https://github.com/dd-duda/bitdistiller
공식 코드BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation
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/declare-lab/vip
공식 코드Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding
https://github.com/deep-fry/mayo
공식 코드https://github.com/deep-privacy/SA-toolkit
공식 코드Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques
https://github.com/descriptinc/descript-audio-codec
공식 코드https://github.com/devnkong/VQ-GNN
공식 코드VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
https://github.com/diaoenmao/Dimension-Reduced-Turbulent-Flow-Data-From-Deep-Vector-Quantizers
공식 코드A Physics-Informed Vector Quantized Autoencoder for Data Compression of Turbulent Flow
https://github.com/diff7/QuanToaster
공식 코드https://github.com/dimitarsh1/nmt-ecofootprint
공식 코드The Ecological Footprint of Neural Machine Translation Systems
https://github.com/dingxiaoh/repoptimizers
공식 코드https://github.com/dixin-lab/bfvr-stc
공식 코드Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
https://github.com/dlyuangod/tinygpt-v
공식 코드TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
https://github.com/dlyuangod/vit-1.58b
공식 코드https://github.com/dongchen06/macacc
공식 코드https://github.com/donglao/srt
공식 코드Sub-token ViT Embedding via Stochastic Resonance Transformers
https://github.com/dongyounglim/etheopoula
공식 코드https://github.com/dongyp13/Stochastic-Quantization
공식 코드Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization
https://github.com/dqwang122/lssamp
공식 코드Accelerating Antimicrobial Peptide Discovery with Latent Structure
https://github.com/dsevero/rcaq
공식 코드https://github.com/duangzhu/maexp
공식 코드MAexp: A Generic Platform for RL-based Multi-Agent Exploration
https://github.com/duanzhiihao/lossy-vae
공식 코드https://github.com/ducdauge/sft-llm
공식 코드https://github.com/dvmazur/mixtral-offloading
공식 코드Fast Inference of Mixture-of-Experts Language Models with Offloading
https://github.com/eai-lab/transpl
공식 코드https://github.com/ecolab-postech/nipq
공식 코드https://github.com/ecolab-postech/owq
공식 코드https://github.com/edmav4/biper
공식 코드https://github.com/eduardacaldeira/compression_bias_survey
공식 코드Model Compression Techniques in Biometrics Applications: A Survey
https://github.com/eduardgorbunov/ef_sigma_k
공식 코드https://github.com/edwintsalcedo/cubital
공식 코드Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital Fossa
https://github.com/efeslab/atom
공식 코드Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
https://github.com/efficient-ml/qwen3-quantization
공식 코드https://github.com/efsotr/NeUQI
공식 코드NeUQI: Near-Optimal Uniform Quantization Parameter Initialization
https://github.com/ehaleva/riq
공식 코드https://github.com/ehw-fit/timeloop-with-quantization
공식 코드Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators
https://github.com/ejaasaari/lorann
공식 코드LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.