import torch
import torch.nn as nn
import math


class CausalSelfAttention(nn.Module):
    def __init__(self, d_model, n_heads, block_size):
        super().__init__()
        self.n_heads = n_heads
        self.key = nn.Linear(d_model, d_model)
        self.query = nn.Linear(d_model, d_model)
        self.value = nn.Linear(d_model, d_model)

        self.proj = nn.Linear(d_model, d_model)
        self.register_buffer(
            "mask",
            torch.tril(torch.ones(block_size, block_size))
        )

    def forward(self, x):
        B, T, C = x.size()
        H = self.n_heads
        k = self.key(x).view(B, T, H, C // H).transpose(1, 2)
        q = self.query(x).view(B, T, H, C // H).transpose(1, 2)
        v = self.value(x).view(B, T, H, C // H).transpose(1, 2)

        att = (q @ k.transpose(-2, -1)) / math.sqrt(C // H)
        att = att.masked_fill(self.mask[:T, :T] == 0, float("-inf"))
        att = torch.softmax(att, dim=-1)

        out = att @ v
        out = out.transpose(1, 2).contiguous().view(B, T, C)
        return self.proj(out)


class Block(nn.Module):
    def __init__(self, d_model, n_heads, block_size):
        super().__init__()
        self.ln1 = nn.LayerNorm(d_model)
        self.attn = CausalSelfAttention(d_model, n_heads, block_size)
        self.ln2 = nn.LayerNorm(d_model)
        self.mlp = nn.Sequential(
            nn.Linear(d_model, 4 * d_model),
            nn.GELU(),
            nn.Linear(4 * d_model, d_model)
        )

    def forward(self, x):
        x = x + self.attn(self.ln1(x))
        x = x + self.mlp(self.ln2(x))
        return x


class SIMGPT(nn.Module):
    def __init__(self, vocab_size, block_size, n_layers, n_heads, d_model):
        super().__init__()
        self.token_emb = nn.Embedding(vocab_size, d_model)
        self.pos_emb = nn.Embedding(block_size, d_model)
        self.blocks = nn.Sequential(*[
            Block(d_model, n_heads, block_size) for _ in range(n_layers)
        ])
        self.ln = nn.LayerNorm(d_model)
        self.head = nn.Linear(d_model, vocab_size)

    def forward(self, idx):
        B, T = idx.shape
        pos = torch.arange(0, T, device=idx.device)
        x = self.token_emb(idx) + self.pos_emb(pos)
        x = self.blocks(x)
        x = self.ln(x)
        return self.head(x)