!wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
--2023-01-30 20:48:45-- https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.111.133, 185.199.108.133, ... Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 1115394 (1.1M) [text/plain] Saving to: ‘input.txt’ input.txt 100%[===================>] 1.06M 801KB/s in 1.4s 2023-01-30 20:48:46 (801 KB/s) - ‘input.txt’ saved [1115394/1115394]
# extract and load the data
with open('input.txt', 'r', encoding='utf-8') as f:
text = f.read()
# length of dataset
print("length of dataset in characters: ", len(text))
length of dataset in characters: 1115394
# first 1000 characters of 'input.txt'
print(text[:1000])
First Citizen: Before we proceed any further, hear me speak. All: Speak, speak. First Citizen: You are all resolved rather to die than to famish? All: Resolved. resolved. First Citizen: First, you know Caius Marcius is chief enemy to the people. All: We know't, we know't. First Citizen: Let us kill him, and we'll have corn at our own price. Is't a verdict? All: No more talking on't; let it be done: away, away! Second Citizen: One word, good citizens. First Citizen: We are accounted poor citizens, the patricians good. What authority surfeits on would relieve us: if they would yield us but the superfluity, while it were wholesome, we might guess they relieved us humanely; but they think we are too dear: the leanness that afflicts us, the object of our misery, is as an inventory to particularise their abundance; our sufferance is a gain to them Let us revenge this with our pikes, ere we become rakes: for the gods know I speak this in hunger for bread, not in thirst for revenge.
# here are all the unique characters that occur in this text
chars = sorted(list(set(text)))
vocab_size = len(chars)
print(''.join(chars))
print(vocab_size)
!$&',-.3:;?ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz 65
# 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: takes a string, outputs a list of integers
decode = lambda l: ''.join([itos[i] for i in l]) # decoder: takes a list of integers, outputs a string
print(encode('Hello, World!'))
print(decode(encode('Hello, World!')))
[20, 43, 50, 50, 53, 6, 1, 35, 53, 56, 50, 42, 2] Hello, World!
# encode the entire dataset and store it into a torch.Tensor
import torch
data = torch.tensor(encode(text), dtype=torch.long)
print(data.shape, data.dtype)
print(data[:1000]) # first 1000 characters encoded
torch.Size([1115394]) torch.int64
tensor([18, 47, 56, 57, 58, 1, 15, 47, 58, 47, 64, 43, 52, 10, 0, 14, 43, 44,
53, 56, 43, 1, 61, 43, 1, 54, 56, 53, 41, 43, 43, 42, 1, 39, 52, 63,
1, 44, 59, 56, 58, 46, 43, 56, 6, 1, 46, 43, 39, 56, 1, 51, 43, 1,
57, 54, 43, 39, 49, 8, 0, 0, 13, 50, 50, 10, 0, 31, 54, 43, 39, 49,
6, 1, 57, 54, 43, 39, 49, 8, 0, 0, 18, 47, 56, 57, 58, 1, 15, 47,
58, 47, 64, 43, 52, 10, 0, 37, 53, 59, 1, 39, 56, 43, 1, 39, 50, 50,
1, 56, 43, 57, 53, 50, 60, 43, 42, 1, 56, 39, 58, 46, 43, 56, 1, 58,
53, 1, 42, 47, 43, 1, 58, 46, 39, 52, 1, 58, 53, 1, 44, 39, 51, 47,
57, 46, 12, 0, 0, 13, 50, 50, 10, 0, 30, 43, 57, 53, 50, 60, 43, 42,
8, 1, 56, 43, 57, 53, 50, 60, 43, 42, 8, 0, 0, 18, 47, 56, 57, 58,
1, 15, 47, 58, 47, 64, 43, 52, 10, 0, 18, 47, 56, 57, 58, 6, 1, 63,
53, 59, 1, 49, 52, 53, 61, 1, 15, 39, 47, 59, 57, 1, 25, 39, 56, 41,
47, 59, 57, 1, 47, 57, 1, 41, 46, 47, 43, 44, 1, 43, 52, 43, 51, 63,
1, 58, 53, 1, 58, 46, 43, 1, 54, 43, 53, 54, 50, 43, 8, 0, 0, 13,
50, 50, 10, 0, 35, 43, 1, 49, 52, 53, 61, 5, 58, 6, 1, 61, 43, 1,
