File size: 7,071 Bytes
f630b1b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8063ed9
f630b1b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
import os
import yaml
import torch
import torch.nn as nn
import torch.optim as optim
import torch.utils.data as data
import math
import copy

class MultiHeadAttention(nn.Module):
    def __init__(self, d_model, num_heads):
        super(MultiHeadAttention, self).__init__()
        # Ensure that the model dimension (d_model) is divisible by the number of heads
        assert d_model % num_heads == 0, "d_model must be divisible by num_heads"
        
        # Initialize dimensions
        self.d_model = d_model # Model's dimension
        self.num_heads = num_heads # Number of attention heads
        self.d_k = d_model // num_heads # Dimension of each head's key, query, and value
        
        # Linear layers for transforming inputs
        self.W_q = nn.Linear(d_model, d_model) # Query transformation
        self.W_k = nn.Linear(d_model, d_model) # Key transformation
        self.W_v = nn.Linear(d_model, d_model) # Value transformation
        self.W_o = nn.Linear(d_model, d_model) # Output transformation
        
    def scaled_dot_product_attention(self, Q, K, V, mask=None):
        # Calculate attention scores
        attn_scores = torch.matmul(Q, K.transpose(-2, -1)) / math.sqrt(self.d_k)
        
        # Apply mask if provided (useful for preventing attention to certain parts like padding)
        if mask is not None:
            attn_scores = attn_scores.masked_fill(mask == 0, -1e4) # LS: CHANGED FROM -1e9 FOR quantization
        
        # Softmax is applied to obtain attention probabilities
        attn_probs = torch.softmax(attn_scores, dim=-1)
        
        # Multiply by values to obtain the final output
        output = torch.matmul(attn_probs, V)
        return output
        
    def split_heads(self, x):
        # Reshape the input to have num_heads for multi-head attention
        batch_size, seq_length, d_model = x.size()
        return x.view(batch_size, seq_length, self.num_heads, self.d_k).transpose(1, 2)
        
    def combine_heads(self, x):
        # Combine the multiple heads back to original shape
        batch_size, _, seq_length, d_k = x.size()
        return x.transpose(1, 2).contiguous().view(batch_size, seq_length, self.d_model)
        
    def forward(self, Q, K, V, mask=None):
        # Apply linear transformations and split heads
        Q = self.split_heads(self.W_q(Q))
        K = self.split_heads(self.W_k(K))
        V = self.split_heads(self.W_v(V))
        
        # Perform scaled dot-product attention
        attn_output = self.scaled_dot_product_attention(Q, K, V, mask)
        
        # Combine heads and apply output transformation
        output = self.W_o(self.combine_heads(attn_output))
        return output
    

class PositionWiseFeedForward(nn.Module):
    def __init__(self, d_model, d_ff):
        super(PositionWiseFeedForward, self).__init__()
        self.fc1 = nn.Linear(d_model, d_ff)
        self.fc2 = nn.Linear(d_ff, d_model)
        self.relu = nn.ReLU()

    def forward(self, x):
        return self.fc2(self.relu(self.fc1(x)))
    

class PositionalEncoding(nn.Module):
    def __init__(self, d_model, max_seq_length):
        super(PositionalEncoding, self).__init__()
        
        pe = torch.zeros(max_seq_length, d_model)
        position = torch.arange(0, max_seq_length, 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)
        
        self.register_buffer('pe', pe.unsqueeze(0))
        
    def forward(self, x):
        return x + self.pe[:, :x.size(1)]
    

class EncoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout):
        super(EncoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = PositionWiseFeedForward(d_model, d_ff)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, mask):
        attn_output = self.self_attn(x, x, x, mask)
        x = self.norm1(x + self.dropout(attn_output))
        ff_output = self.feed_forward(x)
        x = self.norm2(x + self.dropout(ff_output))
        return x


class DecoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout):
        super(DecoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.cross_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = PositionWiseFeedForward(d_model, d_ff)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.norm3 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, enc_output, src_mask, tgt_mask):
        attn_output = self.self_attn(x, x, x, tgt_mask)
        x = self.norm1(x + self.dropout(attn_output))
        attn_output = self.cross_attn(x, enc_output, enc_output, src_mask)
        x = self.norm2(x + self.dropout(attn_output))
        ff_output = self.feed_forward(x)
        x = self.norm3(x + self.dropout(ff_output))
        return x
    

class Transformer(nn.Module):
    def __init__(self, src_vocab_size, tgt_vocab_size, d_model, num_heads, num_layers, d_ff, max_seq_length, dropout = 0.05):
        super(Transformer, self).__init__()
        self.encoder_embedding = nn.Embedding(src_vocab_size, d_model,padding_idx=0)
        self.decoder_embedding = nn.Embedding(tgt_vocab_size, d_model,padding_idx=0)
        self.positional_encoding = PositionalEncoding(d_model, max_seq_length)

        self.encoder_layers = nn.ModuleList([EncoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])
        self.decoder_layers = nn.ModuleList([DecoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])

        self.fc = nn.Linear(d_model, tgt_vocab_size)
        self.dropout = nn.Dropout(dropout)

    def generate_mask(self, src, tgt):
        src_mask = (src != 0).unsqueeze(1).unsqueeze(2)
        tgt_mask = (tgt != 0).unsqueeze(1).unsqueeze(3)
        seq_length = tgt.size(1)
        nopeak_mask = (1 - torch.triu(torch.ones(1, seq_length, seq_length,device=tgt.device), diagonal=1)).bool()
        tgt_mask = tgt_mask & nopeak_mask
        return src_mask, tgt_mask

    def forward(self, src, tgt):
        src_mask, tgt_mask = self.generate_mask(src, tgt)
        src_embedded = self.dropout(self.positional_encoding(self.encoder_embedding(src)))
        tgt_embedded = self.dropout(self.positional_encoding(self.decoder_embedding(tgt)))

        enc_output = src_embedded
        for enc_layer in self.encoder_layers:
            enc_output = enc_layer(enc_output, src_mask)

        dec_output = tgt_embedded
        for dec_layer in self.decoder_layers:
            dec_output = dec_layer(dec_output, enc_output, src_mask, tgt_mask)

        output = self.fc(dec_output)
        return output