books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add PyPI package (#576)

Browse Source 
* Add PyPI package

* fixes

* fixes
This commit is contained in:
Sebastian Raschka
2025-03-23 19:28:49 -05:00
committed by GitHub
parent 85f2bc0a58
commit 7114ccd10d
52 changed files with 2173 additions and 2585 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ch05/01_main-chapter-code/ch05.ipynb
View File

@@ -147,6 +147,11 @@
"source": [
"import torch\n",
"from previous_chapters import GPTModel\n",
"# If the `previous_chapters.py` file is not available locally,\n",
"# you can import it from the `llms-from-scratch` PyPI package.\n",
"# For details, see: https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg\n",
"# E.g.,\n",
"# from llms_from_scratch.ch04 import GPTModel\n",
"\n",
"GPT_CONFIG_124M = {\n",
" \"vocab_size\": 50257, # Vocabulary size\n",
@@ -212,6 +217,9 @@
"import tiktoken\n",
"from previous_chapters import generate_text_simple\n",
"\n",
"# Alternatively:\n",
"# from llms_from_scratch.ch04 import generate_text_simple\n",
"\n",
"def text_to_token_ids(text, tokenizer):\n",
" encoded = tokenizer.encode(text, allowed_special={'<|endoftext|>'})\n",
" encoded_tensor = torch.tensor(encoded).unsqueeze(0) # add batch dimension\n",
@@ -924,6 +932,8 @@
"outputs": [],
"source": [
"from previous_chapters import create_dataloader_v1\n",
"# Alternatively:\n",
"# from llms_from_scratch.ch02 import create_dataloader_v1\n",
"\n",
"# Train/validation ratio\n",
"train_ratio = 0.90\n",
@@ -2548,7 +2558,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.8"
"version": "3.10.16"
}
},
"nbformat": 4,

293
ch05/02_alternative_weight_loading/previous_chapters.py
View File

@@ -1,293 +0,0 @@
# 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 2-4.
# This file can be run as a standalone script.
import tiktoken
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
#####################################
# Chapter 2
#####################################
class GPTDatasetV1(Dataset):
def __init__(self, txt, tokenizer, max_length, stride):
self.input_ids = []
self.target_ids = []
# Tokenize the entire text
token_ids = tokenizer.encode(txt, allowed_special={"<|endoftext|>"})
# Use a sliding window to chunk the book into overlapping sequences of max_length
for i in range(0, len(token_ids) - max_length, stride):
input_chunk = token_ids[i:i + max_length]
target_chunk = token_ids[i + 1: i + max_length + 1]
self.input_ids.append(torch.tensor(input_chunk))
self.target_ids.append(torch.tensor(target_chunk))
def __len__(self):
return len(self.input_ids)
def __getitem__(self, idx):
return self.input_ids[idx], self.target_ids[idx]
def create_dataloader_v1(txt, batch_size=4, max_length=256,
stride=128, shuffle=True, drop_last=True, num_workers=0):
# Initialize the tokenizer
tokenizer = tiktoken.get_encoding("gpt2")
# Create dataset
dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)
# Create dataloader
dataloader = DataLoader(
dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, num_workers=num_workers)
return dataloader
#####################################
# 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
def generate_text_simple(model, idx, max_new_tokens, context_size):
# idx is (B, T) array of indices in the current context
for _ in range(max_new_tokens):
# Crop current context if it exceeds the supported context size
# E.g., if LLM supports only 5 tokens, and the context size is 10
# then only the last 5 tokens are used as context
idx_cond = idx[:, -context_size:]
# Get the predictions
with torch.no_grad():
logits = model(idx_cond)
# Focus only on the last time step
# (batch, n_token, vocab_size) becomes (batch, vocab_size)
logits = logits[:, -1, :]
# Get the idx of the vocab entry with the highest logits value
idx_next = torch.argmax(logits, dim=-1, keepdim=True) # (batch, 1)
# Append sampled index to the running sequence
idx = torch.cat((idx, idx_next), dim=1) # (batch, n_tokens+1)
return idx
#####################################
# Chapter 5
#####################################
def text_to_token_ids(text, tokenizer):
encoded = tokenizer.encode(text)
encoded_tensor = torch.tensor(encoded).unsqueeze(0) # add batch dimension
return encoded_tensor
def token_ids_to_text(token_ids, tokenizer):
flat = token_ids.squeeze(0) # remove batch dimension
return tokenizer.decode(flat.tolist())
def generate(model, idx, max_new_tokens, context_size, temperature=0.0, top_k=None, eos_id=None):
# For-loop is the same as before: Get logits, and only focus on last time step
for _ in range(max_new_tokens):
idx_cond = idx[:, -context_size:]
with torch.no_grad():
logits = model(idx_cond)
logits = logits[:, -1, :]
# New: Filter logits with top_k sampling
if top_k is not None:
# Keep only top_k values
top_logits, _ = torch.topk(logits, top_k)
min_val = top_logits[:, -1]
logits = torch.where(logits < min_val, torch.tensor(float('-inf')).to(logits.device), logits)
# New: Apply temperature scaling
if temperature > 0.0:
logits = logits / temperature
# Apply softmax to get probabilities
probs = torch.softmax(logits, dim=-1) # (batch_size, context_len)
# Sample from the distribution
idx_next = torch.multinomial(probs, num_samples=1) # (batch_size, 1)
# Otherwise same as before: get idx of the vocab entry with the highest logits value
else:
idx_next = torch.argmax(logits, dim=-1, keepdim=True) # (batch_size, 1)
if idx_next == eos_id: # Stop generating early if end-of-sequence token is encountered and eos_id is specified
break
# Same as before: append sampled index to the running sequence
idx = torch.cat((idx, idx_next), dim=1) # (batch_size, num_tokens+1)
return idx

