CustomClasses.py

import matplotlib.pyplot as plt
import numpy as np
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 = []

        token_ids = tokenizer.encode(txt, allowed_special={"<|endoftext|>"})

        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):

    tokenizer = tiktoken.get_encoding("gpt2")

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

    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 num_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)  # Optional 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)

        # 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)

        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]
        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.contiguous().view(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.epsilon = 1e-5 # To avoid division by zero errors, if variance is zero
        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.epsilon)
        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.attn = 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.ffn = FeedForward(cfg)
        self.norm1 = LayerNorm(cfg["emb_dim"])
        self.norm2 = LayerNorm(cfg["emb_dim"])
        self.dropout = nn.Dropout(cfg["drop_rate"])

    def forward(self, x):
        shortcut = x
        x = self.norm1(x)
        x = self.attn(x)
        x = self.dropout(x)
        x = x + shortcut  

        shortcut = x
        x = self.norm2(x)
        x = self.ffn(x)
        x = self.dropout(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_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
        x = self.drop_emb(x)
        x = self.trf_blocks(x)
        x = self.final_norm(x)
        logits = self.out_head(x)
        return logits
    
def generate_text(model, idx, max_new_tokens, context_size):
    # idx is (batch, n_tokens) array of indices in the current context
    for _ in range(max_new_tokens):
        
        # Crop current context if it exceeds the supported context size
        idx_cond = idx[:, -context_size:]
        with torch.no_grad():
            logits = model(idx_cond)
        
        # Extract the last vector
        generated_word = logits[:, -1, :]  
        probabilities = torch.softmax(generated_word, dim=-1)  # (batch, vocab_size)
        # Get the idx of the vocab entry with the highest probability value
        idx_next = torch.argmax(probabilities, dim=-1, keepdim=True)  # (batch, 1)

        # Append it to the running sequence
        idx = torch.cat((idx, idx_next), dim=1)  # (batch, n_tokens+1)

    return idx

def text_to_token_ids(text, tokenizer):
    encoded = tokenizer.encode(text, allowed_special={'<|endoftext|>'})
    encoded_tensor = torch.tensor(encoded).unsqueeze(0) # add batch dimension
    return encoded_tensor

def token_ids_to_text(token_ids, tokenizer):
    flat = token_ids.squeeze(0) # remove batch dimension
    return tokenizer.decode(flat.tolist())

def assign(left, right):
    if left.shape != right.shape:
        raise ValueError(f"Shape mismatch. Left: {left.shape}, Right: {right.shape}")
    return torch.nn.Parameter(torch.tensor(right))

import numpy as np

def load_weights_into_gpt(gpt, params):
    gpt.pos_emb.weight = assign(gpt.pos_emb.weight, params['wpe'])
    gpt.tok_emb.weight = assign(gpt.tok_emb.weight, params['wte'])
    
    for b in range(len(params["blocks"])):
        q_w, k_w, v_w = np.split((params["blocks"][b]["attn"]["c_attn"])["w"], 3, axis=-1)
        gpt.trf_blocks[b].attn.W_query.weight = assign(gpt.trf_blocks[b].attn.W_query.weight, q_w.T)
        gpt.trf_blocks[b].attn.W_key.weight = assign(gpt.trf_blocks[b].attn.W_key.weight, k_w.T)
        gpt.trf_blocks[b].attn.W_value.weight = assign(gpt.trf_blocks[b].attn.W_value.weight, v_w.T)

        q_b, k_b, v_b = np.split((params["blocks"][b]["attn"]["c_attn"])["b"], 3, axis=-1)
        gpt.trf_blocks[b].attn.W_query.bias = assign(gpt.trf_blocks[b].attn.W_query.bias, q_b)
        gpt.trf_blocks[b].attn.W_key.bias = assign(gpt.trf_blocks[b].attn.W_key.bias, k_b)
        gpt.trf_blocks[b].attn.W_value.bias = assign(gpt.trf_blocks[b].attn.W_value.bias, v_b)

        gpt.trf_blocks[b].attn.out_proj.weight = assign(gpt.trf_blocks[b].attn.out_proj.weight, params["blocks"][b]["attn"]["c_proj"]["w"].T)
        gpt.trf_blocks[b].attn.out_proj.bias = assign(gpt.trf_blocks[b].attn.out_proj.bias, params["blocks"][b]["attn"]["c_proj"]["b"])

        gpt.trf_blocks[b].ffn.layers[0].weight = assign(gpt.trf_blocks[b].ffn.layers[0].weight, params["blocks"][b]["mlp"]["c_fc"]["w"].T)
        gpt.trf_blocks[b].ffn.layers[0].bias = assign(gpt.trf_blocks[b].ffn.layers[0].bias, params["blocks"][b]["mlp"]["c_fc"]["b"])
        gpt.trf_blocks[b].ffn.layers[2].weight = assign(gpt.trf_blocks[b].ffn.layers[2].weight, params["blocks"][b]["mlp"]["c_proj"]["w"].T)
        gpt.trf_blocks[b].ffn.layers[2].bias = assign(gpt.trf_blocks[b].ffn.layers[2].bias, params["blocks"][b]["mlp"]["c_proj"]["b"])

