Create app.py

app.py

@@ -0,0 +1,520 @@
+import tiktoken
+import torch
+import time
+import math
+from torch.utils.data import Dataset, DataLoader
+
+import gradio as gr
+import torch.nn as nn
+
+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
+
+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 attnetion 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 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 attnetion 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 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 # 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)
+        
+        # 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.contiguous().view(b, num_tokens, self.d_out)
+        context_vec = self.out_proj(context_vec) # optional projection
+
+        return context_vec
+    
+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 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 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
+
+
+
+
+GPT_CONFIG_124M = {
+    "vocab_size": 50257,   # Vocabulary size
+    "context_length": 256, # Shortended context length (orig: 1024)
+    "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
+}
+
+model = GPTModel(GPT_CONFIG_124M)
+
+def generate(model, idx, max_new_tokens, context_size, tokenizer, text_to_token_ids, temperature=0.0, top_k=None, eos_id=None):
+
+    # For-loop is the same as before: Get logits, and only focus on last time step
+    for _ in range(max_new_tokens):
+        idx_cond = idx[:, -context_size:]
+        with torch.no_grad():
+            logits = model(idx_cond)
+        logits = logits[:, -1, :]
+
+        # New: Filter logits with top_k sampling
+        if top_k is not None:
+            # Keep only top_k values
+            top_logits, _ = torch.topk(logits, top_k)
+            min_val = top_logits[:, -1]
+            logits = torch.where(logits < min_val, torch.tensor(float("-inf")).to(logits.device), logits)
+        
+        # New: Apply temperature scaling
+        if temperature > 0.0:
+            logits = logits / temperature
+
+            # Apply softmax to get probabilities
+            probs = torch.softmax(logits, dim=-1) # (batch_size, context_len)
+
+            # Sample from the distribution
+            idx_next = torch.multinomial(probs, num_samples=1) # (batch_size, 1)
+        
+        # Otherwise, same as before: get the idx of the vocab entry with the highest logits value
+        else:
+            idx_next = torch.argmax(logits, dim=-1, keepdim=True) # (batch_size, 1)
+        
+        if idx_next == eos_id: # Stop generating early if end-of-sequence token is encountered and eos_id is specified
+            break
+        
+        # if idx_next == text_to_token_ids(".", tokenizer):
+        if idx_next == "tensor([[13]])":
+            # idx_next = idx_next + text_to_token_ids("Meow.", tokenizer)
+            print("\nperiod\n")
+        
+        # if idx_next == text_to_token_ids("?", tokenizer):
+        if idx_next == "tensor([[30]])":
+            # idx_next = idx_next + text_to_token_ids("Meow.", tokenizer)
+            print("\nperiod\n")
+        
+        # if idx_next == text_to_token_ids("!", tokenizer):
+        if idx_next == "tensor([[0]])":
+            # idx_next = idx_next + text_to_token_ids("Meow.", tokenizer)
+            print("\nperiod\n")
+        
+        # print(idx_next)
+        # print("----")
+        # print(idx_next + text_to_token_ids("Meow.", tokenizer))
+        # test = idx_next + text_to_token_ids("Meow.", tokenizer)
+        # print("------")
+        # print(token_ids_to_text(idx_next, tokenizer))
+        # Same as before: append sampled index to the running sequence
+        idx = torch.cat((idx, idx_next), dim=1) # (batch_size, num_tokens+1)
+        new_idx = re.sub(".", ". Meow.", idx)
+    
+    return new_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 train_model(model, train_loader, val_loader, optimizer, device,
+                n_epochs, eval_freq, eval_iter, start_context, tokenizer,
+                warmup_steps, initial_lr=3e-05, min_lr=1e-6):
+    
+    train_losses, val_losses, track_tokens_seen, track_lrs = [], [], [], []
+    tokens_seen, global_step = 0, -1
+
+    # Retrieve the maximum learning rate from the optimizer
+    peak_lr = optimizer.param_groups[0]["lr"]
+
+    # Calculate the total number of iterations in the training process
+    total_training_steps = len(train_loader) * n_epochs
+
+    # Calculate the learning rate increment during the warmup phase
+    lr_increment = (peak_lr - initial_lr) / warmup_steps
+
+    for epoch in range(n_epochs):
+        model.train()
+        for input_batch, target_batch in train_loader:
+            optimizer.zero_grad()
+            global_step += 1
+
+            # Adjust the learning rate based on the current phase (warmup or cosine annealing)
+            if global_step < warmup_steps:
+                # Linear warmup
+                lr = initial_lr + global_step * lr_increment
+            else:
+                # Cosine annealing after warmup
+                progress = ((global_step - warmup_steps) /
+                            (total_training_steps - warmup_steps))
+                lr = min_lr + (peak_lr - min_lr) * 0.5 * (1 + math.cos(math.pi * progress))
+            
+            # Apply the calculated learning rate to the optimizer
+            for param_group in optimizer.param_groups:
+                param_group["lr"] = lr
+            track_lrs.append(lr) # Store the current learning rate
+
+            # Calculate and backpropagate the loss
+            loss = calc_loss_batch(input_batch, target_batch, model, device)
