File size: 7,444 Bytes
da68b24 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
from dataclasses import dataclass
import torch
import torch.nn as nn
from torch.nn import functional as F
from torch.nn import LayerNorm
import math
import tiktoken
import inspect
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)
self.c_proj.NANOGPT_SCALE_INIT = 1
# regularization
self.n_head = config.n_head
self.n_embd = config.n_embd
def forward(self, x):
B, T, C = x.size()
qkv = self.c_attn(x)
q, k, v = qkv.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)x`
y = F.scaled_dot_product_attention(q, k, v, is_causal=True) # flash attention
y = y.transpose(1, 2).contiguous().view(B, T, C) # re-assemble all head outputs side by side
# output projection
y = self.c_proj(y)
return y
class MLP(nn.Module):
def __init__(self, config):
super().__init__()
self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd)
self.gelu = nn.GELU(approximate='tanh')
self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)
self.c_proj.NANOGPT_SCALE_INIT = 1
def forward(self, x):
x = self.c_fc(x)
x = self.gelu(x)
x = self.c_proj(x)
return x
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
@dataclass
class GPTConfig:
block_size: int = 1024 #1024
vocab_size: int = 50257
n_layer: int = 8
n_head: int = 8
n_embd: int = 256
class GPT(nn.Module):
def __init__(self, config):
super().__init__()
self.config = config
self.transformer = nn.ModuleDict(dict(
wte = nn.Embedding(config.vocab_size, config.n_embd),
wpe = nn.Embedding(config.block_size, config.n_embd),
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)
#weight sharing scheme
self.transformer.wte.weight = self.lm_head.weight
#init params
self.apply(self._init_weights)
def _init_weights(self, module):
if isinstance(module, nn.Linear):
std = 0.02
if hasattr(module, 'NANOGPT_SCALE_INIT'):
std *= (2 * self.config.n_layer) ** -0.5
torch.nn.init.normal_(module.weight, mean=0.0, std=std)
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, idx, targets=None):
# idx is of shape (B, T)
B, T = idx.size()
assert T <= self.config.block_size, f"Cannot forward sequence of length {T}, block size is only {self.config.block_size}"
# forward the token and posisition embeddings
pos = torch.arange(0, T, dtype=torch.long, device= 'cuda' if torch.cuda.is_available() else "cpu") # shape (T)
pos_emb = self.transformer.wpe(pos) # position embeddings of shape (T, n_embd)
tok_emb = self.transformer.wte(idx) # token embeddings of shape (B, T, n_embd)
x = tok_emb + pos_emb
# forward the blocks of the transformer
for block in self.transformer.h:
x = block(x)
# forward the final layernorm and the classifier
x = self.transformer.ln_f(x)
logits = self.lm_head(x) # (B, T, vocab_size)
loss = None
if targets is not None:
loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
return logits, loss
def configure_optimizers(self, weight_decay, learning_rate, device_type):
# start with all of the candidate parameters (that require grad)
param_dict = {pn: p for pn, p in self.named_parameters()}
param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
# create optim groups. Any parameters that is 2D will be weight decayed, otherwise no.
# i.e. all weight tensors in matmuls + embeddings decay, all biases and layernorms don't.
decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
optim_groups = [
{'params': decay_params, 'weight_decay': weight_decay},
{'params': nodecay_params, 'weight_decay': 0.0}
]
num_decay_params = sum(p.numel() for p in decay_params)
num_nodecay_params = sum(p.numel() for p in nodecay_params)
print(f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters")
print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
# Create AdamW optimizer and use the fused version if it is available
fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
use_fused = fused_available and device_type == "cuda"
print(f"using fused AdamW: {use_fused}")
optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=(0.9, 0.95), eps=1e-8, fused=use_fused)
return optimizer
device = 'cpu'
model = GPT(GPTConfig())
# Load the weights
import torch
# Load the model on CPU
model.load_state_dict(torch.load("model.pth", map_location=torch.device('cpu')))
model.eval()
import tiktoken
enc = tiktoken.get_encoding("gpt2")
num_return_sequences = 5
max_length = 100
tokens = enc.encode("love in the air")
tokens = torch.tensor(tokens, dtype=torch.long)
tokens = tokens.unsqueeze(0).repeat(num_return_sequences, 1)
xgen = tokens.to(device)
sample_rng = torch.Generator(device=device)
sample_rng.manual_seed(42)
while xgen.size(1) < max_length:
with torch.no_grad():
logits, loss = model(xgen) # (B, T, vocab_size)
logits = logits[:, -1, :] # (B, vocab_size)
probs = F.softmax(logits, dim=-1)
topk_probs, topk_indices = torch.topk(probs, 50, dim=-1)
ix = torch.multinomial(topk_probs, 1, generator=sample_rng) # (B, 1)
xcol = torch.gather(topk_indices, -1, ix) # (B, 1)
xgen = torch.cat((xgen, xcol), dim=1)
for i in range(num_return_sequences):
tokens = xgen[i, :max_length].tolist()
decoded = enc.decode(tokens)
print(f"sample {i}: {decoded}") |