GPU_test.py

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

# --- GPU-Scale Hyperparameters ---
n_embd     = 384 
n_head     = 6
n_layer    = 6
block_size = 256
dropout    = 0.2
device     = 'cuda' if torch.cuda.is_available() else 'cpu'

# --- Architecture ---

class Head(nn.Module):
    def __init__(self, head_size):
        super().__init__()
        self.key   = nn.Linear(n_embd, head_size, bias=False)
        self.query = nn.Linear(n_embd, head_size, bias=False)
        self.value = 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(-2, -1) * k.shape[-1] ** -0.5
        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf'))
        wei = F.softmax(wei, dim=-1)
        wei = self.dropout(wei)
        return wei @ self.value(x)

class MultiHeadAttention(nn.Module):
    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(head_size * num_heads, n_embd)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        out = torch.cat([h(x) for h in self.heads], dim=-1)
        return self.dropout(self.proj(out))

class FeedFoward(nn.Module):
    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):
    def __init__(self, n_embd, n_head):
        super().__init__()
        head_size = n_embd // n_head
        self.sa   = MultiHeadAttention(n_head, head_size)
        self.ffwd = FeedFoward(n_embd)
        self.ln1  = nn.LayerNorm(n_embd)
        self.ln2  = nn.LayerNorm(n_embd)

    def forward(self, x):
        x = x + self.sa(self.ln1(x))
        x = x + self.ffwd(self.ln2(x))
        return x

class GPTLanguageModel(nn.Module):
    def __init__(self, vocab_size):
        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.ln_f                     = nn.LayerNorm(n_embd)
        self.lm_head                  = nn.Linear(n_embd, vocab_size)
        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):
        B, T    = idx.shape
        tok_emb = self.token_embedding_table(idx)
        pos_emb = self.position_embedding_table(torch.arange(T, device=device))
        x       = tok_emb + pos_emb
        x       = self.blocks(x)
        x       = self.ln_f(x)
        logits  = self.lm_head(x)
        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, _ = self(idx_cond)
            logits    = logits[:, -1, :]
            probs     = F.softmax(logits, dim=-1)
            idx_next  = torch.multinomial(probs, num_samples=1)
            idx       = torch.cat((idx, idx_next), dim=1)
        return idx

# --- TRAINING LOGIC WRAPPER ---
if __name__ == "__main__":
    # This part only runs if you execute transformer.py directly.
    # It points to your original data.txt
    dataset_path = 'data.txt' 
    if os.path.exists(dataset_path):
        with open(dataset_path, 'r', encoding='utf-8') as f:
            text = f.read()
        chars = sorted(list(set(text)))
        print(f"Data Loaded. Vocab size: {len(chars)}")
    else:
        print(f"File {dataset_path} not found.")