Papers with Code 아카이브

Quantization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 10
보존된 평가 기록: 32

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/aktgpt/vq-nnf

공식 코드

Efficient High-Resolution Template Matching with Vector Quantized Nearest Neighbour Fields

https://github.com/alanansell/peft

공식 코드

Scaling Sparse Fine-Tuning to Large Language Models

https://github.com/albert2x/moc_rvq

공식 코드

MOC-RVQ: Multilevel Codebook-Assisted Digital Generative Semantic Communication

https://github.com/albertomarchisio/swifttron

공식 코드

SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers

https://github.com/alcunha/filtering-empty-camera-trap-images

공식 코드

Filtering Empty Camera Trap Images in Embedded Systems

https://github.com/alex04072000/SingleHDR

공식 코드

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

https://github.com/alexanderrichard/squirrel

공식 코드

A Bag-of-Words Equivalent Recurrent Neural Network for Action Recognition

https://github.com/alexmr09/Mixed-precision-Neural-Networks-on-RISC-V-Cores

공식 코드

Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operations

https://github.com/algohunt/vqrf

공식 코드

Compressing Volumetric Radiance Fields to 1 MB

https://github.com/algolzw/ncnet

공식 코드

Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution

https://github.com/ali77sina/morphuesnet

공식 코드

MorpheusNet: Resource efficient sleep stage classifier for embedded on-line systems

https://github.com/aliyun/alibabacloud-quantization-networks

공식 코드

Quantization Networks

https://github.com/allenbai01/ProxQuant

공식 코드

ProxQuant: Quantized Neural Networks via Proximal Operators

https://github.com/allisonandreyev/WhisperQuantization

공식 코드

Quantization for OpenAI's Whisper Models: A Comparative Analysis

https://github.com/amanmohanty/idl-nncompress

공식 코드

Efficient CNN-LSTM based Image Captioning using Neural Network Compression

https://github.com/amazon-research/dq-bart

공식 코드

DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization

https://github.com/amazon-science/chronos-forecasting

공식 코드

Chronos: Learning the Language of Time Series

https://github.com/amazon-science/polygon-transformer

공식 코드

PolyFormer: Referring Image Segmentation as Sequential Polygon Generation

https://github.com/aminesi/robustness-on-device

공식 코드

Robustness Analysis of Deep Learning Frameworks on Mobile Platforms

https://github.com/amirgholami/ZeroQ

공식 코드

ZeroQ: A Novel Zero Shot Quantization Framework

https://github.com/amirzandieh/qjl

공식 코드

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead

https://github.com/amrnag/specialized-transformers

공식 코드

AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models

https://github.com/ana-oprescu/greenllms

공식 코드

An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2

https://github.com/anacletolab/sham

공식 코드

Compact representations of convolutional neural networks via weight pruning and quantization

https://github.com/andreArtelt/efficient_computation_counterfactuals_lvq

공식 코드

Efficient computation of counterfactual explanations of LVQ models

https://github.com/andreacos/BoostingCNN-Jpeg-Primary-Quantization-Matrix-Estimation

공식 코드

Boosting CNN-based primary quantization matrix estimation of double JPEG images via a classification-like architecture

https://github.com/andreartelt/explaining_lvq_reject

공식 코드

Explaining Reject Options of Learning Vector Quantization Classifiers

https://github.com/andrewnam/gfn_attractors

공식 코드

Discrete, compositional, and symbolic representations through attractor dynamics

https://github.com/andyjm3/SLTrain

공식 코드

SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining

https://github.com/anguswlx/dmassq

공식 코드

Diffusion Models as Stochastic Quantization in Lattice Field Theory

https://github.com/aninrusimha/qat-pretrain

공식 코드

Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization

https://github.com/anony4paper/quan_study

공식 코드

Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment

https://github.com/anonymous1252022/exaq

공식 코드

EXAQ: Exponent Aware Quantization For LLMs Acceleration

https://github.com/anonymous1252022/fp4-all-the-way

공식 코드

FP4 All the Way: Fully Quantized Training of LLMs

https://github.com/antigonerandy/quantbackdoor_efrap

공식 코드

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks

https://github.com/antspy/quantized_distillation

공식 코드

Model compression via distillation and quantization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.