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/hkuds/recgpt
공식 코드https://github.com/hoangnguyenm/bridle
공식 코드BRIDLE: Generalized Self-supervised Learning with Quantization
https://github.com/honee-w/flowse
공식 코드FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
https://github.com/hossein1387/U-Net-Fixed-Point-Quantization-for-Medical-Image-Segmentation
공식 코드U-Net Fixed-Point Quantization for Medical Image Segmentation
https://github.com/hou-yz/color_distillation
공식 코드https://github.com/houlu369/Loss-aware-weight-quantization
공식 코드https://github.com/hpi-xnor/BMXNet-v2
공식 코드https://github.com/hpi-xnor/bnext
공식 코드Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket
https://github.com/hqythu/bit-rnn
공식 코드Effective Quantization Methods for Recurrent Neural Networks
https://github.com/hsu1023/duquant
공식 코드DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
https://github.com/htqin/IR-Net
공식 코드Forward and Backward Information Retention for Accurate Binary Neural Networks
https://github.com/htqin/awesome-model-quantization
공식 코드https://github.com/htqin/dsg
공식 코드Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
https://github.com/htqin/ir-qlora
공식 코드Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
https://github.com/huangdiudiu/eqv
공식 코드https://github.com/huangowen/qat-acs
공식 코드Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
https://github.com/huangowen/quantization-variation
공식 코드Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
https://github.com/huangowen/rolora
공식 코드RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
https://github.com/huangowen/vvtq
공식 코드Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
https://github.com/huangyuxiang03/Locret
공식 코드https://github.com/huanpengchu/qncd
공식 코드https://github.com/huawei-noah/Efficient-Computing/tree/master/BinaryNetworks/AdaBin
공식 코드AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
https://github.com/huawei-noah/Pretrained-Language-Model
공식 코드https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/TernaryBERT
공식 코드https://github.com/huawei-noah/noah-research/tree/master/S3-Training
공식 코드DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization
https://github.com/hubertsiuzdak/snac
공식 코드https://github.com/huggingface/diffusers
공식 코드BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
https://github.com/huggingface/transformers
공식 코드Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
https://github.com/huggingface/transformers/tree/master/src/transformers/models/ibert
공식 코드https://github.com/hugozhl/mevi
공식 코드https://github.com/hui-po-wang/LM-GC
공식 코드https://github.com/huqinghao/palquant
공식 코드PalQuant: Accelerating High-precision Networks on Low-precision Accelerators
https://github.com/hustvl/pd-quant
공식 코드PD-Quant: Post-Training Quantization based on Prediction Difference Metric
https://github.com/huyz2023/2by4-pretrain
공식 코드S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
https://github.com/hvoss-techfak/AQGT
공식 코드AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.