File size: 932 Bytes
38e2dac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Source: https://github.com/karpathy/nanoGPT/blob/master/model.py
"""
from torch import nn

from models.attention import CausalSelfAttention
from models.decoder_ffn import FFNN


class DecoderBlock(nn.Module):
    def __init__(
        self,
        d,
        H,
        T,
        bias=False,
        dropout=0.2,
    ):
        """
        Arguments:
        d: size of embedding dimension
        H: number of attention heads
        T: maximum length of input sequences (in tokens)
        bias: whether or not to use bias in linear layers
        dropout: probability of dropout
        """
        super().__init__()
        self.ln_1 = nn.LayerNorm(d)
        self.attn = CausalSelfAttention(d, H, T, bias, dropout)
        self.ln_2 = nn.LayerNorm(d)
        self.ffnn = FFNN(d, bias, dropout)


    def forward(self, x):
        x = x + self.attn(self.ln_1(x))
        x = x + self.ffnn(self.ln_2(x))
        return x