import math
import torch
import torch.nn as nn

class TransformerModel(nn.Module):
    def __init__(self, vocab_size, d_model, nhead, num_encoder_layers, num_decoder_layers, dim_feedforward, dropout=0.1):
        super(TransformerModel, self).__init__()
        self.model_type = 'Transformer'
        self.src_mask = None
        self.pos_encoder = PositionalEncoding(d_model, dropout)
        self.encoder = nn.Embedding(vocab_size, d_model)
        self.transformer = nn.Transformer(d_model, nhead, num_encoder_layers, num_decoder_layers, dim_feedforward, dropout)
        self.decoder = nn.Linear(d_model, vocab_size)

    def forward(self, src, tgt, src_mask=None, tgt_mask=None):
        src = self.encoder(src) * math.sqrt(self.d_model)
        src = self.pos_encoder(src)
        tgt = self.encoder(tgt) * math.sqrt(self.d_model)
        tgt = self.pos_encoder(tgt)
        output = self.transformer(src, tgt, src_mask, tgt_mask)
        output = self.decoder(output)
        return output

class PositionalEncoding(nn.Module):
    def __init__(self, d_model, dropout=0.1, max_len=5000):
        super(PositionalEncoding, self).__init__()
        self.dropout = nn.Dropout(p=dropout)

        pe = torch.zeros(max_len, d_model)
        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        pe = pe.unsqueeze(0).transpose(0, 1)
        self.register_buffer('pe', pe)

    def forward(self, x):
        x = x + self.pe[:x.size(0), :]
        return self.dropout(x)