transformer
Attention Is All You Need paper
attention node
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)
# regularization
self.attn_dropout = nn.Dropout(config.dropout)
self.resid_dropout = nn.Dropout(config.dropout)
# causal mask to ensure that attention is only applied to the left in the input sequence
self.register_buffer("bias", torch.tril(torch.ones(config.block_size, config.block_size))
.view(1, 1, config.block_size, config.block_size))
self.n_head = config.n_head
self.n_embd = config.n_embd
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
q, k ,v = self.c_attn(x).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)
# causal self-attention; Self-attend: (B, nh, T, hs) x (B, nh, hs, T) -> (B, nh, T, T)
# 除方差
att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
# 只取下半部分，我们只能看到之前的内容
att = att.masked_fill(self.bias[:,:,:T,:T] == 0, float('-inf'))
att = F.softmax(att, dim=-1)
att = self.attn_dropout(att)
y = att @ v # (B, nh, T, T) x (B, nh, T, hs) -> (B, nh, T, hs)
y = y.transpose(1, 2).contiguous().view(B, T, C) # re-assemble all head outputs side by side
# output projection
y = self.resid_dropout(self.c_proj(y))
return y
add & norm
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
feed forward
def fused_gelu(x):
"""
Implementation of the GELU activation function currently in Google BERT repo (identical to OpenAI GPT).
Reference: Gaussian Error Linear Units (GELU) paper: https://arxiv.org/abs/1606.08415
"""
return 0.5 * x * (1.0 + torch.tanh(math.sqrt(2.0 / math.pi) * (x + 0.044715 * torch.pow(x, 3.0))))
class MLP(nn.Module):
def __init__(self, config):
super().__init__()
self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd)
self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)
self.dropout = nn.Dropout(config.dropout)
def forward(self, x):
x = self.c_fc(x)
x = fused_gelu(x)
x = self.c_proj(x)
x = self.dropout(x)
return x
All
class GPT(nn.Module):
def __init__(self, config):
super().__init__()
assert config.vocab_size is not None
assert config.block_size is not None
self.block_size = config.block_size
self.transformer = nn.ModuleDict(dict(
wte = nn.Embedding(config.vocab_size, config.n_embd),
wpe = nn.Embedding(config.block_size, config.n_embd),
drop = nn.Dropout(config.dropout),
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)
# report number of parameters (note we don't count the decoder parameters in lm_head)
n_params = sum(p.numel() for p in self.transformer.parameters())
print("number of parameters: %.2fM" % (n_params/1e6,))
def forward(self, idx, targets=None):
device = idx.device
b, t = idx.size()
assert t <= self.block_size, f"Cannot forward sequence of length {t}, block size is only {self.block_size}"
pos = torch.arange(0, t, dtype=torch.long, device=device).unsqueeze(0) # shape (1, t)
# forward the GPT model itself
tok_emb = self.transformer.wte(idx) # token embeddings of shape (b, t, n_embd)
pos_emb = self.transformer.wpe(pos) # position embeddings of shape (1, t, n_embd)
x = self.transformer.drop(tok_emb + pos_emb)
for block in self.transformer.h:
x = block(x)
x = self.transformer.ln_f(x)
logits = self.lm_head(x)
# if we are given some desired targets also calculate the loss
loss = None
if targets is not None:
loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
return logits, loss
@torch.no_grad()
def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None):
"""
Take a conditioning sequence of indices idx (LongTensor of shape (b,t)) and complete
the sequence max_new_tokens times, feeding the predictions back into the model each time.
Most likely you'll want to make sure to be in model.eval() mode of operation for this.
"""
for _ in range(max_new_tokens):
# if the sequence context is growing too long we must crop it at block_size
idx_cond = idx if idx.size(1) <= self.block_size else idx[:, -self.block_size:]
# forward the model to get the logits for the index in the sequence
logits, _ = self(idx_cond)
# pluck the logits at the final step and scale by desired temperature
logits = logits[:, -1, :] / temperature
# optionally crop the logits to only the top k options
if top_k is not None:
v, _ = torch.topk(logits, top_k)
logits[logits < v[:, [-1]]] = -float('Inf')
# apply softmax to convert logits to (normalized) probabilities
probs = F.softmax(logits, dim=-1)
# sample from the distribution
idx_next = torch.multinomial(probs, num_samples=1)
# append sampled index to the running sequence and continue
idx = torch.cat((idx, idx_next), dim=1)
return