8000

#

model-pruning

Here are 45 public repositories matching this topic...

sentinel-ai

CambrianTech / sentinel-ai

Sentinel-AI is a neuroscience-inspired transformer that dynamically prunes and regrows attention heads. Guided by controller feedback and entropy-based pruning, it self-optimizes through biologically informed cycles—compressing, adapting, and evolving its architecture over time.

pytorch unet model-pruning colab-notebook transformer-architecture huggingface adaptive-transformers neural-network-controller forge-alloy

Updated Apr 9, 2026
Python

peremartra / optipfair

Structured pruning and bias visualization for Large Language Models. Tools for LLM optimization and fairness analysis.

python transformers fairness model-pruning bias-detection structured-pruning bias-mitigation activation-analysis large-language-models llm

Updated Apr 5, 2026
Python

Franzabner / attention-head-surgery-epi

Removing Attention Heads: Does the Energy Actually Drop or Do Remaining Heads Compensate? Dual-stream correlation of PyTorch timing hooks and epi-meter power traces on Pi 5 cluster.

raspberry-pi transformer energy-efficiency model-pruning epi power-measurement ai-research attention-heads

Updated Mar 29, 2026
Python

Franzabner / expert-pruning-epi

Dropping MoE Experts and Measuring Energy Per Intelligence: Where Is the Efficient Operating Point? Expert pruning on Qwen3-30B-A3B measured by EPI on Pi 5 cluster.

raspberry-pi energy-efficiency model-pruning epi ai-research mixture-of-experts llm qwen

Updated Mar 29, 2026
Python

Bhabesh-Rath / local-inventory-ai

A three day challenge to rapidly prototype a local inventory app that integrates a pruned AI model that runs on mid range devices.

android dart computer-vision mobile-app sqlite-android flutter model-pruning tflite edge-ai on-device-ml on-device-ai mobilenetv4

Updated Mar 28, 2026
Python

entangelk / Q-PSA_Pr

A framework for analyzing Large Language Model (LLM) performance through Quantized PSA and structured weight pruning experiments

quantization bert model-pruning model-compression perplexity llm-analysis

Updated Mar 26, 2026
Python

ZhngQ1 / TAP-ViTs

Task-adaptive pruning framework for deploying Vision Transformers on heterogeneous edge devices without accessing private data (arXiv 2601.02437)

model-pruning privacy-preserving federated-learning edge-deployment on-device-ai vision-transformer

Updated Mar 11, 2026
Python

onnx / neural-compressor

Model compression for ONNX

deep-learning quantization model-pruning model-compression onnx onnxruntime

Updated Mar 1, 2026
Python

datawhalechina / awesome-compression

模型压缩的小白入门教程，PDF下载地址 https://github.com/datawhalechina/awesome-compression/releases

compression quantization svd knowledge-distillation model-pruning prune model-compression neural-architecture-search kd model-quantization low-rank-matrix-decomposition

Updated Nov 25, 2025

TheodorePTP / model_compression_action

模型压缩的技术文档与项目实践

knowledge-distillation model-pruning model-compression model-quantization

Updated Nov 25, 2025
Python

JasonSloan / DeepFusion

A ready-to-use notebook!

computer-vision deep-learning yolo object-detection model-pruning model-deployment model-training

Updated Oct 24, 2025
C++

czg1225 / SlimSAM

[NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim

knowledge-distillation model-pruning model-compression segment-anything-model

Updated Sep 27, 2025
Python

shahzadmustafa15 / DecisionTreeClassifier

Decision Tree Classifier on Social Network Ads dataset with pruning for improved performance.

python machine-learning scikit-learn classification decision-trees decision-tree model-evaluation model-pruning user-behaviour social-network-ads

Updated Sep 18, 2025
Jupyter Notebook

julianscher / SLTN-GA

Genetic algorithm framework for identifying strong lottery ticket networks in randomly initialized neural networks — features YAML-based configuration, works with any model architecture, and is easily extendable with new genetic operators.

deep-learning genetic-algorithm model-pruning lottery-ticket-hypothesis

Updated Aug 13, 2025
Python

wish44165 / Optimizing-Facial-Landmark-Estimation-for-Embedded-Systems

< 10BC0 a href="/login?return_to=%2Fwish44165%2FOptimizing-Facial-Landmark-Estimation-for-Embedded-Systems" rel="nofollow" data-hydro-click="{"event_type":"authentication.click","payload":{"location_in_page":"star button","repository_id":752912136,"auth_type":"LOG_IN","originating_url":"https://github.com/topics/model-pruning?o=desc&s=updated","user_id":null}}" data-hydro-click-hmac="e3134e1be559e56bf19b828a6750ca4abf9bc8de37a0990b3b96e14ac74e8052" aria-label="You must be signed in to star a repository" data-view-component="true" class="tooltipped tooltipped-sw btn-sm btn color-bg-default"> Star

🔥 IEEE 2024 (Niagara Falls, Canada) - ICME Grand Challenges 🥈

python competition optimization pytorch model-pruning embedded-system tensorflow-lite facial-landmark-detection grand-challenge icme2024 iterative-autolabeling

Updated Jun 6, 2025
Python

uglyghost / FedOBP

FedOBP: Federated Optimal Brain Personalization with Few Personalized Parameters

optimal-brain-damage model-pruning federated-learning

Updated Jan 30, 2025
Python

JasonSloan / yolov8-prune

Yolov8-pruning based on constraint of BN layer gamma values.

model-pruning l1-regularization model-sparsity yolov8-pruning

Updated Dec 31, 2024
Python

zeyneddinoz / subMFL

subMFL: Compatible subModel Generation for Federated Learning in Device Heterogeneous Environment

model-pruning model-compression edge-computing resource-constrained-ml federated-learning distributed-learning mobile-edge-agent ondeviceai edge-intelligence decentralized-learning model-personalization statistical-heterogeneity trustworthy-ai model-generalization resource-constrained-devices heterogeneous-environment

Updated Dec 30, 2024
Jupyter Notebook

llama-pruning

MedITSolutionsKurman / llama-pruning

This project provides tools to load and prune large language models using a structured pruning method.

ai pruning slm model-pruning pruning-algorithms llm

Updated Dec 2, 2024
Python

OpenNLG / OpenBA-v2

OpenBA-V2: 3B LLM (Large Language Model) with T5 architecture, utilizing model pruning technique and continuing pretraining from OpenBA-15B.

model-pruning model-compression train-from-scratch llm

Updated May 10, 2024
Python

Improve this page

Add a description, image, and links to the model-pruning topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the model-pruning topic, visit your repo's landing page and select "manage topics."

0