import torch
import torch.nn as nn
from torch.nn import functional as F
from qiskit.circuit.library import RealAmplitudes, ZZFeatureMap, ZFeatureMap
from qiskit import QuantumCircuit
from qiskit_machine_learning.neural_networks import SamplerQNN
from qiskit_machine_learning.connectors import TorchConnector
from dataclasses import dataclass

# Quantum Neural Network setup
num_qubits = 8

def create_qnn():
    """Creates a Quantum Neural Network."""
    feature_map = ZFeatureMap(num_qubits, reps=32)
    ansatz = RealAmplitudes(num_qubits, reps=32)
    qc = QuantumCircuit(num_qubits)
    qc.compose(feature_map, inplace=True)
    qc.compose(ansatz, inplace=True)

    qnn = SamplerQNN(
        circuit=qc,
        input_params=feature_map.parameters,
        weight_params=ansatz.parameters,
    )

    return qnn

# Model Components
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.n_head = config.n_head
        self.n_embd = config.n_embd

    def forward(self, x):
        B, T, C = x.size()  # Batch size, sequence length, embedding 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.quantum_embedding = nn.Linear(config.n_embd, num_qubits)
        self.qnn_layer = TorchConnector(create_qnn())
        self.output_layer = nn.Linear(2 ** num_qubits, 1024)

    def forward(self, x):
        x = self.quantum_embedding(x)
        x = self.qnn_layer(x)
        x = self.gelu(x)
        x = self.output_layer(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:
    block_size: int = 1024
    vocab_size: int = 50257
    n_layer: int = 24
    n_head: int = 16
    n_embd: int = 1024

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):
        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, idx, targets=None):
        B, T = idx.size()
        assert T <= self.config.block_size, "Sequence length exceeds block size"
        pos = torch.arange(0, T, dtype=torch.long, device=idx.device)
        tok_emb = self.transformer.wte(idx)
        pos_emb = self.transformer.wpe(pos)
        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))
        return logits, loss

# Export the architecture for inference
if __name__ == "__main__":
    config = GPTConfig()
    model = GPT(config)
    print(f"Model architecture:\n{model}")