#model-compression Repositories
Discover 35 active open source GitHub repositories tagged with #model-compression, accumulating 63,829 total stars (averaging 1,823 stars per project). Leading this topic is z1069614715/objectdetection_script with 7,353 stars.
35 repositories total
Some scripts for object detection and code with improvement ideas; please see readme.md for details.
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
micronet, a model compression and deploy lib. compression: 1ใquantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)ใLow-Bit(โค2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2ใ pruning: normalใregular and group convolutional channel pruning; 3ใ group convolution structure; 4ใbatch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/in
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
GigaModels: A Comprehensive Repository and Platform for Multi-modal, Generative, and Perceptual Models
Collection of recent methods on (deep) neural network compression and acceleration.
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+.
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".
List of papers related to neural network quantization in recent AI conferences and journals.
ControlLoRA: A Lightweight Neural Network To Control Stable Diffusion Spatial Information
Summary, Code for Deep Neural Network Quantization
[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
Awesome machine learning model compression research papers, quantization, tools, and learning material.
Frequently Asked Questions
What is the most popular #model-compression repository on GitHub?
The top ranked open source #model-compression project on GitHub is z1069614715/objectdetection_script with 7,353 stars. Some scripts for object detection and code with improvement ideas; please see readme.md for details.
Which programming languages are most used in #model-compression repositories?
Among the top ranked #model-compression projects on GitHub, the most common programming languages are Python, Jupyter Notebook.
How is the #model-compression repository ranking calculated?
We track 35 active open source repositories tagged with #model-compression (500+ stars), totaling 63,829 stars with an average of 1,823 stars per repository. Rankings update daily from the GitHub API.