set `renormalize_logits=True` for better performance (see `transformers` issue #4290)

Adding generation config file(s)

Add TF weights

metadata: add license

Changed num_beams to 4

Update README.md

Update README.md

Update config.json

Update tokenizer_config.json

Update vocab.json

Update README.md

Update config.json

Update tokenizer_config.json

Update vocab.json

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update config.json

Update config.json

Update tokenizer_config.json

Update vocab.json

Update source.spm

Update target.spm

Update config.json

Update pytorch_model.bin

initial commit