import gradio as gr import torch import torch.nn as nn from torch.nn import functional as F import os from datetime import datetime with open('input.txt', 'r', encoding='utf-8') as f: text = f.read() # here are all the unique characters that occur in this text chars = sorted(list(set(text))) vocab_size = len(chars) # create a mapping from characters to integers stoi = { ch:i for i,ch in enumerate(chars) } itos = { i:ch for i,ch in enumerate(chars) } encode = lambda s: [stoi[c] for c in s] # encoder: take a string, output a list of integers decode = lambda l: ''.join([itos[i] for i in l]) # decoder: take a list of integers, output a string n_embd = 64 block_size = 64 # what is the maximum context length for predictions? n_layer = 4 n_head = 4 dropout = 0.0 device = 'cuda' if torch.cuda.is_available() else 'cpu' class Head(nn.Module): """ one head of self-attention """ def __init__(self, head_size): super().__init__() self.key = nn.Linear(n_embd, head_size, bias=False) self.query = nn.Linear(n_embd, head_size, bias=False) self.value = nn.Linear(n_embd, head_size, bias=False) self.register_buffer('tril', torch.tril(torch.ones(block_size, block_size))) self.dropout = nn.Dropout(dropout) def forward(self, x): B,T,C = x.shape k = self.key(x) # (B,T,C) q = self.query(x) # (B,T,C) # compute attention scores ("affinities") wei = q @ k.transpose(-2,-1) * C**-0.5 # (B, T, C) @ (B, C, T) -> (B, T, T) wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) # (B, T, T) wei = F.softmax(wei, dim=-1) # (B, T, T) wei = self.dropout(wei) # perform the weighted aggregation of the values v = self.value(x) # (B,T,C) out = wei @ v # (B, T, T) @ (B, T, C) -> (B, T, C) return out class MultiHeadAttention(nn.Module): """ multiple heads of self-attention in parallel """ def __init__(self, num_heads, head_size): super().__init__() self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)]) self.proj = nn.Linear(n_embd, n_embd) self.dropout = nn.Dropout(dropout) def forward(self, x): out = torch.cat([h(x) for h in self.heads], dim=-1) out = self.dropout(self.proj(out)) return out class FeedFoward(nn.Module): """ a simple linear layer followed by a non-linearity """ def __init__(self, n_embd): super().__init__() self.net = nn.Sequential( nn.Linear(n_embd, 4 * n_embd), nn.ReLU(), nn.Linear(4 * n_embd, n_embd), nn.Dropout(dropout), ) def forward(self, x): return self.net(x) class Block(nn.Module): """ Transformer block: communication followed by computation """ def __init__(self, n_embd, n_head): # n_embd: embedding dimension, n_head: the number of heads we'd like super().__init__() head_size = n_embd // n_head self.sa = MultiHeadAttention(n_head, head_size) self.ffwd = FeedFoward(n_embd) self.ln1 = nn.LayerNorm(n_embd) self.ln2 = nn.LayerNorm(n_embd) def forward(self, x): x = x + self.sa(self.ln1(x)) x = x + self.ffwd(self.ln2(x)) return x # gpt model class gptModel(nn.Module): def __init__(self): super().__init__() # each token directly reads off the logits for the next token from a lookup table self.token_embedding_table = nn.Embedding(vocab_size, n_embd) self.position_embedding_table = nn.Embedding(block_size, n_embd) self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head) for _ in range(n_layer)]) self.ln_f = nn.LayerNorm(n_embd) # final layer norm self.lm_head = nn.Linear(n_embd, vocab_size) def forward(self, idx, targets=None): B, T = idx.shape # idx and targets are both (B,T) tensor of integers tok_emb = self.token_embedding_table(idx) # (B,T,C) pos_emb = self.position_embedding_table(torch.arange(T, device=device)) # (T,C) x = tok_emb + pos_emb # (B,T,C) x = self.blocks(x) # (B,T,C) x = self.ln_f(x) # (B,T,C) logits = self.lm_head(x) # (B,T,vocab_size) if targets is None: loss = None else: B, T, C = logits.shape logits = logits.view(B*T, C) targets = targets.view(B*T) loss = F.cross_entropy(logits, targets) return logits, loss def generate(self, idx, max_new_tokens): # idx is (B, T) array of indices in the current context context_length = idx.shape[-1] max_new_tokens -= context_length for k in range(max_new_tokens): # crop idx to the last block_size tokens idx_cond = idx[:, -block_size:] # get the predictions logits, loss = self(idx_cond) # focus only on the last time step logits = logits[:, -1, :] # becomes (B, C) # apply softmax to get probabilities probs = F.softmax(logits, dim=-1) # (B, C) # sample from the distribution idx_next = torch.multinomial(probs, num_samples=1) # (B, 1) # append sampled index to the running sequence idx = torch.cat((idx, idx_next), dim=1) # (B, T+1) return idx model = gptModel() m = model.to(device) model_pth = 'checkpoint_epoch-199999_26.10.2023_13:20:27_cpu.pt' model.load_state_dict(torch.load(model_pth)) def generate_text(given_text_context, max_text_length): if given_text_context[-1] != ' ': given_text_context += ' ' if max_text_length > 5000: max_text_length = 5000 if max_text_length < 40: max_text_length = 40 if len(given_text_context) > max_text_length: given_text_context = given_text_context[:max_text_length] context = given_text_context # Encode the context en_context = encode(context) # Convert the Python list to a PyTorch tensor with dtype torch.int en_tensor = torch.tensor(en_context, dtype=torch.int) en_tensor = en_tensor.view(1, len(en_context)) output_msg = decode(m.generate(en_tensor, max_new_tokens=max_text_length)[0].tolist()) return output_msg def gradio_fn(given_text_context, num_chars): num_chars = int(num_chars) output_txt_msg = generate_text(given_text_context, num_chars) return output_txt_msg demo = gr.Interface(fn=gradio_fn, inputs=[gr.Textbox(info="Start my passage with: 'I would like to'"), gr.Number(value=200, minimum=40, maximum=5000, \ info="Num characters for passage min=40, max=5000")], outputs=gr.Textbox(), title="Text Gen with GPT", description="- GPT model that generates text based on \ (a) given text context (b) for given character length") demo.launch(share=True)