https://github.com/maya-simhi/olala
공식 코드OLALa: Online Learned Adaptive Lattice Codes for Heterogeneous Federated Learning
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/mayank31398/lqvae
공식 코드Variational Inference with Latent Space Quantization for Adversarial Resilience
https://github.com/mcao92/quantizedsci
공식 코드A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging
https://github.com/mct10/repcodec
공식 코드RepCodec: A Speech Representation Codec for Speech Tokenization
https://github.com/mdcnn/Deep-Multiple-Description-Coding
공식 코드Deep Optimized Multiple Description Image Coding via Scalar Quantization Learning
https://github.com/megvii-research/Arch-Net
공식 코드Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
https://github.com/megvii-research/FQ-ViT
공식 코드FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
https://github.com/megvii-research/ssql-eccv2022
공식 코드https://github.com/meituan/yolov6
공식 코드YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
https://github.com/menelaoskanakis/zippypoint
공식 코드https://github.com/mengxiangming/qcs-sgm
공식 코드Quantized Compressed Sensing with Score-based Generative Models
https://github.com/mengxiangming/qcs-sgm-plus
공식 코드QCM-SGM+: Improved Quantized Compressed Sensing With Score-Based Generative Models
https://github.com/mengxiayu/llmsuperweight
공식 코드https://github.com/mhvali/interpretable-gans-by-sfvq
공식 코드https://github.com/michaelkinnas/Reducing-Inference-Energy-Consumption-Using-Two-Complementary-CNNs
공식 코드Reducing Inference Energy Consumption Using Dual Complementary CNNs
https://github.com/michalsvento/NLDistortionDiff
공식 코드Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion
https://github.com/microsoft/DeepSpeed
공식 코드Extreme Compression for Pre-trained Transformers Made Simple and Efficient
https://github.com/microsoft/Lightweight-Low-Resource-NMT
공식 코드https://github.com/microsoft/bidr
공식 코드Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
https://github.com/microsoft/dcvc
공식 코드Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
https://github.com/microsoft/geta
공식 코드https://github.com/microsoft/mopq
공식 코드https://github.com/microsoft/msrflute
공식 코드FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
https://github.com/microsoft/random_quantize
공식 코드Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning
https://github.com/microsoft/speecht5
공식 코드SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
https://github.com/microsoft/t-mac
공식 코드T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge
https://github.com/microsoft/vidtok
공식 코드https://github.com/microsoft/vptq
공식 코드VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
https://github.com/mikecovlee/mLoRA
공식 코드MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts
https://github.com/milvlg/imp
공식 코드Imp: Highly Capable Large Multimodal Models for Mobile Devices
https://github.com/mindspore-ai/models/tree/master/research/cv/AdaBin
공식 코드AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
https://github.com/mingyuj666/rope_with_llm
공식 코드Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
https://github.com/mit-han-lab/apq
공식 코드APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
https://github.com/mit-han-lab/deepcompressor
공식 코드SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
https://github.com/mit-han-lab/duo-attention
공식 코드DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
https://github.com/mit-han-lab/lite-transformer
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.