Search Results - RepositoryStats

2.9k

13.8k

other

282

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

cnn gan rnn bert chatgpt pruning tutorial diffusion transformer deep-learning leedl-tutorial self-attention machine-learning transfer-learning network-compression reinforcement-learning

Created 2019-07-02

582 commits to master branch, last one 9 days ago

distiller IntelLabs

801

4.4k

apache-2.0

132

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

onnx pruning pytorch early-exit group-lasso distillation quantization truncated-svd regularization jupyter-notebook pruning-structures network-compression deep-neural-networks automl-for-compression

This repository has been archived (exclude archived)

Created 2018-04-24

643 commits to master branch, last one about a year ago

deepsparse neuralmagic

173

3.0k

other

57

Sparsity-aware deep learning inference runtime for CPUs

nlp cpus onnx pruning inference deepsparse performance quantization llm-inference sparsification computer-vision machinelearning object-detection pretrained-models

Created 2020-12-14

1,052 commits to main branch, last one 4 months ago

Torch-Pruning VainF

335

2.7k

mit

37

[CVPR 2023] DepGraph: Towards Any Structural Pruning

pruning cvpr2023 depgraph channel-pruning network-pruning model-compression structural-pruning structured-pruning efficient-deep-learning

Created 2019-12-15

1,442 commits to master branch, last one a day ago

Awesome-Pruning he-y

330

2.4k

unknown

88

A curated list of neural network pruning resources.

pruning awesome-list model-compression model-acceleration

Created 2019-05-30

61 commits to master branch, last one 7 months ago

neural-compressor intel

257

2.2k

apache-2.0

33

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

awq fp4 gptq int4 int8 pruning mxformat sparsity sparsegpt auto-tuning smoothquant quantization low-precision large-language-models knowledge-distillation post-training-quantization quantization-aware-training

Created 2020-07-21

3,619 commits to master branch, last one a day ago

micronet 666DZY666

478

2.2k

mit

41

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Ari...

Created 2019-12-04

295 commits to master branch, last one 3 years ago

aimet quic

383

2.2k

other

49

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

auto-ml pruning opensource compression open-source quantization deep-learning machine-learning network-compression deep-neural-networks network-quantization

Created 2020-04-21

2,289 commits to develop branch, last one a day ago

sparseml neuralmagic

148

2.1k

apache-2.0

49

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

nlp onnx keras automl pruning pytorch sparsity tensorflow smaller-models sparsification object-detection transfer-learning pruning-algorithms deep-learning-models image-classification deep-learning-library sparsification-recipes deep-learning-algorithms computer-vision-algorithms

Created 2020-12-11

1,826 commits to main branch, last one 4 months ago

PaddleSlim PaddlePaddle

345

1.6k

apache-2.0

91

PaddleSlim is an open-source library for deep model compression and architecture search.

nas bert ernie yolov5 yolov6 yolov7 pruning sparsity tensorrt detection compression transformer distillation quantization segmentation

Created 2019-12-16

1,245 commits to develop branch, last one a day ago

model-optimization tensorflow

323

1.5k

apache-2.0

120

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

ml keras pruning sparsity tensorflow compression optimization quantization deep-learning machine-learning model-compression quantized-networks quantized-training quantized-neural-networks

Created 2018-10-31

833 commits to master branch, last one 17 days ago

mmrazor open-mmlab

229

1.5k

apache-2.0

20

OpenMMLab Model Compression Toolbox and Benchmark.

nas spos darts pruning pytorch autoslim detection quantization segmentation classification knowledge-distillation

Created 2021-12-22

229 commits to main branch, last one about a year ago

autorestic cupcakearmy

72

1.3k

apache-2.0

11

Config driven, easy backup cli for restic.

cli backup config restic pruning incremental config-driven deduplication incremental-backup

Created 2019-06-20

541 commits to master branch, last one 6 days ago

Efficient-Computing huawei-noah

210

1.2k

unknown

24

Efficient computing methods developed by Huawei Noah's Ark Lab

pruning quantization self-supervised model-compression binary-neural-networks knowledge-distillation

