import os
import math
import torch
import torch.nn as nn
from torch.nn import functional as F
import gradio as gr
import tiktoken

# GPT model code
class GPTConfig:
    def __init__(self):
        self.block_size = 1024
        self.vocab_size = 50304
        self.n_layer = 12
        self.n_head = 12
        self.n_embd = 768

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
        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)
        y = F.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True)
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        return self.c_proj(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()
        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)

    def forward(self, x):
        return self.c_proj(self.gelu(self.c_fc(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.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):
        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).unsqueeze(0)
        
        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), ignore_index=-1)
        
        return logits, loss

# Load the trained model
def load_model(model_path):
    config = GPTConfig()
    model = GPT(config)
    model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))
    model.eval()
    return model

model = load_model('GPT_model.pth')  # Replace with the actual path to your .pth file
enc = tiktoken.get_encoding('gpt2')

def generate_text(prompt, max_length=100, temperature=0.7):
    input_ids = torch.tensor(enc.encode(prompt)).unsqueeze(0)
    
    with torch.no_grad():
        for _ in range(max_length):
            outputs, _ = model(input_ids)
            next_token_logits = outputs[:, -1, :] / temperature
            next_token = torch.multinomial(torch.softmax(next_token_logits, dim=-1), num_samples=1)
            input_ids = torch.cat([input_ids, next_token], dim=-1)
            
            if next_token.item() == enc.encode('\n')[0]:
                break
    
    generated_text = enc.decode(input_ids[0].tolist())
    return generated_text

# Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.Textbox(label="Prompt", placeholder="Enter your prompt here..."),
        gr.Slider(minimum=10, maximum=200, value=100, step=1, label="Max Length"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature")
    ],
    outputs=gr.Textbox(label="Generated Text"),
    title="GPT-2 Text Generator",
    description="Enter a prompt and generate text using a fine-tuned GPT-2 model."
)

# Launch the app
iface.launch()