This Github Repo contains the supporting Jupyter-notebooks for the Paperspace blog series on PyTorch covering everything from the basic building blocks all the way to building custom architectures. The series has following parts

Blog Post	1-Click Notebook
PyTorch 101 Part 1 - Understanding Computation Graphs and Autograd
PyTorch 101 Part 2 - Building Neural Networks With PyTorch
PyTorch 101 Part 3 - Going Deeper with PyTorch
PyTorch 101 Part 4 - Memory Management and Using Multiple GPUs
PyTorch 101 Part 5 - Understanding Hooks

The notebooks and links for the rest of the parts will be updated as and when they are published.