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

class Head(nn.Module):
    """One head of self-attention"""
    def __init__(self, n_embd, head_size, block_size, dropout):
        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)))
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        B, T, C = x.shape
        k = self.key(x)  
        q = self.query(x)  
        wei = q @ k.transpose(-2, -1) * k.shape[-1] ** -0.5 
        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) 
        wei = F.softmax(wei, dim=-1)  
        wei = self.dropout(wei)
        v = self.value(x)  
        out = wei @ v  
        return out

class MultiHeadAttention(nn.Module):
    """Multiple heads of self-attention in parallel"""
    def __init__(self, n_embd, num_heads, block_size, dropout):
        super().__init__()
        head_size = n_embd // num_heads
        self.heads = nn.ModuleList([Head(n_embd, head_size, block_size, dropout) for _ in range(num_heads)])
        self.proj = nn.Linear(head_size * num_heads, n_embd)
        self.dropout = nn.Dropout(dropout)

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

class FeedForward(nn.Module):
    """A simple feedforward layer"""
    def __init__(self, n_embd, dropout):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(n_embd, 4 * n_embd),
            nn.ReLU(),
            nn.Linear(4 * n_embd, n_embd),
            nn.Dropout(dropout),
        )

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

class Block(nn.Module):
    """Transformer block: Self-Attention followed by Feed Forward"""
    def __init__(self, n_embd, n_head, block_size, dropout):
        super().__init__()
        self.sa = MultiHeadAttention(n_embd, n_head, block_size, dropout)
        self.ffwd = FeedForward(n_embd, dropout)
        self.ln1 = nn.LayerNorm(n_embd)
        self.ln2 = nn.LayerNorm(n_embd)

    def forward(self, x):
        x = self.ln1(x + self.sa(x))
        x = self.ln2(x + self.ffwd(x))
        return x

class BharatAI(nn.Module):
    def __init__(self, vocab_size, n_embd=768, n_head=12, n_layer=12, block_size=256, dropout=0.2):
        super().__init__()
        self.n_embd = n_embd
        self.n_head = n_head
        self.n_layer = n_layer
        self.block_size = block_size
        self.dropout = dropout

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

        self.apply(self._init_weights)

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

    def forward(self, index, targets=None):
        B, T = index.shape
        tok_emb = self.token_embedding_table(index)  
        pos_emb = self.position_embedding_table(torch.arange(T, device=index.device))  
        x = tok_emb + pos_emb  
        x = self.blocks(x)  
        x = self.ln_f(x)  
        logits = self.lm_head(x)  

        if targets is None:
            loss = None
        else:
            B, T, C = logits.shape
            logits = logits.view(B * T, C)
            targets = targets.view(B * T)
            loss = F.cross_entropy(logits, targets)

        return logits, loss

    def generate(self, index, max_new_tokens):
        for _ in range(max_new_tokens):
            index_cond = index[:, -self.block_size:]  
            logits, loss = self.forward(index_cond)
            logits = logits[:, -1, :]  
            probs = F.softmax(logits, dim=-1)
            index_next = torch.multinomial(probs, num_samples=1)
            index = torch.cat((index, index_next), dim=1)  
        return index