load model

gpt_load.py

@@ -0,0 +1,73 @@
+import torch
+import gradio as gr
+import tiktoken  # Import tiktoken for GPT-2 tokenization
+from gpt_parts import GPTModel  # Ensure gpt_parts.py contains your GPTModel definition
+
+# Configuration for GPT-2 model, same as used during training
+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
+    }
+
+# Initialize the tokenizer using tiktoken's GPT-2 encoding
+tokenizer = tiktoken.get_encoding("gpt2")
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model = GPTModel(GPT_CONFIG_124M).to(device)
+model.load_state_dict(torch.load("model.pth", map_location=device, weights_only=True))
+model.eval()  # Set model to evaluation mode
+
+def text_to_token_ids(text, tokenizer):
+    """Encode text to token IDs."""
+    encoded = tokenizer.encode(text)
+    return torch.tensor(encoded).unsqueeze(0)
+
+def token_ids_to_text(token_ids, tokenizer):
+    """Decode token IDs to text."""
+    return tokenizer.decode(token_ids.squeeze(0).tolist())
+
+def generate_text_simple(model, idx, max_new_tokens, context_size):
+    """Autoregressively generate new tokens."""
+    for _ in range(max_new_tokens):
+        idx_cond = idx[:, -context_size:]
+        with torch.no_grad():
+            logits = model(idx_cond)
+        logits = logits[:, -1, :]
+        idx_next = torch.argmax(logits, dim=-1, keepdim=True) 
+        idx = torch.cat((idx, idx_next), dim=1)
+    return idx
+
+# Define text generation function for Gradio
+def generate_text(start_context, max_new_tokens=50):
+    # Encode the starting context
+    encoded_input = text_to_token_ids(start_context, tokenizer).to(device)
+    
+    # Generate text
+    generated_token_ids = generate_text_simple(
+        model=model, 
+        idx=encoded_input, 
+        max_new_tokens=max_new_tokens, 
+        context_size=GPT_CONFIG_124M["context_length"]
+    )
+    
+    # Decode the generated tokens to text
+    generated_text = token_ids_to_text(generated_token_ids, tokenizer)
+    return generated_text.replace("\n", " ")
+
+iface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.Textbox(lines=2, placeholder="Enter starting text here...", label="Start Context"),
+        gr.Slider(minimum=1, maximum=100, step=1, label="Max New Tokens")
+    ],
+    outputs="text",
+    title="GPT-2 Text Generation",
+    description="Generate text using a fine-tuned GPT-2 model. Enter some starting text, and choose the maximum number of tokens to generate."
+)
+iface.launch(share=True)
+

gpt_parts.py

@@ -0,0 +1,132 @@
+import torch
+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_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