def __init__(self, langpair: str, is_base: bool = True) -> None:
super().__init__()
configs = Config()
configs.add_tokenizer(langpair)
configs.add_model(is_base)
dim_model: int = configs.model.model_params.dim_model
vocab_size = configs.tokenizer.vocab_size
self.encoder = Encoder(langpair)
self.decoder = Decoder(langpair)
self.linear = nn.Linear(dim_model, vocab_size)
def __init__(self, langpair: str, is_base: bool = True) -> None:
super().__init__()
# TODO: support transformer-base and transformer-big
configs = Config()
configs.add_model(is_base)
configs.add_tokenizer(langpair)
tokenizer = load_tokenizer(langpair)
padding_idx = tokenizer.token_to_id("<pad>")
self.dim_model: int = configs.model.model_params.dim_model
self.vocab_size = configs.tokenizer.vocab_size
self.embedding_matrix = nn.Embedding(self.vocab_size,
self.dim_model,
padding_idx=padding_idx)
self.scale = self.dim_model**0.5
self.max_len = configs.model.model_params.max_len
self.positional_encoding = PositionalEncoding(self.max_len,
self.dim_model)
