modeling_gpt2_custom.py

import tiktoken
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader


class GPTDatasetV1(Dataset):
    def __init__(self, txt, tokenizer, max_length, stride):
        self.input_ids = []
        self.target_ids = []

        # Check if txt is a generator (streaming mode)
        if hasattr(txt, "__iter__") and not isinstance(txt, (str, bytes)):
            # Process data in chunks for streamed input
            all_tokens = []
            for chunk in txt:
                if isinstance(chunk, str):
                    chunk_tokens = tokenizer.encode(
                        chunk, allowed_special={"<|endoftext|>"}
                    )
                    all_tokens.extend(chunk_tokens)

                    # Process accumulated tokens when we have enough for at least one sequence
                    while len(all_tokens) >= max_length + 1:
                        input_chunk = all_tokens[:max_length]
                        target_chunk = all_tokens[1 : max_length + 1]
                        self.input_ids.append(torch.tensor(input_chunk))
                        self.target_ids.append(torch.tensor(target_chunk))

                        # Remove processed tokens with stride
                        all_tokens = all_tokens[stride:]
        else:
            # Original implementation for string input
            token_ids = tokenizer.encode(txt, allowed_special={"<|endoftext|>"})

            # Use a sliding window to chunk the book into overlapping sequences of max_length
            for i in range(0, len(token_ids) - max_length, stride):
                input_chunk = token_ids[i : i + max_length]
                target_chunk = token_ids[i + 1 : i + max_length + 1]
                self.input_ids.append(torch.tensor(input_chunk))
                self.target_ids.append(torch.tensor(target_chunk))

    def __len__(self):
        return len(self.input_ids)

    def __getitem__(self, idx):
        return self.input_ids[idx], self.target_ids[idx]


def create_dataloader_v1(
    txt,
    batch_size=4,
    max_length=256,
    stride=128,
    shuffle=True,
    drop_last=True,
    num_workers=0,
):
    # Initialize the tokenizer
    tokenizer = tiktoken.get_encoding("gpt2")

    # Create dataset
    dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)

    # Create dataloader
    dataloader = DataLoader(
        dataset,
        batch_size=batch_size,
        shuffle=shuffle,
        drop_last=drop_last,
        num_workers=num_workers,
    )

    return dataloader


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
        )  # Reduce the projection dim to match desired output dim

        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)  # Linear layer to combine head outputs
        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)  # Shape: (b, num_tokens, d_out)
        queries = self.W_query(x)
        values = self.W_value(x)

        # We implicitly split the matrix by adding a `num_heads` dimension
        # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
        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)

        # Transpose: (b, num_tokens, num_heads, head_dim) -> (b, num_heads, num_tokens, head_dim)
        keys = keys.transpose(1, 2)
        queries = queries.transpose(1, 2)
        values = values.transpose(1, 2)

        # Compute scaled dot-product attention (aka self-attention) with a causal mask
        attn_scores = queries @ keys.transpose(2, 3)  # Dot product for each head

        # Original mask truncated to the number of tokens and converted to boolean
        mask_bool = self.mask.bool()[:num_tokens, :num_tokens]

        # Use the mask to fill attention scores
        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)

        # Shape: (b, num_tokens, num_heads, head_dim)
        context_vec = (attn_weights @ values).transpose(1, 2)

        # Combine heads, where self.d_out = self.num_heads * self.head_dim
        context_vec = context_vec.reshape(b, num_tokens, self.d_out)
        context_vec = self.out_proj(context_vec)  # optional projection

        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 connection for attention block
        shortcut = x
        x = self.norm1(x)
        x = self.att(x)  # Shape [batch_size, num_tokens, emb_size]
        x = self.drop_shortcut(x)
        x = x + shortcut  # Add the original input back

        # Shortcut connection for feed-forward block
        shortcut = x
        x = self.norm2(x)
        x = self.ff(x)
        x = self.drop_shortcut(x)
        x = x + shortcut  # Add the original input back

        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_idx):
        batch_size, seq_len = in_idx.shape
        tok_embeds = self.tok_emb(in_idx)
        pos_embeds = self.pos_emb(torch.arange(seq_len, device=in_idx.device))
        x = tok_embeds + pos_embeds  # Shape [batch_size, num_tokens, emb_size]
        x = self.drop_emb(x)
        x = self.trf_blocks(x)
        x = self.final_norm(x)
        logits = self.out_head(x)
        return logits


import torch.nn.functional as F


def generate_text_simple(
    model,
    idx,
    max_new_tokens: int,
    context_size: int,
    temperature=1.0,
    stream=False,
    tokenizer=None,
):
    """
    If stream=True: return a generator that yields decoded tokens one at a time.
    If stream=False: return the full generated tensor.
    """
    if tokenizer is None:
        raise ValueError("Tokenizer must be provided for decoding.")

    def _gen():
        nonlocal idx
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -context_size:]
            with torch.no_grad():
                logits = model(idx_cond)
            logits = logits[:, -1, :] / temperature
            probs = F.softmax(logits, dim=-1)
            idx_next = torch.multinomial(probs, num_samples=1)
            idx = torch.cat((idx, idx_next), dim=1)
            yield tokenizer.decode(idx_next[0].tolist())

    if stream:
        return _gen()
    else:
        from loguru import logger

        logger.info("stream=False")
        # run through generator silently, but collect idx
        for _ in _gen():
            pass
        return idx


if __name__ == "__main__":

    GPT_CONFIG_124M = {
        "vocab_size": 50257,  # Vocabulary size
        "context_length": 1024,  # Context length
        "emb_dim": 768,  # Embedding dimension
        "n_heads": 12,  # Number of attention heads
        "n_layers": 12,  # Number of layers
        "drop_rate": 0.1,  # Dropout rate
        "qkv_bias": False,  # Query-Key-Value bias
    }

    torch.manual_seed(123)
    model = GPTModel(GPT_CONFIG_124M)
    model.eval()  # disable dropout

    start_context = "Hello, I am"

    tokenizer = tiktoken.get_encoding("gpt2")
    encoded = tokenizer.encode(start_context)
    encoded_tensor = torch.tensor(encoded).unsqueeze(0)

    print(f"\n{50*'='}\n{22*' '}IN\n{50*'='}")
    print("\nInput text:", start_context)
    print("Encoded input text:", encoded)
    print("encoded_tensor.shape:", encoded_tensor.shape)

    out = generate_text_simple(
        model=model,
        idx=encoded_tensor,
        max_new_tokens=10,
        context_size=GPT_CONFIG_124M["context_length"],
    )
    decoded_text = tokenizer.decode(out.squeeze(0).tolist())

    print(f"\n\n{50*'='}\n{22*' '}OUT\n{50*'='}")
    print("\nOutput:", out)
    print("Output length:", len(out[0]))
    print("Output text:", decoded_text)