https://github.com/lawrencerliu/nowag
공식 코드NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models
Papers with Code 아카이브
Quantization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/leapmind/ern
공식 코드https://github.com/leeyegy/SimDR
공식 코드SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation
https://github.com/lgrativol/fl_exps
공식 코드Federated learning compression designed for lightweight communications
https://github.com/lgrativol/flocora_eusipco24
공식 코드FLoCoRA: Federated learning compression with low-rank adaptation
https://github.com/lgrco/l-greco
공식 코드L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning
https://github.com/lhxcs/dvd-quant
공식 코드DVD-Quant: Data-free Video Diffusion Transformers Quantization
https://github.com/libertyeagle/LISA
공식 코드Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation
https://github.com/libozhu03/passionsr
공식 코드https://github.com/libozhu03/qartsr
공식 코드https://github.com/lidq92/mpeg-pcc-tmc13
공식 코드Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression
https://github.com/lifelonglab/tinysubnets
공식 코드TinySubNets: An efficient and low capacity continual learning strategy
https://github.com/lightmatter-ai/int-fp-qsim
공식 코드INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision Transformers
https://github.com/lihuantong/hast
공식 코드https://github.com/lilujunai/emq-series
공식 코드EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization
https://github.com/limapku/qsam
공식 코드Picking Up Quantization Steps for Compressed Image Classification
https://github.com/limei0307/GQT
공식 코드https://github.com/linfeng-feng/uld
공식 코드Eliminating Quantization Errors in Classification-Based Sound Source Localization
https://github.com/little0o0/quaff
공식 코드Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis
https://github.com/littlepey/ptpm
공식 코드Semi-supervised 3D Object Detection with PatchTeacher and PillarMix
https://github.com/liuqk3/put
공식 코드Reduce Information Loss in Transformers for Pluralistic Image Inpainting
https://github.com/liuxuannan/stochastic-gradient-aggregation
공식 코드Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation
https://github.com/liuzechun/nonuniform-to-uniform-quantization
공식 코드https://github.com/liyunqianggyn/equal-bits-bnn
공식 코드Equal Bits: Enforcing Equally Distributed Binary Network Weights
https://github.com/lizonghang/prima.cpp
공식 코드PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters
https://github.com/lmbxmu/RBNN
공식 코드https://github.com/lollipop321/mini-decoder-network
공식 코드https://github.com/longhao-chen/aicas2024
공식 코드https://github.com/lowlevelai/glare
공식 코드GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval
https://github.com/lpyhdzx/DecoQuant_code
공식 코드Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression
https://github.com/lsyhprum/brewess
공식 코드Routing-Guided Learned Product Quantization for Graph-Based Approximate Nearest Neighbor Search
https://github.com/lth14/mar
공식 코드https://github.com/lucas-schwengber/h2q
공식 코드https://github.com/lucidrains/vector-quantize-pytorch
공식 코드https://github.com/luithw/decolle-quantization
공식 코드https://github.com/lukaslaobeyer/token-opt
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.