Papers › BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation

BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation

16 Feb 2024arXiv:2402.10631archive 2025-07-28

Dayou Du, Yijia Zhang, Shijie Cao, Jiaqi Guo, Ting Cao, Xiaowen Chu, Ningyi Xu

The upscaling of Large Language Models (LLMs) has yielded impressive advances in natural language processing, yet it also poses significant deployment challenges. Weight quantization has emerged as a widely embraced solution to reduce memory and computational demands. This paper introduces BitDistiller, a framework that synergizes Quantization-Aware Training (QAT) with Knowledge Distillation (KD) to boost the performance of LLMs at ultra-low precisions (sub-4-bit). Specifically, BitDistiller first incorporates a tailored asymmetric quantization and clipping technique to maximally preserve the fidelity of quantized weights, and then proposes a novel Confidence-Aware Kullback-Leibler Divergence (CAKLD) objective, which is employed in a self-distillation manner to enable faster convergence and superior model performance. Empirical evaluations demonstrate that BitDistiller significantly surpasses existing methods in both 3-bit and 2-bit configurations on general language understanding and complex reasoning benchmarks. Notably, BitDistiller is shown to be more cost-effective, demanding fewer data and training resources. The code is available at https://github.com/DD-DuDa/BitDistiller.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

dd-duda/bitdistiller officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 8 ran (3 instrument-failed) · 7 unverified report
microsoft/bitblas mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits (arXiv:2402.17764; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

15 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
3ran
7unverified

Licence: 3 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from dd-duda/bitdistiller. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

dd-duda/bitdistiller official repository 15 samples, 8 ran (3 instrument-failed) · 7 unverified
build_alibi_bias inference/models/mpt.py ran MIT (permissive) · f9ef8eeb630a0972 · report fixture: signature n_heads:int/0/int, seq_len:int/0/int, full:bool/0/bool, alibi_bias_max:int/0/int, dtype:dtype/0/? · returned tuple · level recorded 2026-09-24
calculate_zeros_width quantization/qmodule.py ran MIT (permissive) · fd8719af3db2c5ae · report fixture: signature in_features:int/0/int, group_size:int/0/int, pack_num:int/0/int · returned int · level recorded 2026-09-24
gen_slopes inference/models/mpt.py ran · honoured contract fingerprinted MIT (permissive) · 5dfd0c2387dff573 · report fixture: signature n_heads:int/0/int, alibi_bias_max:int/0/int · returned Tensor · level recorded 2026-09-24
get_named_linears quantization/pre_quant.py ran · our draft was wrong MIT (permissive) · 0310065bdf9208bb · report fixture: signature module:callable/0/? · returned dict · level recorded 2026-09-24
make_divisible in 76 papers quantization/qmodule.py ran fingerprinted MIT (permissive) · ad85b288e9acb9c2 · report fixture: signature c:int/0/int, divisor:int/0/int · returned int · level recorded 2026-09-24
precompute_freqs_cis in 112 papers inference/models/llama.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 14a84c2cbfebc413 · report fixture: signature dim:int/0/int, end:int/0/int, theta:float/0/float · returned Tensor · level recorded 2026-09-22
reshape_for_broadcast in 90 papers
census: 6 implementations from 10 papers, 1 distinct output on one shared input
inference/models/llama.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 70bf6ebaafd266c4 · report fixture: signature freqs_cis:Tensor/2/float, x:Tensor/4/float · returned Tensor · level recorded, date not recorded
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
inference/models/falcon.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 766ad0e51b7a8f09 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-26
apply_rotary_emb in 121 papers inference/models/llama.py unverified MIT (permissive) · 797af70a155dd94f · report
convertModelToQuant quantization/qlinear.py unverified MIT (permissive) · daff7fa3b7b944d2 · report
get_blocks in 39 papers quantization/pre_quant.py unverified MIT (permissive) · fa80a6587641fb46 · report
get_calib_dataset quantization/clip_utils.py unverified MIT (permissive) · a1ca17436132cd8f · report
get_calib_dataset_code quantization/clip_utils.py unverified MIT (permissive) · eca59c8a0da72a0c · report
get_pile_dataset quantization/clip_utils.py unverified MIT (permissive) · 05aeb596afd8012e · report
run_awq quantization/pre_quant.py unverified MIT (permissive) · fa755c29499d4073 · report

Tasks

Knowledge DistillationQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge Distillation

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