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/tegusi/RGCNN
https://github.com/tencentarc/open-magvit2
Taming Scalable Visual Tokenizer for Autoregressive Image Generation
https://github.com/tencentyouturesearch/crowdcounting-p2pnet
Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting
https://github.com/tensorflow/models/tree/master/research/seq_flow_lite
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
https://github.com/tensorflow/models/tree/master/research/sequence_projection
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
https://github.com/thaarres/Quantized_CNN
https://github.com/theundercover01/caga-a-cascaded-dilated-convolution-approach-for-mpox-lesion-classification
A Transfer Learning and Explainable Solution to Detect mpox from Smartphones images
https://github.com/thisisbillhe/zipcache
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
https://github.com/thu-ml/spargeattn
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
https://github.com/thudm/chatglm
https://github.com/thudm/chatglm-6b
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/thudm/chatglm2-6b
https://github.com/thudm/chatglm3
https://github.com/thulab/DeepHash
https://github.com/tommyod/KDEpy
Efficient statistical classification of satellite measurements
https://github.com/tongjingqi/code2logic
https://github.com/trietnm2/sent2vec4j
https://github.com/tshev/faster-FastText
https://github.com/tval2/contextual-pruning
Mini-GPTs: Efficient Large Language Models through Contextual Pruning
https://github.com/twistedcubic/learn-to-hash
https://github.com/ucb-bar/gemmini
https://github.com/una-dinosauria/stacked-quantizers
https://github.com/uw-mad-dash/Accordion
Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
https://github.com/vaapopescu/gradient-pruning
https://github.com/vainf/tinyfusion
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
https://github.com/vasudevgupta7/gsoc-wav2vec2
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/vectorch-ai/scalellm
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
https://github.com/verified-intelligence/alpha-beta-crown
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
https://github.com/vicentvankor/sun-shine
https://github.com/vinhkhuc/JFastText
https://github.com/vinsis/ternary-quantization
https://github.com/vita-group/atmc
Model Compression with Adversarial Robustness: A Unified Optimization Framework
https://github.com/voice-privacy-challenge/voice-privacy-challenge-2024
Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques
https://github.com/vovamedentsiy/mpdnn
Mixed Precision DNNs: All you need is a good parametrization
https://github.com/vuthede/heatmap-based-landmarker
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.