49, 52, 53, 61, 5, 58, 8, 0, 0, 18, 47, 56, 57, 58, 1, 15, 47, 58,
47, 64, 43, 52, 10, 0, 24, 43, 58, 1, 59, 57, 1, 49, 47, 50, 50, 1,
46, 47, 51, 6, 1, 39, 52, 42, 1, 61, 43, 5, 50, 50, 1, 46, 39, 60,
43, 1, 41, 53, 56, 52, 1, 39, 58, 1, 53, 59, 56, 1, 53, 61, 52, 1,
54, 56, 47, 41, 43, 8, 0, 21, 57, 5, 58, 1, 39, 1, 60, 43, 56, 42,
47, 41, 58, 12, 0, 0, 13, 50, 50, 10, 0, 26, 53, 1, 51, 53, 56, 43,
1, 58, 39, 50, 49, 47, 52, 45, 1, 53, 52, 5, 58, 11, 1, 50, 43, 58,
1, 47, 58, 1, 40, 43, 1, 42, 53, 52, 43, 10, 1, 39, 61, 39, 63, 6,
1, 39, 61, 39, 63, 2, 0, 0, 31, 43, 41, 53, 52, 42, 1, 15, 47, 58,
47, 64, 43, 52, 10, 0, 27, 52, 43, 1, 61, 53, 56, 42, 6, 1, 45, 53,
53, 42, 1, 41, 47, 58, 47, 64, 43, 52, 57, 8, 0, 0, 18, 47, 56, 57,
58, 1, 15, 47, 58, 47, 64, 43, 52, 10, 0, 35, 43, 1, 39, 56, 43, 1,
39, 41, 41, 53, 59, 52, 58, 43, 42, 1, 54, 53, 53, 56, 1, 41, 47, 58,
47, 64, 43, 52, 57, 6, 1, 58, 46, 43, 1, 54, 39, 58, 56, 47, 41, 47,
39, 52, 57, 1, 45, 53, 53, 42, 8, 0, 35, 46, 39, 58, 1, 39, 59, 58,
46, 53, 56, 47, 58, 63, 1, 57, 59, 56, 44, 43, 47, 58, 57, 1, 53, 52,
1, 61, 53, 59, 50, 42, 1, 56, 43, 50, 47, 43, 60, 43, 1, 59, 57, 10,
1, 47, 44, 1, 58, 46, 43, 63, 0, 61, 53, 59, 50, 42, 1, 63, 47, 43,
50, 42, 1, 59, 57, 1, 40, 59, 58, 1, 58, 46, 43, 1, 57, 59, 54, 43,
56, 44, 50, 59, 47, 58, 63, 6, 1, 61, 46, 47, 50, 43, 1, 47, 58, 1,
61, 43, 56, 43, 0, 61, 46, 53, 50, 43, 57, 53, 51, 43, 6, 1, 61, 43,
1, 51, 47, 45, 46, 58, 1, 45, 59, 43, 57, 57, 1, 58, 46, 43, 63, 1,
56, 43, 50, 47, 43, 60, 43, 42, 1, 59, 57, 1, 46, 59, 51, 39, 52, 43,
50, 63, 11, 0, 40, 59, 58, 1, 58, 46, 43, 63, 1, 58, 46, 47, 52, 49,
1, 61, 43, 1, 39, 56, 43, 1, 58, 53, 53, 1, 42, 43, 39, 56, 10, 1,
58, 46, 43, 1, 50, 43, 39, 52, 52, 43, 57, 57, 1, 58, 46, 39, 58, 0,
39, 44, 44, 50, 47, 41, 58, 57, 1, 59, 57, 6, 1, 58, 46, 43, 1, 53,
40, 48, 43, 41, 58, 1, 53, 44, 1, 53, 59, 56, 1, 51, 47, 57, 43, 56,
63, 6, 1, 47, 57, 1, 39, 57, 1, 39, 52, 0, 47, 52, 60, 43, 52, 58,
53, 56, 63, 1, 58, 53, 1, 54, 39, 56, 58, 47, 41, 59, 50, 39, 56, 47,
57, 43, 1, 58, 46, 43, 47, 56, 1, 39, 40, 59, 52, 42, 39, 52, 41, 43,
11, 1, 53, 59, 56, 0, 57, 59, 44, 44, 43, 56, 39, 52, 41, 43, 1, 47,
57, 1, 39, 1, 45, 39, 47, 52, 1, 58, 53, 1, 58, 46, 43, 51, 1, 24,
43, 58, 1, 59, 57, 1, 56, 43, 60, 43, 52, 45, 43, 1, 58, 46, 47, 57,
1, 61, 47, 58, 46, 0, 53, 59, 56, 1, 54, 47, 49, 43, 57, 6, 1, 43,
56, 43, 1, 61, 43, 1, 40, 43, 41, 53, 51, 43, 1, 56, 39, 49, 43, 57,
10, 1, 44, 53, 56, 1, 58, 46, 43, 1, 45, 53, 42, 57, 1, 49, 52, 53,
61, 1, 21, 0, 57, 54, 43, 39, 49, 1, 58, 46, 47, 57, 1, 47, 52, 1,
46, 59, 52, 45, 43, 56, 1, 44, 53, 56, 1, 40, 56, 43, 39, 42, 6, 1,
52, 53, 58, 1, 47, 52, 1, 58, 46, 47, 56, 57, 58, 1, 44, 53, 56, 1,
56, 43, 60, 43, 52, 45, 43, 8, 0, 0])
# splitting the data into training and validation sets
n = int(0.9*len(data))
train_data = data[:n]
val_data= data[n:]
block_size = 8
train_data[:block_size+1]
tensor([18, 47, 56, 57, 58, 1, 15, 47, 58])
x = train_data[:block_size]
y = train_data[1:block_size+1]
for t in range(block_size):
context = x[:t+1]
target = y[t]
print(f'when input is {context} the target is {target}')
when input is tensor([18]) the target is 47 when input is tensor([18, 47]) the target is 56 when input is tensor([18, 47, 56]) the target is 57 when input is tensor([18, 47, 56, 57]) the target is 58 when input is tensor([18, 47, 56, 57, 58]) the target is 1 when input is tensor([18, 47, 56, 57, 58, 1]) the target is 15 when input is tensor([18, 47, 56, 57, 58, 1, 15]) the target is 47 when input is tensor([18, 47, 56, 57, 58, 1, 15, 47]) the target is 58
