Function embed

reur and position embeddings :param input_ids: int Tensor of shape [batch_size, seq_length]. :param vocab_size: number of words in vocab :param embedding_size: dimensionality of the embedding :param position_offset: aka number of cached tokens. :param initializer_range: float. Ra

(input_ids,
          vocab_size,
          embedding_size,
          position_offset=0,
          initializer_range=0.02,
          max_position_embeddings=512,
          use_one_hot_embeddings=True)