/models_utils.py
code served (permissive licence) · get_code("4df9168e0a0c38eb")
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 tuple. 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 numpy as np

torch.manual_seed(0)

# The function takes a pair (a, b) where both a and b are sequences
# It slices a to remove the last (len(b) - 1) elements
# Both a and b should support len() and slicing operations
# Lists work perfectly for this

a = [1, 2, 3, 4, 5, 6, 7, 8]  # Context window
b = [9, 10, 11]  # Continuation window

pair = (a, b)

ARGS = {
    "pair": pair
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
pattern_match Ran
ran; our contract draft was wrong, not the code
xuyuzhuang11/OneBit/evaluation/lm_eval/evaluator.py
pointer only (licence: MIT); the stored copy get_code serves, from deeplearning-wisc/weak_llm_teacher, is pointer only (licence: NONE) · get_code("c12b55ef635e9947")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from deeplearning-wisc/weak_llm_teacher, 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.

truncate_number Ran
ran; our contract draft was wrong, not the code
xuyuzhuang11/OneBit/evaluation/lm_eval/models_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from utkarshsaxena1/eigenattn, is pointer only (licence: NONE) · get_code("4e53fbbdfa160f7d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from utkarshsaxena1/eigenattn, 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.

get_architectures_from_config_class Not yet run
unverified (harvested, no recorded run)
xuyuzhuang11/OneBit/transformers/utils/create_dummy_models.py
pointer only (licence: MIT); the stored copy get_code serves, from takagi97/OXA-Fine-tuning, is pointer only (licence: NONE) · get_code("b176efb26f72e507")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from takagi97/OXA-Fine-tuning, 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.

get_pile Not yet run
unverified (harvested, no recorded run)
xuyuzhuang11/OneBit/evaluation/lm_eval/datautils.py
code served (permissive licence) · get_code("ffa31cd3568da2b9")
How it ran

no invocation recorded.

get_ptb Not yet run
unverified (harvested, no recorded run)
xuyuzhuang11/OneBit/evaluation/lm_eval/datautils.py
code served (permissive licence) · get_code("90dfde049522b716")
How it ran

no invocation recorded.

get_wikitext2 Not yet run
unverified (harvested, no recorded run)
xuyuzhuang11/OneBit/evaluation/lm_eval/datautils.py
code served (permissive licence) · get_code("27d7c058388f491d")
How it ran

no invocation 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 12 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 5 the same month, 11 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
hash_args 44 other papers
7 dated earlier, 2 the same month, 33 later, 1 same year, order not determinable, 1 undated
2005.14165 (2020-05)
Language Models are Few-Shot Learners
2110.04374 (2021-10)
A Few More Examples May Be Worth Billions of Parameters
2303.17003 (2023-03)
Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams
and 41 more not named here
get_config_class_from_processor_class 27 other papers
6 dated earlier, 2 the same month, 17 later, 2 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2308.12219 (2023-08)
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
and 24 more not named here
get_architectures_from_config_class 25 other papers
5 dated earlier, 2 the same month, 17 later, 1 same year, order not determinable
2308.12219 (2023-08)
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
2312.15710 (2023-12)
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
and 22 more not named here
get_processor_types_from_config_class 25 other papers
5 dated earlier, 2 the same month, 17 later, 1 same year, order not determinable
2308.12219 (2023-08)
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
2311.07468 (2023-11)
An Analysis and Mitigation of the Reversal Curse
2312.15710 (2023-12)
Alleviating Hallucinations of Large Language Models through Induced Hallucinations
and 22 more not named here
make_disjoint_window 10 other papers
3 dated earlier, 7 later
2304.01089 (2023-04)
RPTQ: Reorder-based Post-training Quantization for Large Language Models
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
and 7 more not named here
find_layers 9 other papers
3 dated earlier, 6 later
2304.01089 (2023-04)
RPTQ: Reorder-based Post-training Quantization for Large Language Models
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
and 6 more not named here
truncate_number 8 other papers
2 dated earlier, 6 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
2403.12544 (2024-03)
AffineQuant: Affine Transformation Quantization for Large Language Models
and 5 more not named here
get_pile 7 other papers
2 dated earlier, 5 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
2404.14047 (2024-04)
An empirical study of LLaMA3 quantization: from LLMs to MLLMs
and 4 more not named here
get_ptb 6 other papers
1 dated earlier, 5 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2403.12544 (2024-03)
AffineQuant: Affine Transformation Quantization for Large Language Models
2404.14047 (2024-04)
An empirical study of LLaMA3 quantization: from LLMs to MLLMs
and 3 more not named here
pattern_match 6 other papers
3 dated earlier, 1 the same month, 2 later
2306.03078 (2023-06)
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
2309.06256 (2023-09)
Mitigating the Alignment Tax of RLHF
2401.12873 (2024-01)
Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model
and 3 more not named here
get_wikitext2 5 other papers
1 dated earlier, 4 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2403.12544 (2024-03)
AffineQuant: Affine Transformation Quantization for Large Language Models
2404.14047 (2024-04)
An empirical study of LLaMA3 quantization: from LLMs to MLLMs
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

Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs. However, current quantization methods suffer severe performance degradation when the bit-width is extremely reduced, and thus focus on utilizing 4-bit or 8-bit values to quantize models. This paper boldly quantizes the weight matrices of LLMs to 1-bit, paving the way for the extremely low bit-width deployment of LLMs. For this target, we introduce a 1-bit model compressing framework named OneBit, including a novel 1-bit parameter representation method to better quantize LLMs as well as an effective parameter initialization method based on matrix decomposition to improve the convergence speed of the quantization framework. Sufficient experimental results indicate that OneBit achieves good performance (at least 81% of the non-quantized performance on LLaMA models) with robust training processes when only using 1-bit weight matrices. Code and checkpoints are available at https://github.com/xuyuzhuang11/OneBit

For agents

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

get_harvested_code_for_paper("2402.11295")
get_code_for_paper("2402.11295")
have("2402.11295")

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

curl https://syntology.ai/api/ran/2402.11295.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.11295.svg)](https://syntology.ai/paper/2402.11295)

Connect an agent — have() is free.