#大语言模型#《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
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
#自然语言处理#Sparsity-aware deep learning inference runtime for CPUs
[CVPR 2023] DepGraph: Towards Any Structural Pruning
#Awesome#A curated list of neural network pruning resources.
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
#计算机科学#AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
翻译 - AIMET是一个为经过训练的神经网络模型提供高级量化和压缩技术的库。
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...
翻译 - 基于pytorch的模型压缩(1,量化:8/4 / 2bits(dorefa),三进制/二进制值(twn / bnn / xnornet); 2,修剪:常规,常规和组卷积通道修剪; 3,组卷积结构; 4,特征(A)的二进制值的分批归一化折叠)
#自然语言处理#Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
翻译 - 使用几行代码将稀疏化配方应用于神经网络的库,实现更快和更小的模型
PaddleSlim is an open-source library for deep model compression and architecture search.
翻译 - PaddleSlim是一个用于深度模型压缩和体系结构搜索的开源库。
OpenMMLab Model Compression Toolbox and Benchmark.
翻译 - OpenMMLab 模型压缩工具箱和基准。
#计算机科学#A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
翻译 - 新手和高级用户都可以使用一套工具来优化机器学习模型以进行部署和执行。
Config driven, easy backup cli for restic.
Efficient computing methods developed by Huawei Noah's Ark Lab
#自然语言处理#Neural Network Compression Framework for enhanced OpenVINO™ inference
#大语言模型#[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.
#计算机科学#PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference
mobilev2-yolov5s剪枝、蒸馏,支持ncnn,tensorRT部署。ultra-light but better performence!
#计算机科学#TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
#计算机科学#Embedded and mobile deep learning research resources