torch实现transformer

deepseek的回答：

当然可以！下面是一个使用 PyTorch 实现 Transformer 的简单版本。这个实现包括 Transformer 的核心组件：多头自注意力机制、位置编码、前馈神经网络等。

1. 导入必要的库

import torch
import torch.nn as nn
import torch.nn.functional as F
import math

2. 实现位置编码

位置编码用于为输入序列中的每个位置添加位置信息。

class PositionalEncoding(nn.Module):
    def __init__(self, d_model, max_len=5000):
        super(PositionalEncoding, self).__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)

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

3. 实现多头自注意力机制

class MultiHeadAttention(nn.Module):
    def __init__(self, d_model, num_heads):
        super(MultiHeadAttention, self).__init__()
        assert d_model % num_heads == 0, "d_model must be divisible by num_heads"
        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 forward(self, q, k, v, mask=None):
        batch_size = q.size(0)

        # Linear projections
        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)

        # Scaled Dot-Product Attention
        scores = torch.matmul(q, k.transpose(-2, -1)) / math.sqrt(self.d_k)
        if mask is not None:
            scores = scores.masked_fill(mask == 0, -1e9)
        attn = F.softmax(scores, dim=-1)
        output = torch.matmul(attn, v)

        # Concatenate heads
        output = output.transpose(1, 2).contiguous().view(batch_size, -1, self.d_model)

        # Final linear projection
        output = self.W_o(output)
        return output

4. 实现前馈神经网络

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

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

5. 实现 Transformer 编码器层

class EncoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout=0.1):
        super(EncoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = FeedForward(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=None):
        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

6. 实现 Transformer 编码器

class Encoder(nn.Module):
    def __init__(self, num_layers, d_model, num_heads, d_ff, dropout=0.1):
        super(Encoder, self).__init__()
        self.layers = nn.ModuleList([EncoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])
        self.norm = nn.LayerNorm(d_model)

    def forward(self, x, mask=None):
        for layer in self.layers:
            x = layer(x, mask)
        return self.norm(x)

7. 实现 Transformer 解码器层

class DecoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout=0.1):
        super(DecoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.cross_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = FeedForward(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=None, tgt_mask=None):
        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

8. 实现 Transformer 解码器

class Decoder(nn.Module):
    def __init__(self, num_layers, d_model, num_heads, d_ff, dropout=0.1):
        super(Decoder, self).__init__()
        self.layers = nn.ModuleList([DecoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])
        self.norm = nn.LayerNorm(d_model)

    def forward(self, x, enc_output, src_mask=None, tgt_mask=None):
        for layer in self.layers:
            x = layer(x, enc_output, src_mask, tgt_mask)
        return self.norm(x)

9. 实现完整的 Transformer 模型

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=0.1):
        super(Transformer, self).__init__()
        self.encoder_embedding = nn.Embedding(src_vocab_size, d_model)
        self.decoder_embedding = nn.Embedding(tgt_vocab_size, d_model)
        self.positional_encoding = PositionalEncoding(d_model, max_seq_length)

        self.encoder = Encoder(num_layers, d_model, num_heads, d_ff, dropout)
        self.decoder = Decoder(num_layers, d_model, num_heads, d_ff, dropout)

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

    def forward(self, src, tgt, src_mask=None, tgt_mask=None):
        src_embedded = self.dropout(self.positional_encoding(self.encoder_embedding(src)))
        tgt_embedded = self.dropout(self.positional_encoding(self.decoder_embedding(tgt)))

        enc_output = self.encoder(src_embedded, src_mask)
        dec_output = self.decoder(tgt_embedded, enc_output, src_mask, tgt_mask)

        output = self.fc_out(dec_output)
        return output

10. 使用示例

# 假设词汇表大小为 10000，模型维度为 512，8 个头，6 层，前馈网络维度为 2048，最大序列长度为 100
model = Transformer(src_vocab_size=10000, tgt_vocab_size=10000, d_model=512, num_heads=8, num_layers=6, d_ff=2048, max_seq_length=100)

# 假设输入序列长度为 10，批量大小为 32
src = torch.randint(0, 10000, (32, 10))
tgt = torch.randint(0, 10000, (32, 10))

# 前向传播
output = model(src, tgt)
print(output.shape)  # 输出形状为 (32, 10, 10000)

总结

这个实现是一个简化的 Transformer 模型，包含了编码器和解码器的核心组件。你可以根据需要进一步扩展和优化这个模型，例如添加更多的层、调整超参数、实现更复杂的注意力机制等。

之前冲浪的时候看到两个还行的库：

https://github.com/jingyaogong/minimind

https://github.com/jingyaogong/minimind-v