https://github.com/ejaasaari/lorann-experiments
공식 코드LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
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/ejmichaud/quantization-model
공식 코드https://github.com/eladhoffer/quantized.pytorch
공식 코드https://github.com/elliothe/n3h_core
공식 코드N3H-Core: Neuron-designed Neural Network Accelerator via FPGA-based Heterogeneous Computing Cores
https://github.com/elybrand/quantized_neural_networks
공식 코드https://github.com/eml-eda/mixprec-pruning
공식 코드Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks
https://github.com/eml-eda/multi-prec-nas
공식 코드Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes
https://github.com/enyac-group/evol-q
공식 코드Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
https://github.com/enyac-group/quamba
공식 코드Quamba: A Post-Training Quantization Recipe for Selective State Space Models
https://github.com/epfml/sparsifiedSGD
공식 코드https://github.com/erellgachon/cytolot
공식 코드https://github.com/eric-qi/neuroquant
공식 코드On Quantizing Neural Representation for Variable-Rate Video Coding
https://github.com/ericwudayi/SkipVQVC
공식 코드VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture
https://github.com/erilyth/HybridBinaryNetworks-WACV18
공식 코드Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory
https://github.com/ermongroup/LISA
공식 코드LISA: Learning Interpretable Skill Abstractions from Language
https://github.com/erxinyu/disbert
공식 코드Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables
https://github.com/eth-pbl/edgecodec
공식 코드EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
https://github.com/eth-sri/llm-quantization-attack
공식 코드https://github.com/ethancaballero/broken_neural_scaling_laws
공식 코드https://github.com/etidav/next
공식 코드https://github.com/etri/nest-compiler
공식 코드https://github.com/evan-sudo/d2gv
공식 코드D2GV: Deformable 2D Gaussian Splatting for Video Representation in 400FPS
https://github.com/ewsn1593/hdrq
공식 코드Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
https://github.com/eyalfish/artoveq
공식 코드Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization
https://github.com/f4biian/hallurag
공식 코드https://github.com/fab-jul/imgcomp-cvpr
공식 코드https://github.com/fabecode/GraphML-FHE
공식 코드https://github.com/facebookresearch/LLM-QAT
공식 코드LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
https://github.com/facebookresearch/active_indexing
공식 코드https://github.com/facebookresearch/any4
공식 코드https://github.com/facebookresearch/audio2photoreal
공식 코드From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations
https://github.com/facebookresearch/bitsandbytes
공식 코드https://github.com/facebookresearch/deepfloat
공식 코드https://github.com/facebookresearch/demucs
공식 코드https://github.com/facebookresearch/diffq
공식 코드Differentiable Model Compression via Pseudo Quantization Noise
https://github.com/facebookresearch/faiss
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.