import streamlit as st 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 device = 'cpu' if torch.cuda.is_available(): device = 'cuda' elif hasattr(torch.backends, "mps") and torch.backends.mps.is_available(): device = "mps" #print(f"using device: {device}") # SEED torch.manual_seed(1337) if torch.cuda.is_available(): torch.cuda.manual_seed(1337) # CHANGES IN CURRENT CODE torch.set_float32_matmul_precision('high') model = GPT(GPTConfig()) model = torch.load('curr_model.pth', map_location=torch.device(device)) model.to(device) model.eval() st.title("Shakespearean Text Generation with GPT-2 Model") # User input for text, num_return_sequences, and max_length input_text = st.text_area("Enter initialization text:", "") num_return_sequences = st.number_input("Number of return sequences:", min_value=1, value=1, step=1) max_length = st.number_input("Maximum length of generated text:", min_value=10, value=50, step=1) # Set default values default_text = "Hello, I'm a language model," default_num_return_sequences = 1 default_max_length = 50 # Use user input if provided, otherwise use default input_text = input_text if input_text else default_text num_return_sequences = num_return_sequences if num_return_sequences else default_num_return_sequences max_length = max_length if max_length else default_max_length import tiktoken enc = tiktoken.get_encoding('gpt2') tokens = enc.encode(input_text) tokens = torch.tensor(tokens, dtype= torch.long) # (8,) #check tiktoken app tokens = tokens.unsqueeze(0).repeat(num_return_sequences, 1) # (5, 8) x = tokens.to(device) torch.manual_seed(42) torch.cuda.manual_seed(42) if st.button("Generate"): try: # Encode input text and generate output while x.size(1) < max_length: # forward the model to get the logits with torch.no_grad(): logits = model(x)[0] # (B, T, vocab_size) # take the logits at the last position logits = logits[:, -1, :] # (B, vocab_size) # get the probabilities probs = F.softmax(logits, dim=-1) # do top-k sampling of 50 (huggingface pipeline default) # topk_probs here becomes (5, 50), topk_indices is (5, 50) topk_probs, topk_indices = torch.topk(probs, 50, dim=-1) # select a token from the top-k probabilities # note: multinomial does not demand the input to sum to 1 ix = torch.multinomial(topk_probs, 1) # (B, 1) # gather the corresponding indices xcol = torch.gather(topk_indices, -1, ix) # (B, 1) # append to the sequence x = torch.cat((x, xcol), dim=1) # print the generated text for i in range(num_return_sequences): tokens = x[i, :max_length].tolist() decoded = enc.decode(tokens) st.write(f"> Generated text {i + 1}:") st.write(decoded) except Exception as e: st.error(f"Error generating text: {e}")