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/graphpku/pissa
공식 코드PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
https://github.com/great8nctu/fox-nas
공식 코드FOX-NAS: Fast, On-device and Explainable Neural Architecture Search
https://github.com/gsgoncalves/emnlp2023_llm_compression_and_social_bias
공식 코드Understanding the Effect of Model Compression on Social Bias in Large Language Models
https://github.com/guanchuwang/division
공식 코드DIVISION: Memory Efficient Training via Dual Activation Precision
https://github.com/gudovskiy/ShiftCNN
공식 코드ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks
https://github.com/gudovskiy/fmap_compression
공식 코드DNN Feature Map Compression using Learned Representation over GF(2)
https://github.com/gugu511yy/ptq4ris
공식 코드PTQ4RIS: Post-Training Quantization for Referring Image Segmentation
https://github.com/guotianyu2000/active-dormant-attention
공식 코드Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs
https://github.com/guxu313/TeViS
공식 코드https://github.com/hafiztiomoko/ternaryrandomfeatures
공식 코드Random matrices in service of ML footprint: ternary random features with no performance loss
https://github.com/hahnyuan/binaryllm
공식 코드https://github.com/hahnyuan/llm-viewer
공식 코드https://github.com/hahnyuan/pb-llm
공식 코드https://github.com/hahnyuan/ptq4vit
공식 코드PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization
https://github.com/hahnyuan/rptq4llm
공식 코드RPTQ: Reorder-based Post-training Quantization for Large Language Models
https://github.com/haiduo/Double-Rounding
공식 코드https://github.com/hanguo97/flute
공식 코드https://github.com/hanguo97/lq-lora
공식 코드LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
https://github.com/hanliu95/DFM
공식 코드Discrete Factorization Machines for Fast Feature-based Recommendation
https://github.com/haofanwang/accurate-head-pose
공식 코드https://github.com/haokang-timmy/gear
공식 코드GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
https://github.com/haonanwang0522/srpose
공식 코드https://github.com/harvard-edge/quarl
공식 코드QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning
https://github.com/hasanssl/bdslw60_code
공식 코드https://github.com/hassanalikhatim/QuSecNets_SSCNets_FaDec
공식 코드https://github.com/hatchetProject/QuEST
공식 코드QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning
https://github.com/hci-unihd/DTAE
공식 코드Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder
https://github.com/hehongc/DCMRL
공식 코드Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills
https://github.com/helmholtzai-fzj/flex_gen
공식 코드Scaling Image Tokenizers with Grouped Spherical Quantization
https://github.com/henkwymeersch/quantizedfeedback
공식 코드Learning Physical-Layer Communication with Quantized Feedback
https://github.com/henryzhongsc/longctx_bench
공식 코드https://github.com/hfutqian/adadfq
공식 코드https://github.com/hfutqian/adasg
공식 코드https://github.com/hguq/IntegerNet
공식 코드Integer-Only Neural Network Quantization Scheme Based on Shift-Batch-Normalization
https://github.com/hikvision-research/SparseShiftLayer
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.