Upload 3 files

Created a hugging face application to print Shakespear like text

app.py

@@ -0,0 +1,88 @@
+import gradio as gr
+import torch
+import torch.nn.functional as F
+import tiktoken
+from huggingface_hub import hf_hub_download
+from transformers import GPT, GPTConfig  # Import your model class
+
+# Load the model from Hugging Face Hub
+def load_model_from_huggingface(device):
+    # Replace with your Hugging Face model ID (username/model-name)
+    model_id = "EzhirkoArulmozhi/DecoderTransformerModel"
+    checkpoint_path = hf_hub_download(repo_id=model_id, filename="gpt_checkpoint.pth")
+    
+    checkpoint = torch.load(checkpoint_path, map_location=device)
+    config = checkpoint['config']
+    model = GPT(config)
+    model.load_state_dict(checkpoint['model_state_dict'])
+    model.to(device)
+    model.eval()  # Set to evaluation mode
+    
+    # Disable gradient computation
+    for param in model.parameters():
+        param.requires_grad = False
+    return model
+
+def generate_text(model, device, prompt, max_length=100, num_samples=1):
+    enc = tiktoken.get_encoding('gpt2')
+    tokens = enc.encode(prompt)
+    tokens = torch.tensor(tokens, dtype=torch.long)
+    tokens = tokens.unsqueeze(0).repeat(num_samples, 1)
+    tokens = tokens.to(device)
+    
+    with torch.no_grad():
+        for _ in range(max_length):
+            if tokens.size(1) >= 1024:  # GPT context length
+                break
+                
+            logits = model(tokens)[0]
+            logits = logits[:, -1, :]
+            probs = F.softmax(logits, dim=-1)
+            
+            # Top-k sampling
+            topk_probs, topk_indices = torch.topk(probs, 50, dim=-1)
+            ix = torch.multinomial(topk_probs, 1)
+            next_token = torch.gather(topk_indices, -1, ix)
+            
+            tokens = torch.cat((tokens, next_token), dim=1)
+            
+            # Remove special token check entirely
+            # Just generate for the specified length or until context limit
+    
+    generated_texts = []
+    for i in range(num_samples):
+        text = enc.decode(tokens[i].tolist())
+        generated_texts.append(text)
+    
+    return '\n\n---\n\n'.join(generated_texts)
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+model = load_model_from_huggingface(device)
+# Force model to stay in eval mode
+model.train(False)
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        model,
+        device,
+        gr.Textbox(label="Prompt", value="We are accounted poor citizens, the"),
+        gr.Slider(minimum=10, maximum=200, value=100, step=1, label="Max Length"),
+        gr.Slider(minimum=1, maximum=5, value=1, step=1, label="Number of Samples"),
+    ],
+    outputs=gr.Textbox(label="Generated Text"),
+    title="Shakespeare-style Text Generator",
+    description="Enter a prompt to generate Shakespeare-style text continuation",
+    examples=[
+        ["O Romeo, Romeo, wherefore art thou", 100, 1],
+        ["To be, or not to be, that is", 60, 2],
+        ["Friends, Romans, countrymen, lend me", 50, 3],
+        ["All the world's a stage, and all the", 100, 1],
+        ["Now is the winter of our discontent", 100, 1],
+        ["If music be the food of love,", 100, 1],
+    ]
+)
+
+if __name__ == "__main__":
+    iface.launch() 

