Upload 3 files

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+import torch
+from tiktoken import get_encoding
+from model import GPT, GPTConfig  # Replace with your actual model file/module
+
+# Load the GPT-2 tokenizer
+tokenizer = get_encoding("gpt2")
+
+# Load your custom model (adjust as necessary for your model's implementation)
+model_path = "model.pth"  # Replace with the path to your model weights
+model = GPT(GPTConfig())  # Initialize your custom model
+model.load_state_dict(torch.load(model_path, map_location=torch.device("cpu")))
+model.eval()  # Set the model to evaluation mode
+
+
+# Function to tokenize input and generate text
+def generate_text(prompt, max_length=50):
+    # Tokenize the input
+    input_ids = tokenizer.encode(prompt)
+    input_tensor = torch.tensor([input_ids])  # Add batch dimension
+
+    # Generate text using the model
+    with torch.no_grad():
+        output_ids = model.generate(input_tensor, max_length=max_length)  # Adjust if your model uses another method
+
+    # Decode the output back to text
+    generated_text = tokenizer.decode(output_ids[0].tolist())
+    return generated_text
+
+
+# Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Custom Transformer Text Generation")
+    gr.Markdown("Provide an input text prompt, and the model will generate text based on it.")
+
+    with gr.Row():
+        input_text = gr.Textbox(label="Input Prompt", placeholder="Enter your text here...", lines=2)
+        max_len = gr.Slider(label="Max Output Length", minimum=10, maximum=100, value=50, step=5)
+
+    output_text = gr.Textbox(label="Generated Text", lines=5)
+    generate_button = gr.Button("Generate")
+
+    generate_button.click(generate_text, inputs=[input_text, max_len], outputs=output_text)
+
+# Run the app
+if __name__ == "__main__":
+    demo.launch()

model.py

@@ -0,0 +1,202 @@
+# Solving for residual std scaling issue
+import os
+import math
+import time
+import inspect
+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 = 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 = 50257  # number of tokens: 50,000 BPE merges + 256 bytes tokens + 1 <|endoftext|> token
+    n_layer: int = 12  # number of layers
+    n_head: int = 8  # 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
+
+    @classmethod
+    def from_pretrained(cls, model_type):
+        """Loads pretrained GPT-2 model weights from huggingface"""
+        assert model_type in {'gpt2', 'gpt2-medium', 'gpt2-large', 'gpt2-xl'}
+        from transformers import GPT2LMHeadModel
+        print("loading weights from pretrained gpt: %s" % model_type)
+
+        # n_layer, n_head and n_embd are determined from model_type
+        config_args = {
+            'gpt2': dict(n_layer=12, n_head=12, n_embd=768),  # 124M params
+            'gpt2-medium': dict(n_layer=24, n_head=16, n_embd=1024),  # 350M params
+            'gpt2-large': dict(n_layer=36, n_head=20, n_embd=1280),  # 774M params
+            'gpt2-xl': dict(n_layer=48, n_head=25, n_embd=1600),  # 1558M params
+        }[model_type]
+        config_args['vocab_size'] = 50257  # always 50257 for GPT model checkpoints
+        config_args['block_size'] = 1024  # always 1024 for GPT model checkpoints
+        # create a from-scratch initialized minGPT model
+        config = GPTConfig(**config_args)
+        model = GPT(config)
+        sd = model.state_dict()
+        sd_keys = sd.keys()
+        sd_keys = [k for k in sd_keys if not k.endswith('.attn.bias')]  # discard this mask / buffer, not a param
+
+        # init a huggingface/transformers model
+        model_hf = GPT2LMHeadModel.from_pretrained(model_type)
+        sd_hf = model_hf.state_dict()
+
+        # copy while ensuring all of the parameters are aligned and match in names and shapes
+        sd_keys_hf = sd_hf.keys()
+        sd_keys_hf = [k for k in sd_keys_hf if not k.endswith('.attn.masked_bias')]  # ignore these, just a buffer
+        sd_keys_hf = [k for k in sd_keys_hf if not k.endswith('.attn.bias')]  # same, just the mask (buffer)
+        transposed = ['attn.c_attn.weight', 'attn.c_proj.weight', 'mlp.c_fc.weight', 'mlp.c_proj.weight']
+        # basically the openai checkpoints use a "Conv1D" module, but we only want to use a vanilla Linear
+        # this means that we have to transpose these weights when we import them
+        assert len(sd_keys_hf) == len(sd_keys), f"mismatched keys: {len(sd_keys_hf)} != {len(sd_keys)}"
+        for k in sd_keys_hf:
+            if any(k.endswith(w) for w in transposed):
+                # special treatment for the Conv1D weights we need to transpose
+                assert sd_hf[k].shape[::-1] == sd[k].shape
+                with torch.no_grad():
+                    sd[k].copy_(sd_hf[k].t())
+            else:
+                # vanilla copy over the other parameters
+                assert sd_hf[k].shape == sd[k].shape
+                with torch.no_grad():
+                    sd[k].copy_(sd_hf[k])
+
+        return model
+
+    def generate(self, input_tensor, max_length, EOS_TOKEN_ID=50256):
+        output_ids = input_tensor  # Start with input
+        self.eval()
+        for _ in range(max_length - input_tensor.size(1)):
+            logits = self(input_tensor)  # Forward pass
+            if isinstance(logits, tuple):
+                logits = logits[0]
+            next_token = torch.argmax(logits[:, -1, :], dim=-1)  # Get the next token
+            input_tensor = torch.cat([input_tensor, next_token.unsqueeze(0)], dim=1)
+            if next_token.item() == EOS_TOKEN_ID:  # Stop if end-of-sequence token is generated
+                break
+        return input_tensor

requirements.txt

@@ -0,0 +1,4 @@
+torch
+tiktoken
+dataclasses
+gradio