Created 2019-09-04

157 commits to master branch, last one 15 days ago

nncf openvinotoolkit

234

943

apache-2.0

31

Neural Network Compression Framework for enhanced OpenVINO™ inference

nlp bert hawq onnx pruning pytorch openvino sparsity tensorflow compression mmdetection quantization transformers deep-learning classification object-detection semantic-segmentation mixed-precision-training quantization-aware-training

Created 2020-05-13

2,293 commits to develop branch, last one 21 hours ago

LLM-Pruner horseee

104

876

apache-2.0

10

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

llm bloom llama llama3 vicuna chatglm llama-2 pruning baichuan compression neurips-2023 language-model pruning-algorithms

Created 2023-05-17

165 commits to main branch, last one about a month ago

pytorch-pruning jacobgil

202

875

unknown

22

PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference

pruning pytorch deep-learning

Created 2017-06-23

6 commits to master branch, last one 5 years ago

mobile-yolov5-pruning-distillation Syencil

163

825

mit

9

mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！

ncnn yolov5 pruning distillation mobile-yolov5s

Created 2020-09-07

17 commits to master branch, last one 3 years ago

TinyNeuralNetwork alibaba

116

754

mit

21

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

pruning pytorch deep-learning model-converter model-compression deep-neural-networks post-training-quantization quantization-aware-training

Created 2021-11-02

816 commits to main branch, last one 28 days ago

awesome-emdl csarron

166

741

mit

84

Embedded and mobile deep learning research resources

pruning inference mobile-ai embedded-ai quantization deep-learning mobile-inference deep-neural-networks mobile-deep-learning efficient-neural-networks neural-network-compression

Created 2017-06-06

60 commits to master branch, last one about a year ago

KD_Lib SforAiDl

58

608

mit

16

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

pruning pytorch benchmarking data-science quantization machine-learning model-compression deep-learning-library knowledge-distillation algorithm-implementations

Created 2020-05-10

298 commits to master branch, last one about a year ago

filter-pruning-geometric-median he-y

112

593

unknown

8

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)

pruning pytorch model-compression

Created 2019-03-26

19 commits to master branch, last one about a year ago

LLM-Shearing princeton-nlp

47

560

mit

23

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

llm nlp llama llama2 pruning efficiency pre-training

Created 2023-10-16

71 commits to main branch, last one 8 months ago

awesome-ml-model-compression cedrickchee

64

491

mit

23

Awesome machine learning model compression research papers, quantization, tools, and learning material.

pruning awesome-list quantization neural-networks machine-learning model-compression

Created 2018-12-06

41 commits to master branch, last one 2 months ago

YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone SpursLipu

136

445

gpl-3.0

8

YOLO ModelCompression MultidatasetTraining

yolo pruning mobilenetv3 multidataset modelcompression object-detection quantization-aware-training

Created 2019-12-24

438 commits to master branch, last one 2 years ago

optimum-intel huggingface

112

410

apache-2.0

38

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

onnx intel pruning openvino diffusers inference distillation optimization quantization transformers

Created 2022-05-25

942 commits to main branch, last one 20 hours ago

keras-surgeon BenWhetton

108

405

other

17

Pruning and other network surgery for trained Keras models.

keras pruning deep-learning network-surgery

Created 2017-08-22

80 commits to master branch, last one 3 years ago

TextPruner airaria

33

372

apache-2.0

5

A PyTorch-based model pruning toolkit for pre-trained language models

pruning transformer model-pruning pre-trained-language-models

Created 2021-07-20

42 commits to main branch, last one about a year ago

sparsezoo neuralmagic

25

370

apache-2.0

25

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

nlp yolo resnet pruning mobilenet quantization smaller-models computer-vision models-optimized pretrained-models transfer-learning deep-learning-models sparsification-recipe object-detection-model sparse-quantized-models deep-learning-algorithms

Created 2020-12-11

301 commits to main branch, last one 4 months ago

Sparsebit megvii-research

40

327

apache-2.0

12

A model compression and acceleration toolbox based on pytorch.

sparse pruning tensorrt quantization deep-learning post-training-quantization quantization-aware-training

Created 2022-07-21

134 commits to main branch, last one about a year ago