import torch
import torch.nn as nn
import math

class PositionalEncoding(nn.Module):
    def __init__(self, d_model, max_len=5000):
        super().__init__()
        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)
        self.register_buffer('pe', pe, persistent=False)

    def forward(self, x):
        x = x + self.pe[:, :x.size(1)]
        return x

class TransformerModel(nn.Module):
    def __init__(self, ntoken, d_model, nhead, num_layers, dropout=0.0):
        super().__init__()
        self.model_type = 'Transformer'
        self.pos_encoder = PositionalEncoding(d_model)
        encoder_layers = nn.TransformerEncoderLayer(d_model, nhead, batch_first=True, dropout=dropout, dim_feedforward=128)
        self.transformer_encoder = nn.TransformerEncoder(encoder_layers, num_layers)
        self.embedding = nn.Embedding(ntoken, d_model)
        self.d_model = d_model
        self.linear = nn.Linear(d_model, ntoken)

    def forward(self, src, src_mask=None):
        src = self.embedding(src) * math.sqrt(self.d_model)
        src = self.pos_encoder(src)
        output = self.transformer_encoder(src, src_key_padding_mask=src_mask)
        return output