import torch
import torch.nn as nn
from torch.nn import functional as F
import numpy as np
import random
import re
import gradio as gr
# hyperparameters
batch_size = 16 # how many independent sequences will we process in parallel?
block_size = 32 # what is the maximum context length for predictions?
max_iters = 5000
eval_interval = 100
learning_rate = 1e-3
device = 'cuda' if torch.cuda.is_available() else 'cpu'
eval_iters = 200
n_embd = 64
n_head = 4
n_layer = 4
dropout = 0.0
# ------------
torch.manual_seed(1337)
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
# super simple bigram model
class BigramLanguageModel(nn.Module):
def __init__(self, dataset_text, n_embd):
super().__init__()
# Compute character-related parameters
self.chars = sorted(list(set(dataset_text)))
self.vocab_size = len(self.chars)
self.stoi = {ch: i for i, ch in enumerate(self.chars)}
self.itos = {i: ch for ch, i in self.stoi.items()}
self.token_embedding_table = nn.Embedding(self.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)
self.lm_head = nn.Linear(n_embd, self.vocab_size)
self.encode = lambda s: [self.stoi[c] for c in s] # encoder: take a string, output a list of integers
self.decode = lambda l: ''.join([self.itos[i] for i in l]) # decoder: take a list of integers, output a string
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
for _ 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
# Reading shakespeare data
with open('input.txt', 'r', encoding='utf-8') as f:
shakespeare_text = f.read()
# Load the shakespeaere model
shakespeare_model = BigramLanguageModel(shakespeare_text, n_embd).to(device) # Initialize an instance of your model
shakespeare_model.load_state_dict(torch.load('nano-gpt.pth', map_location=torch.device('cpu')))
shakespeare_model.eval() # Set the model to evaluation mode
def generate_shakespeare_outputs(prompt=None, max_new_tokens=2000):
if prompt:
context = torch.tensor(shakespeare_model.encode(prompt), dtype=torch.long, device=device).view(1, -1)
else:
context = torch.zeros((1, 1), dtype=torch.long, device=device)
text_output = shakespeare_model.decode(shakespeare_model.generate(context, max_new_tokens=max_new_tokens)[0].tolist())
return text_output
title = "GPT using Shakespeare Data"
description1 = "Nano GPT trained on Shakespeare dataset. The implementation can be found here."
demo = gr.Interface(generate_shakespeare_outputs,
inputs=[gr.Textbox(label="Enter any prompt ", type="text", value="Once upon a time,"),
gr.Slider(minimum=100, maximum=5000, step=100, value=2000, label="Max new tokens")],
outputs=gr.Textbox(label="Output generated", type="text"), description=description1)
demo.launch()