|
|
import json |
|
|
import torch |
|
|
import torch.nn as nn |
|
|
from torch.nn import functional as F |
|
|
from transformers import PreTrainedModel, PretrainedConfig |
|
|
|
|
|
|
|
|
batch_size = 64 |
|
|
block_size = 256 |
|
|
n_embed = 384 |
|
|
n_head = 6 |
|
|
n_layer = 6 |
|
|
dropout = 0.2 |
|
|
|
|
|
vocab_size = 65 |
|
|
|
|
|
class NoobConfig(PretrainedConfig): |
|
|
model_type = "Noob" |
|
|
vocab_size = vocab_size |
|
|
n_positions = block_size |
|
|
n_embd = n_embed |
|
|
n_layer = n_layer |
|
|
n_head = n_head |
|
|
|
|
|
class Head(nn.Module): |
|
|
""" one head of self-attention """ |
|
|
def __init__(self, head_size): |
|
|
super().__init__() |
|
|
self.key = nn.Linear(n_embed, head_size, bias=False) |
|
|
self.query = nn.Linear(n_embed, head_size, bias=False) |
|
|
self.value = nn.Linear(n_embed, 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) |
|
|
q = self.query(x) |
|
|
wei = q @ k.transpose(-2, -1) * C**-0.5 |
|
|
wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) |
|
|
wei = F.softmax(wei, dim=-1) |
|
|
wei = self.dropout(wei) |
|
|
v = self.value(x) |
|
|
out = wei @ v |
|
|
return out |
|
|
|
|
|
class MultiHeadAttention(nn.Module): |
|
|
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_embed, n_embed) |
|
|
self.dropout = nn.Dropout(dropout) |
|
|
|
|
|
def forward(self, x): |
|
|
out = torch.cat([h(x) for h in self.heads], dim=-1) |
|
|
out = self.proj(out) |
|
|
out = self.dropout(out) |
|
|
return out |
|
|
|
|
|
class FeedFoward(nn.Module): |
|
|
def __init__(self, n_embed): |
|
|
super().__init__() |
|
|
self.net = nn.Sequential( |
|
|
nn.Linear(n_embed, 4 * n_embed), |
|
|
nn.ReLU(), |
|
|
nn.Linear(4 * n_embed, n_embed), |
|
|
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_embed, n_head): |
|
|
super().__init__() |
|
|
head_size = n_embed // n_head |
|
|
self.sa = MultiHeadAttention(n_head, head_size) |
|
|
self.ffwd = FeedFoward(n_embed) |
|
|
self.ln1 = nn.LayerNorm(n_embed) |
|
|
self.ln2 = nn.LayerNorm(n_embed) |
|
|
|
|
|
def forward(self, x): |
|
|
x = x + self.sa(self.ln1(x)) |
|
|
x = x + self.ffwd(self.ln2(x)) |
|
|
return x |
|
|
|
|
|
class Noob(PreTrainedModel): |
|
|
config_class = NoobConfig |
|
|
|
|
|
def __init__(self, config): |
|
|
super().__init__(config) |
|
|
self.token_embedding_table = nn.Embedding(config.vocab_size, config.n_embd) |
|
|
self.position_embedding_table = nn.Embedding(config.n_positions, config.n_embd) |
|
|
self.blocks = nn.Sequential(*[Block(config.n_embd, config.n_head) for _ in range(config.n_layer)]) |
|
|
self.ln_final = nn.LayerNorm(config.n_embd) |
|
|
self.lm_head = nn.Linear(config.n_embd, config.vocab_size) |
|
|
|
|
|
def forward(self, idx, targets=None): |
|
|
B, T = idx.shape |
|
|
tok_emb = self.token_embedding_table(idx) |
|
|
pos_emb = self.position_embedding_table(torch.arange(T, device=idx.device)) |
|
|
x = tok_emb + pos_emb |
|
|
x = self.blocks(x) |
|
|
x = self.ln_final(x) |
|
|
logits = self.lm_head(x) |
|
|
|
|
|
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): |
|
|
for _ in range(max_new_tokens): |
|
|
idx_cond = idx[:, -block_size:] |
|
|
logits, _ = self(idx_cond) |
|
|
logits = logits[:, -1, :] |
|
|
probs = F.softmax(logits, dim=-1) |
|
|
idx_next = torch.multinomial(probs, num_samples=1) |
|
|
idx = torch.cat((idx, idx_next), dim=1) |
|
|
return idx |
