import torch
import torch.nn as nn
import torch.nn.functional as F
import tiktoken
import math

print(f"TORCH OK: {torch.__version__}")

enc = tiktoken.get_encoding("gpt2")
vocab_size = enc.n_vocab
print(f"Tokenizer: GPT2 {vocab_size} tokens")

class Config:
    vocab_size = vocab_size
    block_size = 128
    n_layer = 4
    n_head = 4
    n_embd = 256
    dropout = 0.1

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

    def forward(self, x):
        B, T, C = x.size()
        qkv = self.c_attn(x)
        q, k, v = qkv.split(self.n_embd, dim=2)
        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
        att = att.masked_fill(self.mask[:,:,:T,:T] == 0, float('-inf'))
        att = F.softmax(att, dim=-1)
        att = F.dropout(att, p=self.dropout, training=self.training)
        y = att @ v
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        y = self.c_proj(y)
        return y

class Block(nn.Module):
    def __init__(self, config):
        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 TinyLLM(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.tok_emb = nn.Embedding(config.vocab_size, config.n_embd)
        self.pos_emb = nn.Embedding(config.block_size, config.n_embd)
        self.blocks = nn.ModuleList([Block(config) for _ in range(config.n_layer)])
        self.ln_f = nn.LayerNorm(config.n_embd)
        self.head = nn.Linear(config.n_embd, config.vocab_size, bias=False)

    def forward(self, idx, targets=None):
        B, T = idx.size()
        tok = self.tok_emb(idx)
        pos = self.pos_emb(torch.arange(T, device=idx.device))
        x = tok + pos
        for block in self.blocks:
            x = block(x)
        x = self.ln_f(x)
        logits = self.head(x)
        loss = None
        if targets is not None:
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
        return logits, loss

    @torch.no_grad()
    def generate(self, idx, max_new_tokens=50, top_k=50):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.config.block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :]
            v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
            logits[logits < v[:, [-1]]] = -float('Inf')
            probs = F.softmax(logits, dim=-1)
            idx_next = torch.multinomial(probs, num_samples=1)
            idx = torch.cat((idx, idx_next), dim=1)
        return idx

config = Config()
model = TinyLLM(config)
print(f"Model params: {sum(p.numel() for p in model.parameters())/1e6:.2f}M")

x = torch.randint(0, vocab_size, (2, config.block_size))
y = torch.randint(0, vocab_size, (2, config.block_size))

logits, loss = model(x, y)
print(f"Initial loss: {loss.item():.4f}")

opt = torch.optim.AdamW(model.parameters(), lr=3e-4)
for i in range(20):
    logits, loss = model(x, y)
    opt.zero_grad()
    loss.backward()
    opt.step()
    if i % 5 == 0:
        print(f"step {i} loss {loss.item():.4f}")

prompt = "Hello, I am a"
ids = torch.tensor([enc.encode(prompt)], dtype=torch.long)
out = model.generate(ids, max_new_tokens=30)
print("\nPROMPT:", prompt)
print("GEN:", enc.decode(out[0].tolist()))