import torch
import torch.nn.functional as F
import gradio as gr
import tiktoken
from dataclasses import dataclass
import torch.nn as nn
import math
import inspect
import spaces

# Configuration class (same as in training)
@dataclass
class GPTConfig:
    block_size: int = 1024
    vocab_size: int = 50257
    n_layer: int = 12
    n_head: int = 12
    n_embd: int = 768

# Model architecture classes (copied from training notebook)
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.NANGPT_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.NANOGPT_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

class GPT(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.gradient_checkpointing = True

        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
            if hasattr(module, 'NANGPT_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=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)

        return logits, None if targets is None else F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))

# Initialize model and load weights
def load_model():
    device = 'cuda' if torch.cuda.is_available() else 'cpu'
    model = GPT(GPTConfig())
    
    # Load the state dict with weights_only=True and remove the _orig_mod prefix
    state_dict = torch.load('nano_gpt_model.pt', map_location=device, weights_only=True)
    new_state_dict = {}
    for key in state_dict.keys():
        new_key = key.replace('_orig_mod.', '')
        new_state_dict[new_key] = state_dict[key]
    
    model.load_state_dict(new_state_dict)
    model.to(device)
    model.eval()
    return model, device

# Text generation function
@spaces.GPU(enable_queue=True)
def generate_text(prompt, num_tokens, temperature=0.8):
    enc = tiktoken.get_encoding('gpt2')
    x = torch.tensor([enc.encode(prompt)], dtype=torch.long, device=device)

    with torch.no_grad():
        while x.size(1) < num_tokens:
            with torch.autocast(device_type=device, dtype=torch.bfloat16):
                logits = model(x)[0]
            logits = logits[:, -1, :] / temperature
            probs = F.softmax(logits, dim=-1)
            next_token = torch.multinomial(probs, num_samples=1)
            x = torch.cat([x, next_token], dim=1)

    decoded = enc.decode(x[0].tolist())
    return decoded

# Load the model globally
model, device = load_model()

# Create the Gradio interface
demo = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.Textbox(label="Enter your prompt", value="Thou shalt"),
        gr.Slider(minimum=1, maximum=1024, value=100, step=1, label="Number of tokens to generate"),
        gr.Slider(minimum=0.1, maximum=2.0, value=0.8, step=0.1, label="Temperature (higher = more random)")
    ],
    outputs=gr.Textbox(label="Generated Text"),
    title="GPT Text Generator",
    description="Generate Shakespeare-style text using a trained GPT model",
    allow_flagging="never",
    cache_examples=True
)

if __name__ == "__main__":
    demo.launch()