v2.0.0, update Autograd

• Now Autograd is tape-based, (previously it was fully recursive)
• Bug fixes and optimization
  • Simplify nn.Embedding
  • Simplify autograd reverse_broadcast method
  • Fix where grad_fn method
• Add Seq2Seq Transformer example
• Other
  • Add nn.LogSoftmax
  • Edit nn.Linear bias initialization
  • Оther fixes and improvements

New autograd version enables transformer training, overcoming previous limitations due to slow backpropagation speed.