7
ch05/02_alternative_weight_loading/weight-loading-hf-safetensors.ipynb
View File

@@ -95,7 +95,9 @@
"metadata": {},
"outputs": [],
"source": [
"from previous_chapters import GPTModel"
"from llms_from_scratch.ch04 import GPTModel\n",
"# For llms_from_scratch installation instructions, see:\n",
"# https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg"
]
},
{
@@ -270,7 +272,8 @@
],
"source": [
"import tiktoken\n",
"from previous_chapters import generate, text_to_token_ids, token_ids_to_text\n",
"from llms_from_scratch.ch05 import generate, text_to_token_ids, token_ids_to_text\n",
"\n",
"\n",
"torch.manual_seed(123)\n",
"\n",

7
ch05/02_alternative_weight_loading/weight-loading-hf-transformers.ipynb
View File

@@ -230,7 +230,9 @@
"outputs": [],
"source": [
"import torch\n",
"from previous_chapters import GPTModel\n",
"from llms_from_scratch.ch04 import GPTModel\n",
"# For llms_from_scratch installation instructions, see:\n",
"# https://github.com/rasbt/LLMs-from-scratch/tree/main/\n",
"\n",
"\n",
"gpt = GPTModel(BASE_CONFIG)\n",
@@ -258,7 +260,8 @@
],
"source": [
"import tiktoken\n",
"from previous_chapters import generate, text_to_token_ids, token_ids_to_text\n",
"from llms_from_scratch.ch05 import generate, text_to_token_ids, token_ids_to_text\n",
"\n",
"\n",
"torch.manual_seed(123)\n",
"\n",

14
ch05/03_bonus_pretraining_on_gutenberg/pretraining_simple.py
View File

@@ -17,14 +17,12 @@ from pathlib import Path
import time
import tiktoken
import torch
from previous_chapters import (
create_dataloader_v1,
GPTModel,
generate_and_print_sample,
calc_loss_batch,
evaluate_model,
plot_losses
)
# For llms_from_scratch installation instructions, see:
# https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg
from llms_from_scratch.ch02 import create_dataloader_v1
from llms_from_scratch.ch04 import GPTModel, generate_and_print_sample
from llms_from_scratch.ch05 import calc_loss_batch, evaluate_model, plot_losses
def read_text_file(file_path):

