Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Making models smaller and faster: quantization, distillation, pruning, sparsity and kernel-level work.
Signals: quantization, model-compression, pruning, knowledge-distillation, gptq, awq, bitsandbytes, sparsity
187 results
Knowledge distillation methods implemented with Tensorflow (now there are 11 (+1) methods, and will be added more.)
A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.
针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库
A model compression and acceleration toolbox based on pytorch.
More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt
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-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego
Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch
[ICML'21 Oral] I-BERT: Integer-only BERT Quantization
A PyTorch-based model pruning toolkit for pre-trained language models
PaddleSlim is an open-source library for deep model compression and architecture search.
Practical course about Large Language Models.
rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale
[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
yolov3 network slimming剪枝的一种实现
[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation
Official pytorch Implementation of Relational Knowledge Distillation, CVPR 2019
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
24,535 repositories in the index in total.
