import os
import torch
import torch.nn as nn
from torch.nn import functional as F
from transformers import PreTrainedModel, AutoConfig, AutoModelForCausalLM
from .configuration_gpt import CustomGPTConfig  # Use relative import
from huggingface_hub import HfApi
from huggingface_hub import HfApi, create_repo

# Define the CausalSelfAttention class
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()
        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

# Define the MLP class
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)

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

# Define the Block class
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

# Define the GPT class
class CustomGPT(PreTrainedModel):
    config_class = CustomGPTConfig

    def __init__(self, config):
        super().__init__(config)
        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):
            std = 0.02
            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=0.02)

    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))
        return logits, loss

    def save_pretrained(self, save_directory, safe_serialization=False):
        # Ensure the save directory exists
        if not os.path.exists(save_directory):
            os.makedirs(save_directory)
            print(f"Created directory: {save_directory}")
        else:
            print(f"Directory already exists: {save_directory}")

        # Save the model configuration
        config_path = os.path.join(save_directory, "config.json")
        self.config.save_pretrained(save_directory)
        print(f"Saved configuration to: {config_path}")

        # Save the model weights
        model_path = os.path.join(save_directory, "pytorch_model.bin")
        torch.save(self.state_dict(), model_path)
        print(f"Saved model weights to: {model_path}")

        # If safe_serialization is False, call the base class method
        if not safe_serialization:
            super().save_pretrained(save_directory, safe_serialization=False)
        

        



    def push_to_hub(self, repo_id, commit_message="Push model to hub"):
        try:
            # Save the model locally
            self.save_pretrained(repo_id)
            print(f"Model saved locally to {repo_id}")

            # Create the repository with the desired privacy settings
            api = HfApi()
            api.create_repo(repo_id=repo_id, private=False, exist_ok=True)
            print(f"Repository created (or already exists) with ID: {repo_id}")

            # Use HfApi to push the model to the Hugging Face Hub
            api.upload_folder(
                folder_path=repo_id,
                repo_id=repo_id,
                repo_type="model",
                commit_message=commit_message
            )
            print(f"Model uploaded successfully to {repo_id}")
        except Exception as e:
            print(f"Failed to upload model: {e}")