Add Transformer implementation and text.py

Fix learning rate scaling bug

this bug is quite peculiar and hard to track down, when learning rate for a
parameter is scaled via param_attr and learning rate schedulers are used,
`append_optimizer_op` will error out complaining `LearningRate` input is null

turns out learning rate scaling is done in `_create_param_lr`, which basically
add a scale op, the problem is: it is appended to `orig_prog` (since
`global_learning_rate()` variable is in it), therefore the resulting scaled
learning rate variable can not be found in `train_prog`.

the reason it works previously w/o lr scaling is this:
`clone()` will create a variable with the same name as the
`global_learning_rate()` variable, which will be used in `append_optimizer_op`

Add bmn model

Add models api

Reorganize data from data_loader into inputs and labels.

add evaluate and predict for model

remove init_context