requirement.txt

@@ -0,0 +1,5 @@
+torch
+gradio
+tiktoken
+transformers 
+huggingface_hub

transformers.py

@@ -0,0 +1,129 @@
+from dataclasses import dataclass
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+class CausalSelfAttention(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        assert config.n_embd % config.n_head == 0
+        # key, query, value projections for all heads, but in a batch
+        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
+        # output projection
+        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
+        self.c_proj.NANGPT_SCALE_INIT = 1
+        # regularization
+        self.n_head = config.n_head
+        self.n_embd = config.n_embd
+        self.register_buffer("bias", torch.tril(torch.ones(config.block_size, config.block_size)).view(1, 1, config.block_size, config.block_size))
+
+    def forward(self, x):
+        B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
+        # calculate query, key, values for all heads in batch and move head forward to be the batch dim
+        # nh is "number of heads", hs is "head size", and C (number of channels) = nh * hs
+        # e.g. in GPT-2 (124M), n_head=12, hs=64, so nh*hs=C=768 channels in the Transformer
+        qkv = self.c_attn(x)
+        q, k, v = qkv.split(self.n_embd, dim=2)
+        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+
+        # att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
+        # att = att.masked_fill(self.bias[:, :, :T, :T] == 0, float('-inf'))
+        # att = F.softmax(att, dim=-1)
+        # y = att @ v # (B, nh, T, T) x (B, nh, T, hs) -> (B, nh, T, hs)
+
+        y = F.scaled_dot_product_attention(q, k, v, is_causal = True) # Flash attention
+
+        y = y.transpose(1, 2).contiguous().view(B, T, C) # re-assemble all head outputs side by side
+        # output projection
+        y = self.c_proj(y)
+        return y
+
+class MLP(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.c_fc    = nn.Linear(config.n_embd, 4 * config.n_embd)
+        self.gelu    = nn.GELU(approximate='tanh')
+        self.c_proj  = nn.Linear(4 * config.n_embd, config.n_embd)
+        self.c_proj.NANOGPT_SCALE_INIT = 1
+
+    def forward(self, x):
+        x = self.c_fc(x)
+        x = self.gelu(x)
+        x = self.c_proj(x)
+        return x
+
+class Block(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.ln_1 = nn.LayerNorm(config.n_embd)
+        self.attn = CausalSelfAttention(config)
+        self.ln_2 = nn.LayerNorm(config.n_embd)
+        self.mlp = MLP(config)
+
+    def forward(self, x):
+        x = x + self.attn(self.ln_1(x))
+        x = x + self.mlp(self.ln_2(x))
+        return x
+
+@dataclass
+class GPTConfig:
+    block_size: int = 1024 # max sequence length
+    vocab_size: int = 50304 # number of tokens: 50,000 BPE merges + 256 bytes tokens + 1 <|endoftext|> token
+    n_layer: int = 12 # number of layers
+    n_head: int = 12 # number of heads
+    n_embd: int = 768 # embedding dimension
+
+class GPT(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.config = config
+
+        self.transformer = nn.ModuleDict(dict(
+            wte = nn.Embedding(config.vocab_size, config.n_embd),
+            wpe = nn.Embedding(config.block_size, config.n_embd),
+            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
+            ln_f = nn.LayerNorm(config.n_embd),
+        ))
+        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+
+        # weight sharing
+        self.transformer.wte.weight = self.lm_head.weight
+
+        # weight initialization
+        self.apply(self._init_weights)
+
+    def _init_weights(self, module):
+        if isinstance(module, nn.Linear):
+            std = 0.02
+            if hasattr(module, 'NANGPT_SCALE_INIT'):
+                std *= (2 * self.config.n_layer) ** -0.5
+            torch.nn.init.normal_(module.weight, mean = 0.0, std = std)
+            if module.bias is not None:
+                torch.nn.init.zeros_(module.bias)
+        elif isinstance(module, nn.Embedding):
+            torch.nn.init.normal_(module.weight, mean=0.0, std = 0.02)
+    
+    def forward(self, idx, targets=None):
+        # idx is of shape (B, T)
+        B, T = idx.size()
+        assert T <= self.config.block_size, f"Cannot forward sequence of length {T}, block size is only {self.config.block_size}"
+        # forward the token and posisition embeddings
+        pos = torch.arange(0, T, dtype=torch.long, device=idx.device) # shape (T)
+        pos_emb = self.transformer.wpe(pos) # position embeddings of shape (T, n_embd)
+        tok_emb = self.transformer.wte(idx) # token embeddings of shape (B, T, n_embd)
+        x = tok_emb + pos_emb
+        # forward the blocks of the transformer
+        for block in self.transformer.h:
+            x = block(x)
+        # forward the final layernorm and the classifier
+        x = self.transformer.ln_f(x)
+        logits = self.lm_head(x) # (B, T, vocab_size)
+        loss = None
+        if targets is not None:
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
+        return logits, loss