https://github.com/cwida/pdx
AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information Retrieval
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/cxzhou95/XLSR
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices
https://github.com/czhu95/ternarynet
https://github.com/daniel-furman/sft-demos
https://github.com/daskol/fewbit
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
https://github.com/datastax/jvector
Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD
https://github.com/davidalami/convert
ConveRT: Efficient and Accurate Conversational Representations from Transformers
https://github.com/deJQK/AdaBits
AdaBits: Neural Network Quantization with Adaptive Bit-Widths
https://github.com/deJQK/FracBits
FracBits: Mixed Precision Quantization via Fractional Bit-Widths
https://github.com/deepglint/EasyQuant
EasyQuant: Post-training Quantization via Scale Optimization
https://github.com/dfki-nlp/llmcheckup
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/diff7/DARTS-devices
https://github.com/digantamisra98/digantamisra98.github.io
https://github.com/divisionai/fastText
https://github.com/dmarnerides/hdr-expandnet
https://github.com/dongwonjo/BinaryMoS
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
https://github.com/dr-aheydari/SoftAdapt
Going Beyond Classification Accuracy Metrics in Model Compression
https://github.com/dslisleedh/NCNet-flax
Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
https://github.com/duanzhiihao/qres-vae
https://github.com/eastonYi/wav2vec
Effectiveness of self-supervised pre-training for speech recognition
https://github.com/efficient-large-model/vila
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
https://github.com/eladhoffer/convNet.pytorch
https://github.com/eml-eda/plinio
Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inference
https://github.com/eonu/arx
The Neural Network Pushdown Automaton: Model, Stack and Learning Simulations
https://github.com/ericxsun/fastText
https://github.com/erikaawang/probing-multilingual-dynamics
https://github.com/eth-easl/deltazip
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/etna-team/etna
https://github.com/explosion/floret
https://github.com/facebookresearch/FiD
A Memory Efficient Baseline for Open Domain Question Answering
https://github.com/facebookresearch/brainmagick
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/facebookresearch/fairseq
Unsupervised Cross-lingual Representation Learning for Speech Recognition
https://github.com/facebookresearch/mobilellm
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
https://github.com/facebookresearch/spinquant
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
https://github.com/facebookresearch/uco3d
Compact 3D Scene Representation via Self-Organizing Gaussian Grids
https://github.com/facico/chinese-vicuna
Chinese-Vicuna: A Chinese Instruction-following Llama-based Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.