app.py

import streamlit as st
import torch
import tiktoken
from dataclasses import dataclass
import torch.nn as nn
from torch.nn import functional as F

@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 = 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 print_num_parameters(self):
        num_params = sum(p.numel() for p in self.parameters())
        print(f"Number of model parameters: {num_params}")

    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


# Load the trained model
@st.cache_resource
def load_model():
    config = GPTConfig()
    model = GPT(config)
    try:
        # Load the model with map_location to handle CPU-only environments
        model.load_state_dict(torch.load('trained_model_quantized.pt', map_location=torch.device('cpu')), strict=False)
        model.eval()  # Set the model to evaluation mode
        st.success("Model loaded successfully!")
    except Exception as e:
        st.error(f"Error loading model: {e}")
    return model

# Load the tokenizer
def load_tokenizer():
    return tiktoken.get_encoding('gpt2')

# Generate text function
def generate_text(model, tokenizer, input_text, length, num_sequences):
    # Encode the input text
    input_ids = tokenizer.encode(input_text)
    input_tensor = torch.tensor(input_ids).unsqueeze(0)  # Add batch dimension (shape: [1, T])

    generated_sequences = []
    for _ in range(num_sequences):
        # Generate additional tokens
        with torch.no_grad():
            for _ in range(length):
                logits = model(input_tensor)[0]  # Get logits
                next_token_logits = logits[:, -1, :]  # Get the last token's logits
                next_token_probs = torch.softmax(next_token_logits, dim=-1)
                next_token = torch.multinomial(next_token_probs, num_samples=1)  # Sample from the distribution
                
                # Ensure the next_token has the correct shape for concatenation
                next_token = next_token.view(1, -1)  # Reshape to [1, 1] if necessary
                input_tensor = torch.cat((input_tensor, next_token), dim=1)  # Append the new token

        # Decode the generated tokens
        generated_sequences.append(tokenizer.decode(input_tensor[0].tolist()))

    return generated_sequences

# Streamlit app layout
st.title("GPT Text Generator")
st.write("Enter your text and specify the length of additional text to generate.")

input_text = st.text_area("Input Text", "Once upon a time", max_chars=512)  # Limit to 512 characters
length = st.slider("Predict Additional Text of Length", 1, 50, 10)
num_sequences = st.slider("Number of Sequences to Generate", 1, 5, 1)

if st.button("Generate"):
    model = load_model()  # Load the model for inference
    tokenizer = load_tokenizer()  # Load the tokenizer
    st.write("Generating text...")
    generated_texts = generate_text(model, tokenizer, input_text, length, num_sequences)
    st.write("Text generation complete.")

    st.write("Generated Texts:")
    for i, text in enumerate(generated_texts):
        st.subheader(f"Sequence {i + 1}")
        st.write(text)