        gpt.trf_blocks[b].norm1.scale = assign(gpt.trf_blocks[b].norm1.scale, params["blocks"][b]["ln_1"]["g"])
        gpt.trf_blocks[b].norm1.shift = assign(gpt.trf_blocks[b].norm1.shift, params["blocks"][b]["ln_1"]["b"])
        gpt.trf_blocks[b].norm2.scale = assign(gpt.trf_blocks[b].norm2.scale, params["blocks"][b]["ln_2"]["g"])
        gpt.trf_blocks[b].norm2.shift = assign(gpt.trf_blocks[b].norm2.shift, params["blocks"][b]["ln_2"]["b"])

    gpt.final_norm.scale = assign(gpt.final_norm.scale, params["g"])
    gpt.final_norm.shift = assign(gpt.final_norm.shift, params["b"])
    gpt.out_head.weight = assign(gpt.out_head.weight, params["wte"])

def generate(model, idx, max_new_tokens, context_size, temperature=0.0, top_k=None, eos_id=None):
    for _ in range(max_new_tokens):
        idx_cond = idx[:, -context_size:]
        with torch.no_grad():
            logits = model(idx_cond)
        logits = logits[:, -1, :]

        if top_k is not None:
            # Keep only top_k values
            top_logits, _ = torch.topk(logits, top_k)
            logits = torch.where(logits < top_logits[:, -1], torch.tensor(float("-inf")).to(logits.device), logits)

        if temperature > 0.0:
            logits /= temperature
            probs = torch.softmax(logits, dim=-1)
            idx_next = torch.multinomial(probs, num_samples=1)

        else:
            idx_next = torch.argmax(logits, dim=-1, keepdim=True)

        if idx_next == eos_id: break # Stop if end-of-sequence token is encountered

        # Append sampled index to the running sequence
        idx = torch.cat((idx, idx_next), dim=1)  # (batch_size, num_tokens+1)
    return idx

def train_model_simple(model, train_loader, val_loader, optimizer, device, num_epochs,
                       eval_freq, eval_iter, start_context, tokenizer):
    # Initialize lists to track losses and tokens seen
    train_losses, val_losses, track_tokens_seen = [], [], []
    tokens_seen, global_step = 0, -1

    # Main training loop
    for epoch in range(num_epochs):
        model.train()
        
        for input_batch, target_batch in train_loader:
            optimizer.zero_grad() # Reset loss gradients
            loss = calc_loss_batch(input_batch, target_batch, model, device)
            loss.backward() # Calculating loss gradients
            optimizer.step() # Updating model weights
            tokens_seen += input_batch.numel()
            global_step += 1

            # Every eval_freq steps, get losses to check if model is improving or not
            if global_step % eval_freq == 0: 
                train_loss, val_loss = evaluate_model(model, train_loader, val_loader, device, eval_iter)
                train_losses.append(train_loss)
                val_losses.append(val_loss)
                track_tokens_seen.append(tokens_seen)
                print(f"Ep {epoch+1} (Step {global_step:06d}): "
                      f"Train loss {train_loss:.3f}, Val loss {val_loss:.3f}")

        # Print a sample text after each epoch
        generate_and_print_sample(model, tokenizer, device, start_context)

    return train_losses, val_losses, track_tokens_seen

def evaluate_model(model, train_loader, val_loader, device, eval_iter):
    model.eval()
    with torch.no_grad():
        train_loss = calc_loss_loader(train_loader, model, device, num_batches=eval_iter)
        val_loss = calc_loss_loader(val_loader, model, device, num_batches=eval_iter)
    model.train()
    return train_loss, val_loss

def generate_and_print_sample(model, tokenizer, device, start_context):
    model.eval()
    context_size = model.pos_emb.weight.shape[0]
    encoded = text_to_token_ids(start_context, tokenizer).to(device)
    with torch.no_grad():
        token_ids = generate_text(model=model, idx=encoded, max_new_tokens=50, context_size=context_size)

    decoded_text = token_ids_to_text(token_ids, tokenizer)
    print(decoded_text.replace("\n", " "))
    model.train()

def calc_loss_batch(input_batch, target_batch, model, device):
    input_batch, target_batch = input_batch.to(device), target_batch.to(device) # Via the device setting, we ensure that the data is loaded onto the same device as the LLM model
    logits = model(input_batch)
    loss = torch.nn.functional.cross_entropy(logits.flatten(0, 1), target_batch.flatten())
    return loss

def calc_loss_loader(data_loader, model, device, num_batches=None):
    total_loss = 0.
    if len(data_loader) == 0:
        return float("nan")
    elif num_batches is None:
        num_batches = len(data_loader)
    else:
        num_batches = min(num_batches, len(data_loader))
    for i, (input_batch, target_batch) in enumerate(data_loader):
        if i < num_batches:
            loss = calc_loss_batch(input_batch, target_batch, model, device)
            total_loss += loss.item()
        else:
            break
    return total_loss / num_batches

def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses):
    fig, ax1 = plt.subplots(figsize=(5, 3))

    ax1.plot(epochs_seen, train_losses, label="Training loss")
    ax1.plot(epochs_seen, val_losses, linestyle="-.", label="Validation loss")
    ax1.set_xlabel("Epochs")
    ax1.set_ylabel("Loss")
    ax1.legend(loc="upper right")

    # Create a second x-axis for tokens seen
    ax2 = ax1.twiny()
    ax2.plot(tokens_seen, train_losses, alpha=0)
    ax2.set_xlabel("Tokens seen")

    fig.tight_layout()
    plt.show()