gpt_model.py

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

class LayerNorm(nn.Module):
    def __init__(self, emb_dim):
        super().__init__()
        self.eps = 1e-5
        self.scale = nn.Parameter(torch.ones(emb_dim))
        self.shift = nn.Parameter(torch.zeros(emb_dim))

    def forward(self, x):
        mean = x.mean(dim=-1, keepdim=True)
        var = x.var(dim=-1, keepdim=True, unbiased=False)
        norm_x = (x - mean) / torch.sqrt(var + self.eps)
        return self.scale * norm_x + self.shift

class FeedForward(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.layers = nn.Sequential(
            nn.Linear(cfg["emb_dim"], 4 * cfg["emb_dim"]),
            nn.GELU(),
            nn.Linear(4 * cfg["emb_dim"], cfg["emb_dim"]),
        )
    def forward(self, x):
        return self.layers(x)

class MultiHeadAttention(nn.Module):
    def __init__(self, d_in, d_out, context_length, dropout, num_heads, qkv_bias=False):
        super().__init__()
        assert d_out % num_heads == 0, "d_out must be divisible by num_heads"
        self.d_out = d_out
        self.num_heads = num_heads
        self.head_dim = d_out // num_heads

        self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.W_key   = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.out_proj = nn.Linear(d_out, d_out)
        self.dropout = nn.Dropout(dropout)
        self.register_buffer(
            "mask",
            torch.triu(torch.ones(context_length, context_length), diagonal=1).bool()
        )

    def forward(self, x):
        b, num_tokens, _ = x.shape
        keys    = self.W_key(x).view(b, num_tokens, self.num_heads, self.head_dim).transpose(1, 2)
        queries = self.W_query(x).view(b, num_tokens, self.num_heads, self.head_dim).transpose(1, 2)
        values  = self.W_value(x).view(b, num_tokens, self.num_heads, self.head_dim).transpose(1, 2)

        attn_scores = queries @ keys.transpose(2, 3)
        mask = self.mask[:num_tokens, :num_tokens]
        attn_scores.masked_fill_(mask, float("-inf"))
        attn_weights = torch.softmax(attn_scores / (keys.shape[-1] ** 0.5), dim=-1)
        attn_weights = self.dropout(attn_weights)

        context = (attn_weights @ values).transpose(1, 2).contiguous().view(b, num_tokens, self.d_out)
        return self.out_proj(context)

class TransformerBlock(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.att = MultiHeadAttention(
            d_in=cfg["emb_dim"],
            d_out=cfg["emb_dim"],
            context_length=cfg["context_length"],
            num_heads=cfg["n_heads"],
            dropout=cfg["drop_rate"],
        )
        self.ff = FeedForward(cfg)
        self.norm1 = LayerNorm(cfg["emb_dim"])
        self.norm2 = LayerNorm(cfg["emb_dim"])
        self.drop = nn.Dropout(cfg["drop_rate"])

    def forward(self, x):
        x = x + self.drop(self.att(self.norm1(x)))
        x = x + self.drop(self.ff(self.norm2(x)))
        return x

class GPTModel(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.tok_emb = nn.Embedding(cfg["vocab_size"], cfg["emb_dim"])
        self.pos_emb = nn.Embedding(cfg["context_length"], cfg["emb_dim"])
        self.drop_emb = nn.Dropout(cfg["drop_rate"])
        self.trf_blocks = nn.Sequential(*[TransformerBlock(cfg) for _ in range(cfg["n_layers"])])
        self.final_norm = LayerNorm(cfg["emb_dim"])
        self.out_head = nn.Linear(cfg["emb_dim"], cfg["vocab_size"], bias=False)

    def forward(self, in_idx):
        batch_size, seq_len = in_idx.shape
        tok_embeds = self.tok_emb(in_idx)
        pos = torch.arange(seq_len, device=in_idx.device)
        pos_embeds = self.pos_emb(pos)
        x = self.drop_emb(tok_embeds + pos_embeds)
        x = self.trf_blocks(x)
        x = self.final_norm(x)
        logits = self.out_head(x)
        return logits