Generate_script.py

import torch
import torch.nn as nn
from torch.nn import functional as F

# Hyper Parameters
block_size = 256
device = 'cuda' if torch.cuda.is_available() else 'cpu'
n_embd = 384
n_head = 6
n_layer = 6
dropout = 0.2

# Define your model classes here
class Head(nn.Module):
    """ Implements one head of self attention """
    def __init__(self, head_size):
        super().__init__()
        self.key = nn.Linear(n_embd, head_size, bias=False)
        self.value = nn.Linear(n_embd, head_size, bias=False)
        self.query = nn.Linear(n_embd, head_size, bias=False)
        self.register_buffer('tril', torch.tril(torch.ones(block_size, block_size)))
        self.dropout = nn.Dropout(dropout)
    
    def forward(self, x):
        B, T, C = x.shape
        k = self.key(x)
        q = self.query(x)
        wei = q @ k.transpose(-1, -2) * C**(-0.5)
        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf'))
        wei = F.softmax(wei, dim=-1)
        wei = self.dropout(wei)
        v = self.value(x)
        out = wei @ v
        return out

class MultiHeadAttention(nn.Module):
    """ Multiple heads of self attention in parallel """
    def __init__(self, num_heads, head_size):
        super().__init__()
        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
        self.proj = nn.Linear(num_heads * head_size, n_embd)
        self.dropout = nn.Dropout(dropout)
    
    def forward(self, x):
        out = torch.cat([h(x) for h in self.heads], dim=-1)
        out = self.proj(out)
        out = self.dropout(out)
        return out

class FeedForward(nn.Module):
    """ Feed forward layer. Note -> Feed forward network works at a token level (independent) """
    def __init__(self, n_embd):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(n_embd, 4 * n_embd),
            nn.ReLU(),
            nn.Linear(4 * n_embd, n_embd),
            nn.Dropout(dropout),
        )

    def forward(self, x):
        return self.net(x)

class Block(nn.Module):
    """ Transformer block (decoder sec): Communication followed by computation """
    def __init__(self, n_embd, n_head):
        super().__init__()
        head_size = n_embd // n_head
        self.sa = MultiHeadAttention(n_head, head_size=head_size)
        self.ffwd = FeedForward(n_embd)
        self.ln1 = nn.LayerNorm(n_embd)
        self.ln2 = nn.LayerNorm(n_embd)
    
    def forward(self, x):
        x = self.ln1(x)
        x = x + self.sa(x)
        x = self.ln2(x)
        x = x + self.ffwd(x)
        return x

class BigramLanguageModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
        self.position_embedding_table = nn.Embedding(block_size, n_embd)
        self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head) for _ in range(n_layer)])
        self.lm_f = nn.LayerNorm(n_embd)
        self.lm_head = nn.Linear(n_embd, vocab_size)

    def forward(self, idx, targets=None):
        B, T = idx.shape
        token_emb = self.token_embedding_table(idx)  # (B, T, C)
        pos_emb = self.position_embedding_table(torch.arange(T, device=device))  # (T, C)
        x = token_emb + pos_emb  # (B, T, C)
        x = self.blocks(x)
        logits = self.lm_head(x)  # (B, T, vocab_size)
        if targets is None:
            loss = None
        else:
            B, T, C = logits.shape
            logits = logits.view(B * T, C)
            targets = targets.view(B * T)
            loss = F.cross_entropy(logits, targets)
        return logits, loss

    def generate(self, idx, max_new_tokens):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -block_size:]
            logits, loss = self(idx_cond)
            logits = logits[:, -1, :]  # (B, C)
            probs = F.softmax(logits, dim=-1)  # (B, C)
            idx_next = torch.multinomial(probs, num_samples=1)  # (B, 1)
            idx = torch.cat((idx, idx_next), dim=1)  # (B, T+1)
        return idx

# Load the character mappings (assuming you saved them or can recreate them)
chars = sorted(list(set(open('Friends_script.txt', 'r', encoding='utf-8').read())))
vocab_size = len(chars)
stoi = {ch: i for i, ch in enumerate(chars)}
itos = {i: ch for i, ch in enumerate(chars)}
decode = lambda l: ''.join([itos[i] for i in l])

# Instantiate the model
model = BigramLanguageModel()
model.to(device)

# Load the model state
model_load_path = "C:/Users/bgpra/OneDrive/Documents/GitHub/Baby-GPT/friends_language_model.pth"
checkpoint = torch.load(model_load_path, map_location=torch.device(device))
model.load_state_dict(checkpoint['model_state_dict'])
model.eval()

print(f"Model loaded from {model_load_path}")

# Generate text
context = torch.zeros((1, 1), dtype=torch.long, device=device)
generated_text = decode(model.generate(context, max_new_tokens=50000)[0].tolist())
with open('C:/Users/bgpra/OneDrive/Documents/GitHub/Baby-GPT/Generated_script.txt','w',encoding='utf-8') as file:
    file.write(generated_text)

print("Script written into Generated_script.txt")