MétaCan
Menu
Back to cohort

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models

2024· article· en· W4404783494 on OpenAlexaff
Wenjing Ke, Zhe Li, Dong Li, Lu Tian, Emad Barsoum

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsAdvanced Micro Devices (Canada)
Fundersnot available
KeywordsComputer scienceQuantization (signal processing)Rank (graph theory)Language modelArtificial intelligenceNatural language processingSpeech recognitionMathematicsAlgorithmCombinatorics

Abstract

fetched live from OpenAlex

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research.Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream tasks.Quantization-aware Training (QAT) can alleviate this problem, but it requires significantly more computational resources.To tackle this, we introduced Weight-Decomposed Low-Rank Quantization-Aware Training (DL-QAT), which merges the advantages of QAT while training only less than 1% of the total parameters.Specifically, we introduce a group-specific quantization magnitude to adjust the overall scale of each quantization group.Within each quantization group, we use LoRA matrices to update the weight size and direction in the quantization space.We validated the effectiveness of our method on the LLaMA and LLaMA2 model families.The results show significant improvements over our baseline method across different quantization granularities.For instance, for LLaMA-7B, our approach outperforms the previous state-ofthe-art method by 4.2% in MMLU on 3-bit LLaMA-7B model.Additionally, our quantization results on pre-trained models also surpass previous QAT methods, demonstrating the superior performance and efficiency of our approach.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.976
Threshold uncertainty score0.539

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.041
GPT teacher head0.297
Teacher spread0.256 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207