+            loss.backward()
+
+            # Apply gradient clipping after the warmup phase to avoid exploding gradients
+            if global_step > warmup_steps:
+                torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
+            
+            optimizer.step()
+            tokens_seen += input_batch.numel()
+
+            # Periodically evaluate the model on the training and validation sets
+            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 the current losses
+                print(f"Ep {epoch+1} (Iter {global_step:06d}): "
+                      f"Train loss {train_loss:.3f}, "
+                      f"Val loss {val_loss:.3f}"
+                )
+
+        # Generate and print a sample from the model to monitor progress
+        generate_and_print_sample(
+            model, tokenizer, device, start_context
+        )
+    
+    return train_losses, val_losses, track_tokens_seen, track_lrs
+
+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") # A - Initalize the tokenizer
+    dataset = GPTDatasetV1(txt, tokenizer, max_length, stride) # B - Create dataset
+    dataloader = DataLoader(
+        dataset,
+        batch_size=batch_size,
+        shuffle=shuffle,
+        drop_last=drop_last, # C - drop_last=True drops the last batch if it is shorter than the specified batch_size to prevent loss spikes during training
+        num_workers=0 # D - The number of CPU processes to use for preprocessing
+    )
+
+    return dataloader
+
+
+
+class GPTDatasetV1(Dataset):
+    def __init__(self, txt, tokenizer, max_length, stride):
+        self.tokenizer = tokenizer
+        self.input_ids = []
+        self.target_ids = []
+
+        token_ids = tokenizer.encode(txt) # A
+
+        for i in range(0, len(token_ids) - max_length, stride): # B
+            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 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_simple(
+            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", " ")) # Compact print format
+    model.train()
+
+def calc_loss_batch(input_batch, target_batch, model, device):
+    input_batch, target_batch = input_batch.to(device), target_batch.to(device)
+    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:
+        # Reduce the number of batches to match the total number of batches in the data loader
+        # if num_batches exceeds the number of batches in the data loader
+        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 generate_text_simple(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:]
+
+        # get the predictions
+        with torch.no_grad():
+            logits = model(idx_cond)
+        
+        # Focus only on the last time step
+        # (batch, n_tokens, vocab_size) becomes (batch, vocab_size)
+        logits = logits[:, -1, :]
+
+        # apply softmax to get the probabilities
+        probas = torch.softmax(logits, dim=-1) # (batch, vocab_size)
+
+        # Get the idx of the vocab entry with the highest probability value
+        idx_next = torch.argmax(probas, dim=-1, keepdim=True) # (batch, 1)
+
+        # if idx_next == text_to_token_ids(".", tokenizer):
+        #     idx_next = idx_next + text_to_token_ids("Meow.", tokenizer)
+        
+        # if idx_next == text_to_token_ids("?", tokenizer):
+        #     idx_next = idx_next + text_to_token_ids("Meow.", tokenizer)
+        
+        # if idx_next == text_to_token_ids("!", tokenizer):
+        #     idx_next = idx_next + text_to_token_ids("Meow.", tokenizer)
+
+        # Append sampled index to the running sequence
+        idx = torch.cat((idx, idx_next), dim=1) # (batch , n_tokens+1)
+
+    return idx
+
+def main(input_text, max_new_tokens):
+
+    tokenizer = tiktoken.get_encoding("gpt2")
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+    if torch.cuda.is_available():
+        device = torch.device("cuda")
+    elif torch.backends.mps.is_available():
+        device = torch.device("mps")
+    else:
+        device = torch.device("cpu")
+
+    weights = torch.load("model_and_optimizer.pth", map_location=torch.device(device))
+
+    model = GPTModel({
+    "vocab_size": 50257,   # Vocabulary size
+    "context_length": 512, # Shortened context length (orig: 1024)
+    "emb_dim": 768,        # Embedding dimension
+    "n_heads": 12,         # Number of attention heads
+    "n_layers": 12,        # Number of layers
+    "drop_rate": 0.3,      # Dropout rate
+    "qkv_bias": False      # Query-key-value bias
+    }).to(device)
+    model.load_state_dict(weights)
+    model.eval()
+
+    context_size = model.pos_emb.weight.shape[0]
+    encoded = torch.tensor(tokenizer.encode(input_text.strip())).unsqueeze(0).to(device)
+
+    with torch.no_grad():
+        token_ids = generate_text_simple(
+            model=model, idx=encoded,
+            max_new_tokens=max_new_tokens, context_size=context_size,
+            top_k=25, temperature=1.4, text_to_token_ids=text_to_token_ids, tokenizer=tokenizer
+        )
+        return tokenizer.decode(token_ids.squeeze(0).tolist())
+
+# if __name__ == "__main__":
+#     gr.Interface(fn=main, inputs=[gr.Textbox(label='Starting context'), gr.Number(label="Maximum output tokens")], outputs=[gr.Textbox(label="Response:")], title="CatGPT", article="Meow").launch()
+
+thing = gr.Interface(fn=main, theme=gr.themes.Soft(primary_hue="pink", secondary_hue="stone"), inputs=[gr.Textbox(label='Starting context'), gr.Number(label="Maximum output tokens")], outputs=[gr.Textbox(label="Response:")], title="CatGPT", article="Meow")
+
+
+if __name__ == "__main__":
+    thing.launch()