torch.manual_seed(1337)
batch_size = 4 # how many independent sequences will we process in parallel?
block_size = 8 # what is the maximum context length for predictions?
def get_batch(split):
# generate a small batch of data of inputs X and targets y
data = train_data if split == 'train' else val_data
ix = torch.randint(len(data) - block_size, (batch_size,))
x = torch.stack([data [i:i+block_size] for i in ix])
y = torch.stack([data[i+1:i+block_size+1] for i in ix])
return x, y
xb, yb = get_batch('train')
print('inputs:')
print(xb.shape)
print(xb)
print('targets:')
print(yb.shape)
print(yb)
print( '----')
for b in range(batch_size): # batch dimension
for t in range(block_size): # time dimension
context = xb[b,:t+1]
target = yb[b,t]
print(f"when input is {context.tolist()} the target: {target}")
inputs:
torch.Size([4, 8])
tensor([[24, 43, 58, 5, 57, 1, 46, 43],
[44, 53, 56, 1, 58, 46, 39, 58],
[52, 58, 1, 58, 46, 39, 58, 1],
[25, 17, 27, 10, 0, 21, 1, 54]])
targets:
torch.Size([4, 8])
tensor([[43, 58, 5, 57, 1, 46, 43, 39],
[53, 56, 1, 58, 46, 39, 58, 1],
[58, 1, 58, 46, 39, 58, 1, 46],
[17, 27, 10, 0, 21, 1, 54, 39]])
----
when input is [24] the target: 43
when input is [24, 43] the target: 58
when input is [24, 43, 58] the target: 5
when input is [24, 43, 58, 5] the target: 57
when input is [24, 43, 58, 5, 57] the target: 1
when input is [24, 43, 58, 5, 57, 1] the target: 46
when input is [24, 43, 58, 5, 57, 1, 46] the target: 43
when input is [24, 43, 58, 5, 57, 1, 46, 43] the target: 39
when input is [44] the target: 53
when input is [44, 53] the target: 56
when input is [44, 53, 56] the target: 1
when input is [44, 53, 56, 1] the target: 58
when input is [44, 53, 56, 1, 58] the target: 46
when input is [44, 53, 56, 1, 58, 46] the target: 39
when input is [44, 53, 56, 1, 58, 46, 39] the target: 58
when input is [44, 53, 56, 1, 58, 46, 39, 58] the target: 1
when input is [52] the target: 58
when input is [52, 58] the target: 1
when input is [52, 58, 1] the target: 58
when input is [52, 58, 1, 58] the target: 46
when input is [52, 58, 1, 58, 46] the target: 39
when input is [52, 58, 1, 58, 46, 39] the target: 58
when input is [52, 58, 1, 58, 46, 39, 58] the target: 1
when input is [52, 58, 1, 58, 46, 39, 58, 1] the target: 46
when input is [25] the target: 17
when input is [25, 17] the target: 27
when input is [25, 17, 27] the target: 10
when input is [25, 17, 27, 10] the target: 0
when input is [25, 17, 27, 10, 0] the target: 21
when input is [25, 17, 27, 10, 0, 21] the target: 1
when input is [25, 17, 27, 10, 0, 21, 1] the target: 54
when input is [25, 17, 27, 10, 0, 21, 1, 54] the target: 39
import torch
import torch.nn as nn
from torch.nn import functional as F
torch.manual_seed(1337)
class BigramLanguageModel(nn.Module):
def __init__(self, vocab_size):
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, vocab_size)
def forward(self, idx, targets=None):
# idx and targets are both (B,T) tensor of integers
logits = self.token_embedding_table(idx) # (B,T,C)
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)Iarray of indices in the current context
for _ in range (max_new_tokens):
# get the predictions
logits, loss = self(idx)
# 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) # (В, 1)
# append sampled index to the running sequence
idx = torch. cat((idx, idx_next), dim=1) # (B, T+1)
