import torch.nn as nn
import torch

vocab_size = tokenizer.vocab_size
d_model = 256
n_segments = 2

class Embedding(nn.Module):
    def __init__(self):
        super(Embedding, self).__init__()
        self.tok_embed = nn.Embedding(vocab_size, d_model)  # token embedding
        self.pos_embed = nn.Embedding(max_input_length, d_model)  # position embedding
        self.seg_embed = nn.Embedding(n_segments, d_model)  # segment(token type) embedding
        self.norm = nn.LayerNorm(d_model)

    def forward(self, x, seg):
        seq_len = x.size(1)
        pos = torch.arange(seq_len, dtype=torch.long).to(device)
        pos = pos.unsqueeze(0).expand_as(x)  # (seq_len,) -> (batch_size, seq_len)
        embedding = self.tok_embed(x) + self.pos_embed(pos) + self.seg_embed(seg)
        return self.norm(embedding)

e = Embedding()
e.to(device)