YOLO ModelCompression MultidatasetTraining
-
Updated
Jun 21, 2022 - Python
YOLO ModelCompression MultidatasetTraining
Official code of "Forget the Data and Fine-Tuning! Just Fold the Network to Compress" @ ICLR 2025
Code for paper: Weight-Inherited Distillation for Task-Agnostic BERT Compression
[EMNLP'25] The official PyTorch implementation for "GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression"
High-performance MNIST Engine built from scratch in NumPy. Features 8-bit quantization (92.5% size reduction) and a real-time Streamlit dashboard.
Content-addressable tensor memory for efficient, exact, and fault-tolerant checkpoint storage.
Small models you can actually trust on the edge.
To associate your repository with the modelcompression topic, visit your repo's landing page and select "manage topics."