generate_fullcode.py

import torch
import tiktoken
import gdown
import os
import torch.nn as nn

class MultiHeadAttention(nn.Module):
    def __init__(self, d_in, d_out, context_length, dropout, num_heads, qkv_bias=False):
        super().__init__()
        assert d_out % num_heads == 0, "d_out must be divisible by n_heads"
        self.d_out = d_out
        self.num_heads = num_heads
        self.head_dim = d_out // num_heads
        self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.out_proj = nn.Linear(d_out, d_out)
        self.dropout = nn.Dropout(dropout)
        self.register_buffer('mask', torch.triu(torch.ones(context_length, context_length), diagonal=1))

    def forward(self, x):
        b, num_tokens, d_in = x.shape
        keys = self.W_key(x)
        queries = self.W_query(x)
        values = self.W_value(x)
        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
        values = values.view(b, num_tokens, self.num_heads, self.head_dim)
        queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
        keys = keys.transpose(1, 2)
        queries = queries.transpose(1, 2)
        values = values.transpose(1, 2)
        attn_scores = queries @ keys.transpose(2, 3)
        mask_bool = self.mask.bool()[:num_tokens, :num_tokens]
        attn_scores.masked_fill_(mask_bool, -torch.inf)
        attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1)
        attn_weights = self.dropout(attn_weights)
        context_vec = (attn_weights @ values).transpose(1, 2)
        context_vec = context_vec.reshape(b, num_tokens, self.d_out)
        context_vec = self.out_proj(context_vec)
        return context_vec

class LayerNorm(nn.Module):
    def __init__(self, emb_dim):
        super().__init__()
        self.eps = 1e-5
        self.scale = nn.Parameter(torch.ones(emb_dim))
        self.shift = nn.Parameter(torch.zeros(emb_dim))

    def forward(self, x):
        mean = x.mean(dim=-1, keepdim=True)
        var = x.var(dim=-1, keepdim=True, unbiased=False)
        norm_x = (x - mean) / torch.sqrt(var + self.eps)
        return self.scale * norm_x + self.shift

class GELU(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):
        return 0.5 * x * (1 + torch.tanh(
            torch.sqrt(torch.tensor(2.0 / torch.pi)) *
            (x + 0.044715 * torch.pow(x, 3))
        ))

class FeedForward(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.layers = nn.Sequential(
            nn.Linear(cfg["emb_dim"], 4 * cfg["emb_dim"]),
            GELU(),
            nn.Linear(4 * cfg["emb_dim"], cfg["emb_dim"]),
        )

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

class TransformerBlock(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.att = MultiHeadAttention(
            d_in=cfg["emb_dim"],
            d_out=cfg["emb_dim"],
            context_length=cfg["context_length"],
            num_heads=cfg["n_heads"],
            dropout=cfg["drop_rate"],
            qkv_bias=cfg["qkv_bias"])
        self.ff = FeedForward(cfg)
        self.norm1 = LayerNorm(cfg["emb_dim"])
        self.norm2 = LayerNorm(cfg["emb_dim"])
        self.drop_shortcut = nn.Dropout(cfg["drop_rate"])

    def forward(self, x):
        shortcut = x
        x = self.norm1(x)
        x = self.att(x)
        x = self.drop_shortcut(x)
        x = x + shortcut
        shortcut = x
        x = self.norm2(x)
        x = self.ff(x)
        x = self.drop_shortcut(x)
        x = x + shortcut
        return x

class GPTModel(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.tok_emb = nn.Embedding(cfg["vocab_size"], cfg["emb_dim"])
        self.pos_emb = nn.Embedding(cfg["context_length"], cfg["emb_dim"])
        self.drop_emb = nn.Dropout(cfg["drop_rate"])
        self.trf_blocks = nn.Sequential(
            *[TransformerBlock(cfg) for _ in range(cfg["n_layers"])]
        )
        self.final_norm = LayerNorm(cfg["emb_dim"])
        self.out_head = nn.Linear(cfg["emb_dim"], cfg["vocab_size"], bias=False)

    def forward(self, in_encoded_tensor):
        batch_size, seq_len = in_encoded_tensor.shape
        tok_embeds = self.tok_emb(in_encoded_tensor)
        pos_embeds = self.pos_emb(torch.arange(seq_len, device=in_encoded_tensor.device))
        x = tok_embeds + pos_embeds
        x = self.drop_emb(x)
        x = self.trf_blocks(x)
        x = self.final_norm(x)
        logits = self.out_head(x)
        return logits

GPT_CONFIG = {
    "vocab_size": 50257,
    "context_length": 256,
    "emb_dim": 768,
    "n_heads": 12,
    "n_layers": 12,
    "drop_rate": 0.1,
    "qkv_bias": False
}

FILE_ID = "1mkhifEI6HQoiVahnGgZaRYsVU23req_M"
MODEL_PATH = "model.pth"
if not os.path.exists(MODEL_PATH):
    try:
        print("Downloading model.pth from Google Drive...")
        url = f"https://drive.google.com/uc?id={FILE_ID}"
        gdown.download(url, MODEL_PATH, quiet=False, verify=False)
        print("Download completed.")
    except Exception as e:
        print(f"Error downloading model.pth: {e}")
else:
    print("model.pth already exists.")

model = GPTModel(GPT_CONFIG)
device = torch.device("cpu")
model.to(device)
model.load_state_dict(torch.load(MODEL_PATH, map_location=device, weights_only=True))
tokenizer = tiktoken.get_encoding("gpt2")

start_context = input("Start Context: ")
maxx = input("Max new tokens: ")
assert maxx.isdigit(), "tokens must be integer"
maxx = int(maxx)
encoded = tokenizer.encode(start_context)
encoded_tensor = torch.tensor(encoded).unsqueeze(0)
for _ in range(maxx):
        encoded_tensor_cond = encoded_tensor[:, -GPT_CONFIG["context_length"]:]
        with torch.no_grad():
            logits = model(encoded_tensor_cond)
        logits = logits[:, -1, :]
        encoded_tensor_next = torch.argmax(logits, dim=-1, keepdim=True)
        encoded_tensor = torch.cat((encoded_tensor, encoded_tensor_next), dim=1)
decoded_text = tokenizer.decode(encoded_tensor.squeeze(0).tolist())
print("Output:", decoded_text)