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/mzymzy/paper3-quantized_distillzation
https://github.com/naver/deep-image-retrieval
End-to-end Learning of Deep Visual Representations for Image Retrieval
https://github.com/neonbjb/ocotillo
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/neurosim/DNN_NeuroSim_V2.1
https://github.com/newwhitecheng/compress-all-nn
https://github.com/nii-yamagishilab/project-NN-Pytorch-scripts
Improving LPCNet-based Text-to-Speech with Linear Prediction-structured Mixture Density Network
https://github.com/nlp-en-es/wav2vec2-spanish
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/nowgood/QuantizeCNNModel
Towards Effective Low-bitwidth Convolutional Neural Networks
https://github.com/nvidia/bigvgan
https://github.com/nvidia/ruler
https://github.com/nvidia/tensorrt-model-optimizer
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
https://github.com/nvidia/transformerengine
https://github.com/nvlabs/maskllm
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
https://github.com/nvlabs/queen
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos
https://github.com/nvlabs/vila
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
https://github.com/omarfoq/unsupervised_translator
https://github.com/ondrejmokry/testsignals
https://github.com/open-mmlab/mmrazor
Single Path One-Shot Neural Architecture Search with Uniform Sampling
https://github.com/open-mmlab/mmyolo
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
https://github.com/open3da/ll3da
https://github.com/opengear-project/gear
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
https://github.com/openmedlab/pulse
https://github.com/openmeshlab/meshxl
https://github.com/openvla/openvla
https://github.com/orimeirgit/nestedlatticelut
https://github.com/paper-submission-coder/seminar
https://github.com/paraficial/vae_pancreas_segmentation
U-Net Fixed-Point Quantization for Medical Image Segmentation
https://github.com/park-cheol/ASR-Conformer
https://github.com/parkervg/allrecipes-bert
VideoBERT: A Joint Model for Video and Language Representation Learning
https://github.com/persiaml/persia
https://github.com/phamnam-mta/ConveRT-PolyAI-Vietnamese
ConveRT: Efficient and Accurate Conversational Representations from Transformers
https://github.com/phanxuanphucnd/Arizona-asr
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/phanxuanphucnd/Arizona-spotting
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/phanxuanphucnd/wav2asr
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
https://github.com/pie33000/OpenVLA
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.