import math
from dataclasses import dataclass

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


@dataclass
class ModelConfig:
    vocab_size: int
    block_size: int = 128
    n_embd: int = 128
    n_head: int = 4
    n_layer: int = 4
    dropout: float = 0.1


class CausalSelfAttention(nn.Module):
    def __init__(self, config: ModelConfig):
        super().__init__()
        assert config.n_embd % config.n_head == 0
        self.n_head = config.n_head
        self.head_size = config.n_embd // config.n_head
        self.qkv = nn.Linear(config.n_embd, 3 * config.n_embd)
        self.proj = nn.Linear(config.n_embd, config.n_embd)
        self.dropout = nn.Dropout(config.dropout)
        mask = torch.tril(torch.ones(config.block_size, config.block_size))
        self.register_buffer("mask", mask.view(1, 1, config.block_size, config.block_size))

    def forward(self, x):
        bsz, seq_len, channels = x.shape
        qkv = self.qkv(x)
        q, k, v = qkv.split(channels, dim=2)
        q = q.view(bsz, seq_len, self.n_head, self.head_size).transpose(1, 2)
        k = k.view(bsz, seq_len, self.n_head, self.head_size).transpose(1, 2)
        v = v.view(bsz, seq_len, self.n_head, self.head_size).transpose(1, 2)

        scores = (q @ k.transpose(-2, -1)) / math.sqrt(self.head_size)
        scores = scores.masked_fill(self.mask[:, :, :seq_len, :seq_len] == 0, float("-inf"))
        weights = F.softmax(scores, dim=-1)
        weights = self.dropout(weights)
        out = weights @ v
        out = out.transpose(1, 2).contiguous().view(bsz, seq_len, channels)
        return self.dropout(self.proj(out))


class TransformerBlock(nn.Module):
    def __init__(self, config: ModelConfig):
        super().__init__()
        self.ln1 = nn.LayerNorm(config.n_embd)
        self.attn = CausalSelfAttention(config)
        self.ln2 = nn.LayerNorm(config.n_embd)
        self.mlp = nn.Sequential(
            nn.Linear(config.n_embd, 4 * config.n_embd),
            nn.GELU(),
            nn.Linear(4 * config.n_embd, config.n_embd),
            nn.Dropout(config.dropout),
        )

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


class SuperLilLM(nn.Module):
    def __init__(self, config: ModelConfig):
        super().__init__()
        self.config = config
        self.token_embedding = nn.Embedding(config.vocab_size, config.n_embd)
        self.position_embedding = nn.Embedding(config.block_size, config.n_embd)
        self.blocks = nn.Sequential(*[TransformerBlock(config) for _ in range(config.n_layer)])
        self.ln_f = nn.LayerNorm(config.n_embd)
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size)
        self.dropout = nn.Dropout(config.dropout)
        self.apply(self._init_weights)

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

    def forward(self, idx, targets=None):
        _, seq_len = idx.shape
        if seq_len > self.config.block_size:
            raise ValueError(f"Sequence length {seq_len} exceeds block size {self.config.block_size}")
        positions = torch.arange(seq_len, device=idx.device)
        x = self.token_embedding(idx) + self.position_embedding(positions)
        x = self.dropout(x)
        x = self.blocks(x)
        x = self.ln_f(x)
        logits = self.lm_head(x)

        loss = None
        if targets is not None:
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-100)
        return logits, loss