type annotation lacking/ maybe also add docstrings.

I think micrograd.nn would be easier to understand if the function signatures have type annotation. The backwards compatability of type annotation is limited, but it seems likely very few people will use micrograd with python < 3.8. I'm happy to help with this.

Also docstrings might be helpful for people studying the code.

I followed 'The spelled-out intro to neural networks and backpropagation: building micrograd' on YouTube and am grateful to Andrej for making this. Learned al lot!