mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2025-06-26 23:50:03 +00:00
171 lines
6.0 KiB
Python
171 lines
6.0 KiB
Python
# Copyright (c) Sebastian Raschka under Apache License 2.0 (see LICENSE.txt).
|
|
# Source for "Build a Large Language Model From Scratch"
|
|
# - https://www.manning.com/books/build-a-large-language-model-from-scratch
|
|
# Code: https://github.com/rasbt/LLMs-from-scratch
|
|
#
|
|
# This file collects all the relevant code that we covered thus far
|
|
# throughout Chapters 2-5.
|
|
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
|
|
#####################################
|
|
# Chapter 3
|
|
#####################################
|
|
|
|
|
|
class MultiHeadAttention(nn.Module):
|
|
def __init__(self, d_in, d_out, context_length, dropout, num_heads, qkv_bias=False):
|
|
super().__init__()
|
|
assert d_out % num_heads == 0, "d_out must be divisible by n_heads"
|
|
|
|
self.d_out = d_out
|
|
self.num_heads = num_heads
|
|
self.head_dim = d_out // num_heads # Reduce the projection dim to match desired output dim
|
|
|
|
self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
|
|
self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
|
|
self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
|
|
self.out_proj = nn.Linear(d_out, d_out) # Linear layer to combine head outputs
|
|
self.dropout = nn.Dropout(dropout)
|
|
self.register_buffer('mask', torch.triu(torch.ones(context_length, context_length), diagonal=1))
|
|
|
|
def forward(self, x):
|
|
b, num_tokens, d_in = x.shape
|
|
|
|
keys = self.W_key(x) # Shape: (b, num_tokens, d_out)
|
|
queries = self.W_query(x)
|
|
values = self.W_value(x)
|
|
|
|
# We implicitly split the matrix by adding a `num_heads` dimension
|
|
# Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
|
|
keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
|
|
values = values.view(b, num_tokens, self.num_heads, self.head_dim)
|
|
queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)
|
|
|
|
# Transpose: (b, num_tokens, num_heads, head_dim) -> (b, num_heads, num_tokens, head_dim)
|
|
keys = keys.transpose(1, 2)
|
|
queries = queries.transpose(1, 2)
|
|
values = values.transpose(1, 2)
|
|
|
|
# Compute scaled dot-product attention (aka self-attention) with a causal mask
|
|
attn_scores = queries @ keys.transpose(2, 3) # Dot product for each head
|
|
|
|
# Original mask truncated to the number of tokens and converted to boolean
|
|
mask_bool = self.mask.bool()[:num_tokens, :num_tokens]
|
|
|
|
# Use the mask to fill attention scores
|
|
attn_scores.masked_fill_(mask_bool, -torch.inf)
|
|
|
|
attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1)
|
|
attn_weights = self.dropout(attn_weights)
|
|
|
|
# Shape: (b, num_tokens, num_heads, head_dim)
|
|
context_vec = (attn_weights @ values).transpose(1, 2)
|
|
|
|
# Combine heads, where self.d_out = self.num_heads * self.head_dim
|
|
context_vec = context_vec.reshape(b, num_tokens, self.d_out)
|
|
context_vec = self.out_proj(context_vec) # optional projection
|
|
|
|
return context_vec
|
|
|
|
|
|
#####################################
|
|
# Chapter 4
|
|
#####################################
|
|
class LayerNorm(nn.Module):
|
|
def __init__(self, emb_dim):
|
|
super().__init__()
|
|
self.eps = 1e-5
|
|
self.scale = nn.Parameter(torch.ones(emb_dim))
|
|
self.shift = nn.Parameter(torch.zeros(emb_dim))
|
|
|
|
def forward(self, x):
|
|
mean = x.mean(dim=-1, keepdim=True)
|
|
var = x.var(dim=-1, keepdim=True, unbiased=False)
|
|
norm_x = (x - mean) / torch.sqrt(var + self.eps)
|
|
return self.scale * norm_x + self.shift
|
|
|
|
|
|
class GELU(nn.Module):
|
|
def __init__(self):
|
|
super().__init__()
|
|
|
|
def forward(self, x):
|
|
return 0.5 * x * (1 + torch.tanh(
|
|
torch.sqrt(torch.tensor(2.0 / torch.pi)) *
|
|
(x + 0.044715 * torch.pow(x, 3))
|
|
))
|
|
|
|
|
|
class FeedForward(nn.Module):
|
|
def __init__(self, cfg):
|
|
super().__init__()
|
|
self.layers = nn.Sequential(
|
|
nn.Linear(cfg["emb_dim"], 4 * cfg["emb_dim"]),
|
|
GELU(),
|
|
nn.Linear(4 * cfg["emb_dim"], cfg["emb_dim"]),
|
|
)
|
|
|
|
def forward(self, x):
|
|
return self.layers(x)
|
|
|
|
|
|
class TransformerBlock(nn.Module):
|
|
def __init__(self, cfg):
|
|
super().__init__()
|
|
self.att = MultiHeadAttention(
|
|
d_in=cfg["emb_dim"],
|
|
d_out=cfg["emb_dim"],
|
|
context_length=cfg["context_length"],
|
|
num_heads=cfg["n_heads"],
|
|
dropout=cfg["drop_rate"],
|
|
qkv_bias=cfg["qkv_bias"])
|
|
self.ff = FeedForward(cfg)
|
|
self.norm1 = LayerNorm(cfg["emb_dim"])
|
|
self.norm2 = LayerNorm(cfg["emb_dim"])
|
|
self.drop_shortcut = nn.Dropout(cfg["drop_rate"])
|
|
|
|
def forward(self, x):
|
|
# Shortcut connection for attention block
|
|
shortcut = x
|
|
x = self.norm1(x)
|
|
x = self.att(x) # Shape [batch_size, num_tokens, emb_size]
|
|
x = self.drop_shortcut(x)
|
|
x = x + shortcut # Add the original input back
|
|
|
|
# Shortcut connection for feed-forward block
|
|
shortcut = x
|
|
x = self.norm2(x)
|
|
x = self.ff(x)
|
|
x = self.drop_shortcut(x)
|
|
x = x + shortcut # Add the original input back
|
|
|
|
return x
|
|
|
|
|
|
class GPTModel(nn.Module):
|
|
def __init__(self, cfg):
|
|
super().__init__()
|
|
self.tok_emb = nn.Embedding(cfg["vocab_size"], cfg["emb_dim"])
|
|
self.pos_emb = nn.Embedding(cfg["context_length"], cfg["emb_dim"])
|
|
self.drop_emb = nn.Dropout(cfg["drop_rate"])
|
|
|
|
self.trf_blocks = nn.Sequential(
|
|
*[TransformerBlock(cfg) for _ in range(cfg["n_layers"])])
|
|
|
|
self.final_norm = LayerNorm(cfg["emb_dim"])
|
|
self.out_head = nn.Linear(cfg["emb_dim"], cfg["vocab_size"], bias=False)
|
|
|
|
def forward(self, in_idx):
|
|
batch_size, seq_len = in_idx.shape
|
|
tok_embeds = self.tok_emb(in_idx)
|
|
pos_embeds = self.pos_emb(torch.arange(seq_len, device=in_idx.device))
|
|
x = tok_embeds + pos_embeds # Shape [batch_size, num_tokens, emb_size]
|
|
x = self.drop_emb(x)
|
|
x = self.trf_blocks(x)
|
|
x = self.final_norm(x)
|
|
logits = self.out_head(x)
|
|
return logits
|