LSTM many2many and one2one

Hello, I am new to LSTM. I am currently a bit confused about one2one and many2many. For my understanding, many2many consists of multiple one2one neurons, is this correct? Here is the project I am currently working on, would you please go through the code and check out whether this model is a one2one or many2many, I am so confused about these concepts. The model that I am currently using is a 2-layer LSTM, and I plan to replace this model by a seq2seq model, is this a good choice and what is the main difference between a many2many and a seq2seq?