technical implementation of a Transformer model in Python using PyTorch

by dev

Core Components

Multi-Head Attention

import torch
import torch.nn as nn

class MultiHeadAttention(nn.Module):
    def __init__(self, d_model, num_heads):
        super().__init__()
        self.d_model = d_model
        self.num_heads = num_heads
        self.d_k = d_model // num_heads
        
        self.W_q = nn.Linear(d_model, d_model)
        self.W_k = nn.Linear(d_model, d_model)
        self.W_v = nn.Linear(d_model, d_model)
        self.W_o = nn.Linear(d_model, d_model)

    def scaled_dot_product_attention(self, Q, K, V, mask=None):
        attn_scores = torch.matmul(Q, K.transpose(-2, -1)) / torch.sqrt(torch.tensor(self.d_k))
        if mask is not None:
            attn_scores = attn_scores.masked_fill(mask == 0, -1e9)
        attn_probs = torch.softmax(attn_scores, dim=-1)
        return torch.matmul(attn_probs, V)

    def forward(self, Q, K, V, mask=None):
        batch_size = Q.size(0)
        
        Q = self.W_q(Q).view(batch_size, -1, self.num_heads, self.d_k).transpose(1, 2)
        K = self.W_k(K).view(batch_size, -1, self.num_heads, self.d_k).transpose(1, 2)
        V = self.W_v(V).view(batch_size, -1, self.num_heads, self.d_k).transpose(1, 2)
        
        attn_output = self.scaled_dot_product_attention(Q, K, V, mask)
        attn_output = attn_output.transpose(1, 2).contiguous().view(batch_size, -1, self.d_model)
        
        return self.W_o(attn_output)

Positional Encoding

class PositionalEncoding(nn.Module):
    def __init__(self, d_model, max_seq_len):
        super().__init__()
        position = torch.arange(max_seq_len).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2) * (-math.log(10000.0) / d_model))
        pe = torch.zeros(max_seq_len, d_model)
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        self.register_buffer('pe', pe.unsqueeze(0))

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

Encoder-Decoder Architecture

Transformer Block

class TransformerBlock(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout=0.1):
        super().__init__()
        self.attention = MultiHeadAttention(d_model, num_heads)
        self.norm1 = nn.LayerNorm(d_model)
        self.ffn = nn.Sequential(
            nn.Linear(d_model, d_ff),
            nn.ReLU(),
            nn.Linear(d_ff, d_model)
        )
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x, mask=None):
        attn_output = self.attention(x, x, x, mask)
        x = self.norm1(x + self.dropout(attn_output))
        ffn_output = self.ffn(x)
        x = self.norm2(x + self.dropout(ffn_output))
        return x

Full Transformer