317
ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py
View File

@@ -1,317 +0,0 @@
# 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 2-4.
# This file can be run as a standalone script.
import tiktoken
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator
#####################################
# Chapter 2
#####################################
class GPTDatasetV1(Dataset):
def __init__(self, txt, tokenizer, max_length, stride):
self.input_ids = []
self.target_ids = []
token_ids = tokenizer.encode(txt, allowed_special={'<|endoftext|>'})
for i in range(0, len(token_ids) - max_length, stride):
input_chunk = token_ids[i:i + max_length]
target_chunk = token_ids[i + 1: i + max_length + 1]
self.input_ids.append(torch.tensor(input_chunk))
self.target_ids.append(torch.tensor(target_chunk))
def __len__(self):
return len(self.input_ids)
def __getitem__(self, idx):
return self.input_ids[idx], self.target_ids[idx]
def create_dataloader_v1(txt, batch_size=4, max_length=256,
stride=128, shuffle=True, drop_last=True, num_workers=0):
tokenizer = tiktoken.get_encoding("gpt2")
dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)
dataloader = DataLoader(
dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, num_workers=num_workers)
return dataloader
#####################################
# 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
def generate_text_simple(model, idx, max_new_tokens, context_size):
# idx is (B, T) array of indices in the current context
for _ in range(max_new_tokens):
# Crop current context if it exceeds the supported context size
# E.g., if LLM supports only 5 tokens, and the context size is 10
# then only the last 5 tokens are used as context
idx_cond = idx[:, -context_size:]
# Get the predictions
with torch.no_grad():
logits = model(idx_cond)
# Focus only on the last time step
# (batch, n_token, vocab_size) becomes (batch, vocab_size)
logits = logits[:, -1, :]
# Get the idx of the vocab entry with the highest logits value
idx_next = torch.argmax(logits, dim=-1, keepdim=True) # (batch, 1)
# Append sampled index to the running sequence
idx = torch.cat((idx, idx_next), dim=1) # (batch, n_tokens+1)
return idx
#####################################
# Chapter 5
####################################
def calc_loss_batch(input_batch, target_batch, model, device):
input_batch, target_batch = input_batch.to(device), target_batch.to(device)
logits = model(input_batch)
loss = torch.nn.functional.cross_entropy(logits.flatten(0, 1), target_batch.flatten())
return loss
def calc_loss_loader(data_loader, model, device, num_batches=None):
total_loss = 0.
if len(data_loader) == 0:
return float("nan")
elif num_batches is None:
num_batches = len(data_loader)
else:
num_batches = min(num_batches, len(data_loader))
for i, (input_batch, target_batch) in enumerate(data_loader):
if i < num_batches:
loss = calc_loss_batch(input_batch, target_batch, model, device)
total_loss += loss.item()
else:
break
return total_loss / num_batches
def evaluate_model(model, train_loader, val_loader, device, eval_iter):
model.eval()
with torch.no_grad():
train_loss = calc_loss_loader(train_loader, model, device, num_batches=eval_iter)
val_loss = calc_loss_loader(val_loader, model, device, num_batches=eval_iter)
model.train()
return train_loss, val_loss
def generate_and_print_sample(model, tokenizer, device, start_context):
model.eval()
context_size = model.pos_emb.weight.shape[0]
encoded = text_to_token_ids(start_context, tokenizer).to(device)
with torch.no_grad():
token_ids = generate_text_simple(
model=model, idx=encoded,
max_new_tokens=50, context_size=context_size)
decoded_text = token_ids_to_text(token_ids, tokenizer)
print(decoded_text.replace("\n", " ")) # Compact print format
model.train()
def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses, output_dir):
fig, ax1 = plt.subplots()
# Plot training and validation loss against epochs
ax1.plot(epochs_seen, train_losses, label="Training loss")
ax1.plot(epochs_seen, val_losses, linestyle="-.", label="Validation loss")
ax1.set_xlabel("Epochs")
ax1.set_ylabel("Loss")
ax1.legend(loc="upper right")
ax1.xaxis.set_major_locator(MaxNLocator(integer=True))
# Create a second x-axis for tokens seen
ax2 = ax1.twiny() # Create a second x-axis that shares the same y-axis
ax2.plot(tokens_seen, train_losses, alpha=0) # Invisible plot for aligning ticks
ax2.set_xlabel("Tokens seen")
fig.tight_layout() # Adjust layout to make room
plt.savefig(output_dir / "losses.pdf")
def text_to_token_ids(text, tokenizer):
encoded = tokenizer.encode(text, allowed_special={'<|endoftext|>'})
encoded_tensor = torch.tensor(encoded).unsqueeze(0) # Add batch dimension
return encoded_tensor
def token_ids_to_text(token_ids, tokenizer):
flat = token_ids.squeeze(0) # Remove batch dimension
return tokenizer.decode(flat.tolist())

6
ch05/05_bonus_hparam_tuning/hparam_search.py
View File

@@ -8,7 +8,11 @@ import math
import os
import tiktoken
import torch
from previous_chapters import GPTModel, create_dataloader_v1
# For llms_from_scratch installation instructions, see:
# https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg
from llms_from_scratch.ch02 import create_dataloader_v1
from llms_from_scratch.ch04 import GPTModel
# Define a grid of hyperparameters to search over

