Created by: suchenzang
Cleanup part... 10? Changes here include:
- removed
set_beam_sizeandreorder_incremental_state_scriptingmethods inincremental_decoder.py - moved
TransformerEncoderandEmbedding(moved to modules/) to separate files, renamedtransformer.py->transformer_decoder.py - deleted unused
model_utils.pyfile - moved ffn and transformer encoder layer to separate files
Used a 125m baseline as a test run to confirm parity.