import math
from dataclasses import dataclass

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


@dataclass
class GPTConfig:
    vocab_size: int = 50257
    block_size: int = 256     
    n_layer: int = 6
    n_head: int = 6
    n_embd: int = 384
    dropout: float = 0.1
    bias: bool = False


class CausalSelfAttention(nn.Module):
    def __init__(self, cfg: GPTConfig):
        super().__init__()
        assert cfg.n_embd % cfg.n_head == 0
        self.n_head = cfg.n_head
        self.qkv = nn.Linear(cfg.n_embd, 3 * cfg.n_embd, bias=cfg.bias)
        self.proj = nn.Linear(cfg.n_embd, cfg.n_embd, bias=cfg.bias)
        self.attn_drop = cfg.dropout
        self.resid_drop = nn.Dropout(cfg.dropout)

    def forward(self, x):
        B, T, C = x.shape
        q, k, v = self.qkv(x).split(C, dim=2)
        q, k, v = (t.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) for t in (q, k, v))
        y = F.scaled_dot_product_attention(
            q, k, v,
            dropout_p=self.attn_drop if self.training else 0.0,
            is_causal=True,
        )
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        return self.resid_drop(self.proj(y))


class MLP(nn.Module):
    def __init__(self, cfg: GPTConfig):
        super().__init__()
        self.fc = nn.Linear(cfg.n_embd, 4 * cfg.n_embd, bias=cfg.bias)
        self.proj = nn.Linear(4 * cfg.n_embd, cfg.n_embd, bias=cfg.bias)
        self.drop = nn.Dropout(cfg.dropout)

    def forward(self, x):
        return self.drop(self.proj(F.gelu(self.fc(x))))


class Block(nn.Module):
    """Pre-LayerNorm transformer block."""

    def __init__(self, cfg: GPTConfig):
        super().__init__()
        self.ln1 = nn.LayerNorm(cfg.n_embd, bias=cfg.bias)
        self.attn = CausalSelfAttention(cfg)
        self.ln2 = nn.LayerNorm(cfg.n_embd, bias=cfg.bias)
        self.mlp = MLP(cfg)

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


class GPT(nn.Module):
    def __init__(self, cfg: GPTConfig):
        super().__init__()
        self.cfg = cfg
        self.tok_emb = nn.Embedding(cfg.vocab_size, cfg.n_embd)
        self.pos_emb = nn.Embedding(cfg.block_size, cfg.n_embd)
        self.drop = nn.Dropout(cfg.dropout)
        self.blocks = nn.ModuleList(Block(cfg) for _ in range(cfg.n_layer))
        self.ln_f = nn.LayerNorm(cfg.n_embd, bias=cfg.bias)
        self.lm_head = nn.Linear(cfg.n_embd, cfg.vocab_size, bias=False)
        self.lm_head.weight = self.tok_emb.weight  # weight tying

        self.apply(self._init_weights)
        for name, p in self.named_parameters():
            if name.endswith("proj.weight"):
                nn.init.normal_(p, mean=0.0, std=0.02 / math.sqrt(2 * cfg.n_layer))

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            nn.init.normal_(m.weight, mean=0.0, std=0.02)
            if m.bias is not None:
                nn.init.zeros_(m.bias)
        elif isinstance(m, nn.Embedding):
            nn.init.normal_(m.weight, mean=0.0, std=0.02)

    def num_params(self):
        return sum(p.numel() for p in self.parameters())

    def forward(self, idx, targets=None):
        B, T = idx.shape
        assert T <= self.cfg.block_size, f"Sequence length {T} > block_size {self.cfg.block_size}"
        pos = torch.arange(T, device=idx.device)
        x = self.drop(self.tok_emb(idx) + self.pos_emb(pos))
        for block in self.blocks:
            x = block(x)
        x = self.ln_f(x)

        if targets is not None:
            logits = self.lm_head(x)
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
            return logits, loss
        return self.lm_head(x[:, [-1], :]), None

    def configure_optimizer(self, lr=3e-4, weight_decay=0.1, betas=(0.9, 0.95)):
        params = [p for p in self.parameters() if p.requires_grad]
        decay = [p for p in params if p.dim() >= 2]
        no_decay = [p for p in params if p.dim() < 2]
        groups = [
            {"params": decay, "weight_decay": weight_decay},
            {"params": no_decay, "weight_decay": 0.0},
        ]
        return torch.optim.AdamW(groups, lr=lr, betas=betas)

    @torch.no_grad()
    def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None):
        self.eval()
        eos_token_id = 50256

        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.cfg.block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / max(temperature, 1e-8)

            if top_k is not None:
                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
                logits[logits < v[:, [-1]]] = float("-inf")

            probs = F.softmax(logits, dim=-1)
            next_token = torch.multinomial(probs, 1)
            idx = torch.cat([idx, next_token], dim=1)

            if torch.all(next_token == eos_token_id):
                break

        return idx


if __name__ == "__main__":
    cfg = GPTConfig(vocab_size=1000, block_size=64, n_layer=2, n_head=2, n_embd=64)
    model = GPT(cfg)
    print(f"params: {model.num_params():,}")
    x = torch.randint(0, cfg.vocab_size, (4, 64))
    logits, loss = model(x, targets=x)
    print("loss:", loss.item())  
    print(model.generate(x[:1, :8], max_new_tokens=10).shape)