Experiments for the blog post "No, We Don't Have to Choose Batch Sizes As Powers Of 2"
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
An implementation of a deep learning recommendation model (DLRM)
Open source implementation of AceNAS: https://arxiv.org/abs/2108.03001
[4-5 FPS / Core m3 CPU only] [11 FPS / Core i7 CPU only] OpenVINO+DeeplabV3+LattePandaAlpha/Lapto...
Home of StarCoder: fine-tuning & inference!
StyleGAN - Official TensorFlow Implementation
My best practice of training large dataset using PyTorch.
Explore training for quantized models
Some preliminary explorations of Mamba's context scaling.
Non-local Neural Networks for Video Classification
PyTorch models and training code for 'Planet: Understanding the Amazon from Space' Kaggle
Adversarially Learned Inference in Pytorch
The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detec...