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

n_embd = 384
block_size = 256
dropout = 0.1
n_head = 8
n_layer = 6

# read text file
with open('input.txt', 'r', encoding='utf-8') as f:
    text = f.read()

# collect all the unique characters that occur in this text
chars = sorted(list(set(text)))
vocab_size = len(chars)

cuda = torch.cuda.is_available()
device = 'cuda' if cuda else 'cpu'

class Head(nn.Module):
    """ one head of self-attention"""

    def __init__(self, head_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('trill', 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)
        # compute attention scores ("affinities")
        wei = q @ k.transpose(-2, -1) * C**-0.5
        wei = wei.masked_fill(self.trill[:T, :T] == 0, float('-inf'))
        wei = F.softmax(wei, dim=-1)
        wei = self.dropout(wei)
        # perform the weighted aggregation of the values
        v = self.value(x)
        out = wei @ v
        return out

class MultiHeadAttention(nn.Module):
    """ multiple heads of self-attention in parallel """

    def __init__(self, num_heads, head_size):
        super().__init__()
        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
        self.proj = nn.Linear(n_embd, 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 linear layer followed by a non-linearity """

    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),
            nn.Dropout(dropout)
        )

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

class Block(nn.Module):
    """ Transformer block: communication followed by computation"""

    def __init__(self, n_embd, n_head) -> None:

        super().__init__()
        head_size = n_embd // n_head
        self.sa = MultiHeadAttention(n_head, head_size)
        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)


class BigramLanguageModel(nn.Module):

    def __init__(self):
        super().__init__()
        # each token directly reads off the logits for the next token from a lookup table
        self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
        self.position_embedding_table = nn.Embedding(block_size, n_embd)
        # self.sa_head = MultiHeadAttention(4, n_embd//4)
        # self.ffwd = FeedForward(n_embd)
        # self.blocks = nn.Sequential(
        #     Block(n_embd, n_head=4),
        #     Block(n_embd, n_head=4),
        #     Block(n_embd, n_head=4),
        #     nn.LayerNorm(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, vocab_size)

    def forward(self, idx, targets=None):
        B, T = idx.shape
        # idx and targets are both (B,T) tensor of integers
        tok_emb = self.token_embedding_table(idx) # (B,T,C)
        pos_emb = self.position_embedding_table(torch.arange(T, device=device))
        x = tok_emb + pos_emb
        # x = self.sa_head(x)
        # x = self.ffwd(x)
        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, idx, max_new_tokens):
        # idx is (B, T) array of indices in the current context
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -block_size:]
            # get the predictions
            logits, loss = self(idx_cond)
            # focus only on the last time step
            logits = logits[:, -1, :] # becomes (B, C)
            # apply softmax to get probabilities
            probs = F.softmax(logits, dim=-1) # (B, C)
            # sample from the distribution
            idx_next = torch.multinomial(probs, num_samples=1) # (B, 1)
            # append sampled index to the running sequence
            idx = torch.cat((idx, idx_next), dim=1) # (B, T+1)
        return idx