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

class BigramLanguageModel(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.vocab_size = config["vocab_size"]
        self.block_size = config["block_size"]
        n_embd = config["n_embd"]
        n_head = config["n_head"]
        n_layer = config["n_layer"]

        self.token_embedding_table = nn.Embedding(self.vocab_size, n_embd)
        self.position_embedding_table = nn.Embedding(self.block_size, n_embd)

        self.blocks = nn.Sequential(*[
            Block(n_embd, n_head) for _ in range(n_layer)
        ])
        self.ln_f = nn.LayerNorm(n_embd)
        self.lm_head = nn.Linear(n_embd, self.vocab_size)

    def forward(self, idx):
        B, T = idx.shape
        tok_emb = self.token_embedding_table(idx)
        pos_emb = self.position_embedding_table(torch.arange(T, device=idx.device))
        x = tok_emb + pos_emb
        x = self.blocks(x)
        x = self.ln_f(x)
        return self.lm_head(x)

    @torch.no_grad()
    def generate(self, idx, max_new_tokens):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.block_size:]
            logits = self(idx_cond)
            logits = logits[:, -1, :]
            probs = F.softmax(logits, dim=-1)
            idx_next = torch.multinomial(probs, 1)
            idx = torch.cat([idx, idx_next], dim=1)
        return idx


class Head(nn.Module):
    def __init__(self, n_embd, head_size, block_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 = self.key(x)
        q = 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, n_embd, n_head, block_size):
        super().__init__()
        head_size = n_embd // n_head
        self.heads = nn.ModuleList([
            Head(n_embd, head_size, block_size) for _ in range(n_head)
        ])
        self.proj = nn.Linear(n_embd, n_embd)

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


class FeedForward(nn.Module):
    def __init__(self, n_embd):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(n_embd, 4 * n_embd),
            nn.ReLU(),
            nn.Linear(4 * n_embd, n_embd),
        )

    def forward(self, x):
        return self.net(x)


class Block(nn.Module):
    def __init__(self, n_embd, n_head):
        super().__init__()
        self.sa = MultiHeadAttention(n_embd, n_head, block_size=32)
        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