return idx
m = BigramLanguageModel(vocab_size)
logits, loss = m(xb, yb)
print(logits.shape)
print(loss)
print(decode(m.generate(idx = torch.zeros((1, 1), dtype=torch.long), max_new_tokens=100)[0].tolist()))
torch.Size([32, 65]) tensor(4.8786, grad_fn=<NllLossBackward0>) SKIcLT;AcELMoTbvZv C?nq-QE33:CJqkOKH-q;:la!oiywkHjgChzbQ?u!3bLIgwevmyFJGUGp wnYWmnxKWWev-tDqXErVKLgJ
# create a PyTorch optimizer
optimizer = torch.optim.AdamW(m.parameters(), lr=1e-3)
batch_size = 32
for steps in range (10000):
# sample a batch of data
xb, yb = get_batch('train')
# evaluate the loss
logits, loss = m(xb, yb)
optimizer.zero_grad(set_to_none=True)
loss.backward()
optimizer.step()
print(loss.item())
2.580815076828003
print(decode(m.generate(idx = torch.zeros((1, 1), dtype=torch.long), max_new_tokens=100)[0].tolist()))
I weefapsshe d. S dorithe bld avo the f pir inithe sengr benklos h O: Foveplod? l lll tt brackinds
# train.py
import torch
import torch.nn as nn
from torch.nn import functional as F
# hyperparameters
batch_size = 64 # how many independent sequences will we process in parallel?
block_size = 256 # what is the maximum context length for predictions?
max_iters = 5000
eval_interval = 500
learning_rate = 3e-4
device = 'cuda' if torch.cuda.is_available() else 'mps'
eval_iters = 200
n_embd = 384
n_head = 6
n_layer = 6
dropout = 0.2
# ------------
torch.manual_seed(1337)
# wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
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
# Train and test splits
data = torch.tensor(encode(text), dtype=torch.long)
n = int(0.9*len(data)) # first 90% will be train, rest val
train_data = data[:n]
val_data = data[n:]
# data loading
def get_batch(split):
# generate a small batch of data of inputs x and targets y
data = train_data if split == 'train' else val_data
ix = torch.randint(len(data) - block_size, (batch_size,))
x = torch.stack([data[i:i+block_size] for i in ix])
y = torch.stack([data[i+1:i+block_size+1] for i in ix])
x, y = x.to(device), y.to(device)
return x, y
@torch.no_grad()
def estimate_loss():
out = {}
model.eval()
for split in ['train', 'val']:
losses = torch.zeros(eval_iters)
for k in range(eval_iters):
X, Y = get_batch(split)
logits, loss = model(X, Y)
losses[k] = loss.item()
out[split] = losses.mean()
model.train()
return out
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) * k.shape[-1]**-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):
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
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
model = BigramLanguageModel()
m = model.to(device)
# print the number of parameters in the model
print(sum(p.numel() for p in m.parameters())/1e6, 'M parameters')
# create a PyTorch optimizer
optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)
for iter in range(max_iters):
# every once in a while evaluate the loss on train and val sets
if iter % eval_interval == 0 or iter == max_iters - 1:
losses = estimate_loss()
print(f"step {iter}: train loss {losses['train']:.4f}, val loss {losses['val']:.4f}")
# sample a batch of data
xb, yb = get_batch('train')
# evaluate the loss
logits, loss = model(xb, yb)
optimizer.zero_grad(set_to_none=True)
loss.backward()
optimizer.step()
# generate from the model
context = torch.zeros((1, 1), dtype=torch.long, device=device)
print(decode(m.generate(context, max_new_tokens=500)[0].tolist()))
open('more.txt', 'w').write(decode(m.generate(context, max_new_tokens=10000)[0].tolist()))