Spaces:
Running
Running
File size: 5,861 Bytes
e0646b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 |
import torch
import torch.nn as nn
from torch.nn import functional as F
class hyperparams:
block_size = 128
batch_size = 32
max_iters = 12000
learning_rate = 3e-4
eval_every = 100
n_embd = 384
n_head = 8
n_layer = 8
dropout = 0.2
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
block_size = hyperparams.block_size
batch_size = hyperparams.batch_size
max_iters = hyperparams.max_iters
learning_rate = hyperparams.learning_rate
eval_every = hyperparams.eval_every
n_embd = hyperparams.n_embd
n_head = hyperparams.n_head
n_layer = hyperparams.n_layer
dropout = hyperparams.dropout
device = hyperparams.device
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):
# input of size (batch, time-step, channels)
# output of size (batch, time-step, head size)
B,T,C = x.shape
k = self.key(x) # (B,T,hs)
q = self.query(x) # (B,T,hs)
# compute attention scores ("affinities")
wei = q @ k.transpose(-2,-1) * k.shape[-1]**-0.5 # (B, T, hs) @ (B, hs, 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,hs)
out = wei @ v # (B, T, T) @ (B, T, hs) -> (B, T, hs)
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(head_size * num_heads, n_embd)
self.dropout = nn.Dropout(dropout)
def forward(self, x):
out = torch.cat([h(x) for h in self.heads], dim=-1) # (B, T, F) -> (B, T, [h1, h1, h1, h1, h2, h2, h2, h2, h3, h3, h3, h3])
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):
y = self.sa(x)
x = self.ln1(x + y)
y = self.ffwd(x)
x = self.ln2(x + y)
return x
class GPTLanguageModel(nn.Module):
def __init__(self, vocab_size):
super().__init__()
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)
self.apply(self._init_weights)
def _init_weights(self, module):
if isinstance(module, nn.Linear):
torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
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, index, targets=None):
B, T = index.shape
# idx and targets are both (B,T) tensor of integers
tok_emb = self.token_embedding_table(index) # (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) # reshape to what torch.cross_entropy expects
targets = targets.view(B*T)
loss = F.cross_entropy(logits, targets)
return logits, loss
def generate(self, index, max_new_tokens):
# index is (B, T) array of indices in the current context
for _ in range(max_new_tokens):
# crop idx to the last block_size tokens
index_cond = index[:, -block_size:]
# get the predictions
logits, loss = self.forward(index_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
index_next = torch.multinomial(probs, num_samples=1) # (B, 1)
# append sampled index to the running sequence
index = torch.cat((index, index_next), dim=1) # (B, T+1)
return index
|