import torch
import torch.nn as nn
from dataclasses import dataclass
import torch.nn.functional as F
import tiktoken
import inspect

class CausalSelfAttention(nn.Module):
    def __init__(self, config):
        super().__init__()
        assert config.n_embd % config.n_head == 0
        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
        self.c_proj.GPT_SCALE_INIT = 1
        self.n_head = config.n_head
        self.n_embd = config.n_embd
        self.register_buffer("bias", 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)
        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        q = q.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)
        y = F.scaled_dot_product_attention(q, k, v, is_causal=True)
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        y = self.c_proj(y)
        return y

class MLP(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd)
        self.gelu = nn.GELU(approximate='tanh')
        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)
        self.c_proj.GPT_SCALE_INIT = 1

    def forward(self, x):
        x = self.c_fc(x)
        x = self.gelu(x)
        x = self.c_proj(x)
        return x
    
class Block(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.ln_1 = nn.LayerNorm(config.n_embd)
        self.attn = CausalSelfAttention(config)
        self.ln_2 = nn.LayerNorm(config.n_embd)
        self.mlp = MLP(config)

    def forward(self, x):
        x = x + self.attn(self.ln_1(x))
        x = x + self.mlp(self.ln_2(x))
        return x

@dataclass
class GPTConfig:
    depth: int = 12
    block_size: int = 1024
    vocab_size: int = 50257
    
    @property
    def n_layer(self): return self.depth
    @property
    def n_head(self): return self.depth
    @property
    def n_embd(self): return self.depth * 64

class GPT(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.transformer = nn.ModuleDict(dict(
            wte = nn.Embedding(config.vocab_size, config.n_embd),
            wpe = nn.Embedding(config.block_size, config.n_embd),
            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
            ln_f = nn.LayerNorm(config.n_embd)
        ))
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        self.transformer.wte.weight = self.lm_head.weight
        self.apply(self._init_weights)

    def _init_weights(self, module):
        std = 0.02
        if isinstance(module, nn.Linear):
            if hasattr(module, 'GPT_SCALE_INIT'):
                std *= (2 * self.config.n_layer) ** -0.5
            torch.nn.init.normal_(module.weight, mean=0.0, std=std)
            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=std)

    def forward(self, idx, targets=None):
        B, T = idx.size()
        assert T <= self.config.block_size, f"Cannot forward sequence of length {T}, block size is only {self.config.block_size}."
        pos = torch.arange(0, T, dtype=torch.long, device=idx.device)
        pos_emb = self.transformer.wpe(pos)
        tok_emb = self.transformer.wte(idx)
        x = tok_emb + pos_emb
        for block in self.transformer.h:
            x = block(x)
        x = self.transformer.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
    
    def generate(self, prompt, max_new_tokens=20, top_k=50, enc=None):
        if enc is None:
            enc = tiktoken.get_encoding('gpt2')
        tokens = enc.encode(prompt)
        x = torch.tensor(tokens, dtype=torch.long).unsqueeze(0).to(next(self.parameters()).device)
        self.eval()
        with torch.no_grad():
            while x.size(1) < len(tokens) + max_new_tokens:
                logits, _ = self(x)
                logits = logits[:, -1, :]
                probs = F.softmax(logits, dim=-1)
                topk_probs, topk_indices = torch.topk(probs, top_k, dim=-1)
                ix = torch.multinomial(topk_probs, 1)
                xcol = torch.gather(topk_indices, -1, ix)
                x = torch.cat((x, xcol), dim=1)
        return enc.decode(x[0].tolist())
    
    def configure_optimizers(self, weight_decay, learning_rate, device):
        param_dict = {pn: p for pn, p in self.named_parameters()}
        param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
        decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
        nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
        optim_groups = [
            {'params': decay_params, 'weight_decay': weight_decay},
            {'params': nodecay_params, 'weight_decay': 0.0}
        ]
        num_decay_params = sum(p.numel() for p in decay_params)
        num_nodecay_params = sum(p.numel() for p in nodecay_params)
        print(f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters")
        print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
        fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
        use_fused = fused_available and 'cuda' in device
        print(f"using fused AdamW: {use_fused}")
        optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=(0.9, 0.95), eps=0.00000001, fused=use_fused)
        return optimizer