Changed things as mentioned in issue 6

[tatp22]

Changed some things in the code as mentioned here: #6

In particular, the following changes should be of note:

• Every nn.Linear instantiation is now replaced by the get_linear function, which returns an nn.Linear with xavier init. This also affects how the E and F matrices were initialized.

• There are no more w_q, w_k, and w_v matrices in the LinearAttentionHead module. Instead, in the MHAttention module, to_{q,k,v} is now a ModuleList, and there are nhead nn.Linear layers in each of them, each corresponding to the original weight matrix in the original paper.

• Fixed a bug where there were still **kwargs in the checkpoint function "C2".