import torch
import torch.nn as nn
import math
from transformers import PreTrainedModel, PreTrainedConfig
from transformers.modeling_outputs import CausalLMOutputWithCrossAttentions

class NanoGPTCompressedConfig(PreTrainedConfig):
    model_type = "nanogpt_compressed"
    
    def __init__(
        self,
        vocab_size=6060,
        block_size=1024,
        n_layer=8,
        n_head=8,
        n_embd=512,
        dropout=0.0,
        bias=True,
        compression_method="fixed_low_rank_mlp",
        compression_rank=128,
        compressed_layers=[1],
        **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
        self.compression_method = compression_method
        self.compression_rank = compression_rank
        self.compressed_layers = compressed_layers
        super().__init__(**kwargs)

class LowRankLinear(nn.Module):
    def __init__(self, input_dim, output_dim, rank=16, bias=True):
        super().__init__()
        self.rank = rank
        self.input_dim = input_dim
        self.output_dim = output_dim
        
        self.U = nn.Parameter(torch.randn(input_dim, rank) * 0.02)
        self.V = nn.Parameter(torch.randn(rank, output_dim) * 0.02)
        
        if bias:
            self.bias = nn.Parameter(torch.zeros(output_dim))
        else:
            self.register_parameter('bias', None)
        
    def forward(self, x):
        result = (x @ self.U) @ self.V
        if self.bias is not None:
            result = result + self.bias
        return result

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, input):
        return F.layer_norm(input, 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.dropout = config.dropout
        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)
        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, layer_idx=None):
        super().__init__()
        self.layer_idx = layer_idx
        
        # Check if this layer should be compressed
        if (hasattr(config, 'compressed_layers') and 
            layer_idx is not None and 
            layer_idx in config.compressed_layers):
            
            print(f"Creating compressed MLP for layer {layer_idx}")
            rank = getattr(config, 'compression_rank', 128)
            self.c_fc = LowRankLinear(config.n_embd, 4 * config.n_embd, rank, bias=config.bias)
            self.c_proj = LowRankLinear(4 * config.n_embd, config.n_embd, rank, bias=config.bias)
        else:
            self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd, bias=config.bias)
            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):
        x = self.c_fc(x)
        x = F.gelu(x)
        x = self.c_proj(x)
        x = self.dropout(x)
        return x

class Block(nn.Module):
    def __init__(self, config, layer_idx=None):
        super().__init__()
        self.ln_1 = LayerNorm(config.n_embd, bias=config.bias)
        self.attn = CausalSelfAttention(config)
        self.ln_2 = LayerNorm(config.n_embd, bias=config.bias)
        self.mlp = MLP(config, layer_idx=layer_idx)

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

class NanoGPTCompressedModel(PreTrainedModel):
    config_class = NanoGPTCompressedConfig

    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),
            drop = nn.Dropout(config.dropout),
            h = nn.ModuleList([Block(config, layer_idx=i) for i in range(config.n_layer)]),
            ln_f = LayerNorm(config.n_embd, bias=config.bias),
        ))
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        
        # Share weights
        self.transformer.wte.weight = self.lm_head.weight

        # Initialize weights
        self.apply(self._init_weights)
        for pn, p in self.named_parameters():
            if pn.endswith('c_proj.weight') or pn.endswith('c_proj.V'):
                torch.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):
            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):
        device = idx.device
        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=device)

        tok_emb = self.transformer.wte(idx)
        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 targets is not None:
            logits = self.lm_head(x)
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
        else:
            logits = self.lm_head(x[:, [-1], :])
            loss = None

        return CausalLMOutputWithCrossAttentions(
            loss=loss,
            logits=logits,
            past_key_values=None,
            hidden_states=None,
            attentions=None,
            cross_attentions=None,
        )

    @torch.no_grad()
    def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None):
        for _ in range(max_new_tokens):
            idx_cond = idx if idx.size(1) <= self.config.block_size else idx[:, -self.config.block_size:]
            logits = self(idx_cond).logits
            logits = 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)
            idx = torch.cat((idx, idx_next), dim=1)
        return idx