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/aurelio-labs/semantic-router
https://github.com/autumn0409/Log-based-Anomaly-Detection-System
https://github.com/avrahamraviv/formal-verification-of-object-detection
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
https://github.com/awslabs/speech-representations
DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
https://github.com/badranX/dpq-embedding-compression-torch
Differentiable Product Quantization for End-to-End Embedding Compression
https://github.com/baithebest/adagp
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
https://github.com/baithebest/sparsellm
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
https://github.com/bemova/Deep-Compression-Compressing-Deep-Neural-Networks-with-Pruning-Trained-Quantization-and-Huffman
https://github.com/bentoml/openllm
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/bitsun/faiss-windows
https://github.com/bohanzhuang/Towards-Effective-Low-bitwidth-Convolutional-Neural-Networks
Towards Effective Low-bitwidth Convolutional Neural Networks
https://github.com/bond1995/laser
Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
https://github.com/bowenl0218/bpgan-signal-compression
https://github.com/brandon3964/multimodal-task-vector
https://github.com/bung87/fastText
https://github.com/burcgokden/PLDR-LLM-with-KVG-cache
Power Law Graph Transformer for Machine Translation and Representation Learning
https://github.com/burcgokden/llm-from-power-law-decoder-representations
Power Law Graph Transformer for Machine Translation and Representation Learning
https://github.com/bytedance/dplm
https://github.com/cachett/DCGANandCAE
Deep Convolutional AutoEncoder-based Lossy Image Compression
https://github.com/calipos/dorefa-caffe
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
https://github.com/cambridge-mlg/variational-shannon-coding
https://github.com/casper-hansen/autoawq
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
https://github.com/chenchongthu/ENMF
Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters
https://github.com/chenlicodebank/dynamic-confidence-in-spiking-neural-networks
Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks
https://github.com/chuanraoCV/INQ-incremental-network-quantization-towards-lossless-CNNs-with-low-precision-weights
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
https://github.com/ciodar/deep-compression
https://github.com/cisiplab/cisip-fire
One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
https://github.com/cmacdonald/pyt_jpq
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance
https://github.com/code-implementation1/Code1/tree/main/EF-ENAS
ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
https://github.com/code2k13/nlphose
https://github.com/code2k13/nlppipe
https://github.com/codelion/adaptive-classifier
https://github.com/colorjam/PAMS
PAMS: Quantized Super-Resolution via Parameterized Max Scale
https://github.com/cui0523/Code6/tree/main/ternarybert
https://github.com/currentsapi/fastlangid
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.