Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Structured Neuron Level Pruning to compress Transformer-based models [ECCV'24]

A library for training, compressing and deploying computer vision models (including ViT) with edge devices

The official NetsPresso Python package.

Compressed LLMs for Efficient Text Generation [ICLR'24 Workshop]

A 28× Compressed Wav2Lip for Efficient Talking Face Generation [ICCV'23 Demo] [MLSys'23 Workshop] [NVIDIA GTC'23]

A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ECCV'24]

An open software package dedicated for the development of Brain-Computer Interfaces with various advanced pattern recognition algorithms

Model Zoo for NetsPresso Compressor