model.py

# model.py
import torch
import torch.nn as nn
import torch.nn.functional as F

block_size = 64
n_embd = 128
n_head = 4
n_layer = 2

class Head(nn.Module):
    def __init__(self, head_size):
        super().__init__()
        self.key = nn.Linear(n_embd, head_size, bias=False)
        self.query = nn.Linear(n_embd, head_size, bias=False)
        self.value = nn.Linear(n_embd, head_size, bias=False)
        self.register_buffer("tril", torch.tril(torch.ones(block_size, block_size)))
    def forward(self, x):
        B, T, C = x.shape
        k, q = self.key(x), self.query(x)
        wei = q @ k.transpose(-2, -1) * (C ** -0.5)
        wei = wei.masked_fill(self.tril[:T, :T] == 0, float("-inf"))
        wei = F.softmax(wei, dim=-1)
        v = self.value(x)
        return wei @ v

class MultiHeadAttention(nn.Module):
    def __init__(self, num_heads, head_size):
        super().__init__()
        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
        self.proj = nn.Linear(n_embd, n_embd)
        self.dropout = nn.Dropout(0.1) # Added dropout

    def forward(self, x):
        out = torch.cat([h(x) for h in self.heads], dim=-1)
        out = self.dropout(self.proj(out)) # Applied dropout here
        return self.proj(out)

class FeedForward(nn.Module):
    def __init__(self, n_embd): # Corrected: Add n_embd to init signature
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(n_embd, 4*n_embd),
            nn.ReLU(),
            nn.Linear(4*n_embd, n_embd),
            nn.Dropout(0.1),
        )
    def forward(self, x): return self.net(x)

class Block(nn.Module):
    def __init__(self):
        super().__init__()
        head_size = n_embd // n_head
        self.sa = MultiHeadAttention(n_head, head_size)
        self.ffwd = FeedForward(n_embd)
        self.ln1 = nn.LayerNorm(n_embd)
        self.ln2 = nn.LayerNorm(n_embd)
    def forward(self, x):
        x = x + self.sa(self.ln1(x))
        x = x + self.ffwd(self.ln2(x))
        return x

class TinyTransformer(nn.Module):
    def __init__(self, vocab_size):
        super().__init__()
        self.token_embedding = nn.Embedding(vocab_size, n_embd)
        self.pos_embedding = nn.Embedding(block_size, n_embd)
        self.blocks = nn.Sequential(*[Block() for _ in range(n_layer)])
        self.ln_f = nn.LayerNorm(n_embd)
        self.head = nn.Linear(n_embd, vocab_size)
    def forward(self, idx, targets=None):
        B, T = idx.shape
        tok_emb = self.token_embedding(idx)
        pos_emb = self.pos_embedding(torch.arange(T, device=idx.device))
        x = tok_emb + pos_emb
        x = self.blocks(x)
        x = self.ln_f(x)
        logits = self.head(x)
        if targets is None:
            return logits
        loss = F.cross_entropy(logits.view(-1, vocab_size), targets.view(-1))
        return logits, loss