nathanhubens
Follow
Lists (1)
Stars
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
👀 Apply YOLOv8 exported with ONNX or TensorRT(FP16, INT8) to the Real-time camera
FasterAI: Prune and Distill your models with FastAI and PyTorch
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
Efficient computing methods developed by Huawei Noah's Ark Lab
TedNet: A Pytorch Toolkit for Tensor Decomposition Networks
A model compression and acceleration toolbox based on pytorch.
A custom PyTorch layer that is capable of implementing extremely wide and sparse linear layers efficiently
Train fastai models faster (and other useful tools)
A prize winning solution for DFDC challenge
Easily benchmark PyTorch model FLOPs, latency, throughput, allocated gpu memory and energy consumption
Neural Networks: Zero to Hero
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
A Finder extension for changing folder colors
A library to inspect and extract intermediate layers of PyTorch models.
Simplification of pruned models for accelerated inference | SoftwareX https://doi.org/10.1016/j.softx.2021.100907
Development repository for the Triton language and compiler
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
Repository showing the basics to register, plot and create a first database with the Unicorn Hybrid Black EEG recorder in python.
FFCV: Fast Forward Computer Vision (and other ML workloads!)
Track emissions from Compute and recommend ways to reduce their impact on the environment.
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gan…
Eliminates delay when activating caps lock on macOS OSX
Pytorch implementation of various Knowledge Distillation (KD) methods.