Variable num could be improved

[dumplingdumpling]

In CausalSelfAttention and GPT classes, the variable num decided by the form of different condtions could be improved using the code below:
num = int(bool(config.num_props)) + ((1 - int(config.lstm)) * config.scaffold_maxlen + int(config.lstm)) * int(config.scaffold)

This could handle all the situations I believe.