Papers › OneBit: Towards Extremely Low-bit Large Language Models

OneBit: Towards Extremely Low-bit Large Language Models

17 Feb 2024arXiv:2402.11295archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.11295")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xuyuzhuang11/onebit officialmentioned in papermentioned on GitHubjaxMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 6 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
3ran
6unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from xuyuzhuang11/onebit. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “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.

Each sample ends with its 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.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

find_all_linear_modules xuyuzhuang11/onebit/llama_factory/llamafactory/core.py official repository ran · our draft was wrong MIT (permissive) · 9cfdc209c76fc7a5 · report
find_layers xuyuzhuang11/OneBit/evaluation/lm_eval/models_utils.py official repository ran MIT (permissive) · 904cd61df2fe8fb9 · report
hash_args xuyuzhuang11/OneBit/evaluation/lm_eval/base.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · ea06eaae4fc1eaf0 · report
make_disjoint_window xuyuzhuang11/OneBit/evaluation/lm_eval/models_utils.py official repository ran MIT (permissive) · 4df9168e0a0c38eb · report
pattern_match xuyuzhuang11/OneBit/evaluation/lm_eval/evaluator.py official repository ran · our draft was wrong MIT (permissive) · c12b55ef635e9947 · report
truncate_number xuyuzhuang11/OneBit/evaluation/lm_eval/models_utils.py official repository ran fingerprinted MIT (permissive) · 4e53fbbdfa160f7d · report
get_architectures_from_config_class xuyuzhuang11/OneBit/transformers/utils/create_dummy_models.py official repository unverified MIT (permissive) · b176efb26f72e507 · report
get_config_class_from_processor_class xuyuzhuang11/OneBit/transformers/utils/create_dummy_models.py official repository unverified MIT (permissive) · 3d999b95009c7537 · report
get_pile xuyuzhuang11/OneBit/evaluation/lm_eval/datautils.py official repository unverified MIT (permissive) · ffa31cd3568da2b9 · report
get_processor_types_from_config_class xuyuzhuang11/OneBit/transformers/utils/create_dummy_models.py official repository unverified MIT (permissive) · 0c0b81b081919d8e · report
get_ptb xuyuzhuang11/OneBit/evaluation/lm_eval/datautils.py official repository unverified MIT (permissive) · 90dfde049522b716 · report
get_wikitext2 xuyuzhuang11/OneBit/evaluation/lm_eval/datautils.py official repository unverified MIT (permissive) · 27d7c058388f491d · report

Tasks

Quantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusLLaMASPEED

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