import torch
import torch.nn as nn
import torch.nn.functional as F
import math
from transformers import PreTrainedModel, PretrainedConfig

class GPTConfig(PretrainedConfig):
    model_type = "gpt"

    def __init__(
        self,
        vocab_size=50257,
        block_size=128,
        n_layer=6,
        n_head=6,
        n_embd=384,
        dropout=0.0,
        bias=True,
        **kwargs
    ):
        super().__init__(**kwargs)
        self.vocab_size = vocab_size
        self.block_size = block_size
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_embd = n_embd
        self.dropout = dropout
        self.bias = bias

class LayerNorm(nn.Module):
    def __init__(self, ndim, bias):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(ndim))
        self.bias = nn.Parameter(torch.zeros(ndim)) if bias else None

    def forward(self, x):
        return F.layer_norm(x, self.weight.shape, self.weight, self.bias, 1e-5)

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, bias=config.bias)
        self.c_proj = nn.Linear(config.n_embd, config.n_embd, bias=config.bias)
        self.attn_dropout = nn.Dropout(config.dropout)
        self.resid_dropout = nn.Dropout(config.dropout)
        self.n_head = config.n_head
        self.n_embd = config.n_embd
        self.flash = hasattr(F, 'scaled_dot_product_attention')
        if not self.flash:
            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()
        q, k, v = self.c_attn(x).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)

        if self.flash:
            y = F.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=self.attn_dropout.p if self.training else 0.0, is_causal=True)
        else:
            att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
            att = att.masked_fill(self.bias[:, :, :T, :T] == 0, float('-inf'))
            att = F.softmax(att, dim=-1)
            att = self.attn_dropout(att)
            y = att @ v

        y = y.transpose(1, 2).contiguous().view(B, T, C)
        y = self.resid_dropout(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, bias=config.bias)
        self.gelu = nn.GELU()
        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd, bias=config.bias)
        self.dropout = nn.Dropout(config.dropout)

    def forward(self, x):
        return self.dropout(self.c_proj(self.gelu(self.c_fc(x))))

class Block(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.ln1 = LayerNorm(config.n_embd, config.bias)
        self.attn = CausalSelfAttention(config)
        self.ln2 = LayerNorm(config.n_embd, config.bias)
        self.mlp = MLP(config)

    def forward(self, x):
        x = x + self.attn(self.ln1(x))
        x = x + self.mlp(self.ln2(x))
        return x

class GPT(PreTrainedModel):
    config_class = GPTConfig

    def __init__(self, config):
        super().__init__(config)
        self.transformer = nn.ModuleDict(dict(
            wte=nn.Embedding(config.vocab_size, config.n_embd),
            wpe=nn.Embedding(config.block_size, config.n_embd),
            drop=nn.Dropout(config.dropout),
            h=nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
            ln_f=LayerNorm(config.n_embd, config.bias),
        ))
        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)
        for pn, p in self.named_parameters():
            if pn.endswith('c_proj.weight'):
                nn.init.normal_(p, mean=0.0, std=0.02 / math.sqrt(2 * config.n_layer))

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

    def forward(self, input_ids, labels=None):
        device = input_ids.device
        b, t = input_ids.size()
        assert t <= self.config.block_size
        pos = torch.arange(0, t, dtype=torch.long, device=device)

        tok_emb = self.transformer.wte(input_ids)
        pos_emb = self.transformer.wpe(pos)
        x = self.transformer.drop(tok_emb + pos_emb)
        for block in self.transformer.h:
            x = block(x)
        x = self.transformer.ln_f(x)

        if labels is not None:
            logits = self.lm_head(x)
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), labels.view(-1), ignore_index=-1)
            return {'logits': logits, 'loss': loss}
        else:
            logits = self.lm_head(x[:, [-1], :])
            return {'logits': logits}

    @torch.no_grad()
    def generate(self, input_ids, max_new_tokens, temperature=1.0, top_k=None):
        for _ in range(max_new_tokens):
            idx_cond = input_ids if input_ids.size(1) <= self.config.block_size else input_ids[:, -self.config.block_size:]
            out = self(idx_cond)
            logits = out['logits'][:, -1, :] / temperature
            if top_k is not None:
                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)
            input_ids = torch.cat((input_ids, idx_next), dim=1)
        return input_ids