279
ch05/05_bonus_hparam_tuning/previous_chapters.py
View File

@@ -1,279 +0,0 @@
# 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 2-4.
# This file can be run as a standalone script.
import tiktoken
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
#####################################
# Chapter 2
#####################################
class GPTDatasetV1(Dataset):
def __init__(self, txt, tokenizer, max_length, stride):
self.input_ids = []
self.target_ids = []
# Tokenize the entire text
token_ids = tokenizer.encode(txt, allowed_special={"<|endoftext|>"})
# Use a sliding window to chunk the book into overlapping sequences of max_length
for i in range(0, len(token_ids) - max_length, stride):
input_chunk = token_ids[i:i + max_length]
target_chunk = token_ids[i + 1: i + max_length + 1]
self.input_ids.append(torch.tensor(input_chunk))
self.target_ids.append(torch.tensor(target_chunk))
def __len__(self):
return len(self.input_ids)
def __getitem__(self, idx):
return self.input_ids[idx], self.target_ids[idx]
def create_dataloader_v1(txt, batch_size=4, max_length=256,
stride=128, shuffle=True, drop_last=True, num_workers=0):
# Initialize the tokenizer
tokenizer = tiktoken.get_encoding("gpt2")
# Create dataset
dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)
# Create dataloader
dataloader = DataLoader(
dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, num_workers=num_workers)
return dataloader
#####################################
# 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 num_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.contiguous().view(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
def generate_text_simple(model, idx, max_new_tokens, context_size):
# idx is (B, T) array of indices in the current context
for _ in range(max_new_tokens):
# Crop current context if it exceeds the supported context size
# E.g., if LLM supports only 5 tokens, and the context size is 10
# then only the last 5 tokens are used as context
idx_cond = idx[:, -context_size:]
# Get the predictions
with torch.no_grad():
logits = model(idx_cond)
# Focus only on the last time step
# (batch, n_token, vocab_size) becomes (batch, vocab_size)
logits = logits[:, -1, :]
# Get the idx of the vocab entry with the highest logits value
idx_next = torch.argmax(logits, dim=-1, keepdim=True) # (batch, 1)
# Append sampled index to the running sequence
idx = torch.cat((idx, idx_next), dim=1) # (batch, n_tokens+1)
return idx
if __name__ == "__main__":
GPT_CONFIG_124M = {
"vocab_size": 50257, # Vocabulary size
"context_length": 1024, # Context length
"emb_dim": 768, # Embedding dimension
"n_heads": 12, # Number of attention heads
"n_layers": 12, # Number of layers
"drop_rate": 0.1, # Dropout rate
"qkv_bias": False # Query-Key-Value bias
}
torch.manual_seed(123)
model = GPTModel(GPT_CONFIG_124M)
model.eval() # disable dropout
start_context = "Hello, I am"
tokenizer = tiktoken.get_encoding("gpt2")
encoded = tokenizer.encode(start_context)
encoded_tensor = torch.tensor(encoded).unsqueeze(0)
print(f"\n{50*'='}\n{22*' '}IN\n{50*'='}")
print("\nInput text:", start_context)
print("Encoded input text:", encoded)
print("encoded_tensor.shape:", encoded_tensor.shape)
out = generate_text_simple(
model=model,
idx=encoded_tensor,
max_new_tokens=10,
context_size=GPT_CONFIG_124M["context_length"]
)
decoded_text = tokenizer.decode(out.squeeze(0).tolist())
print(f"\n\n{50*'='}\n{22*' '}OUT\n{50*'='}")
print("\nOutput:", out)
print("Output length:", len(out[0]))
print("Output text:", decoded_text)

6
ch05/06_user_interface/app_orig.py
View File

@@ -7,10 +7,12 @@ import tiktoken
import torch
import chainlit
from previous_chapters import (
# For llms_from_scratch installation instructions, see:
# https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg
from llms_from_scratch.ch04 import GPTModel
from llms_from_scratch.ch05 import (
download_and_load_gpt2,
generate,
GPTModel,
load_weights_into_gpt,
text_to_token_ids,
token_ids_to_text,

7
ch05/06_user_interface/app_own.py
View File

@@ -10,13 +10,16 @@ import tiktoken
import torch
import chainlit
from previous_chapters import (
# For llms_from_scratch installation instructions, see:
# https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg
from llms_from_scratch.ch04 import GPTModel
from llms_from_scratch.ch05 import (
generate,
GPTModel,
text_to_token_ids,
token_ids_to_text,
)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

384
ch05/06_user_interface/previous_chapters.py
View File

@@ -1,384 +0,0 @@
# 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 json
import os
import urllib
import numpy as np
import tensorflow as tf
import torch
import torch.nn as nn
from tqdm import tqdm
#####################################
# 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
#####################################
# Chapter 5
#####################################
def text_to_token_ids(text, tokenizer):
encoded = tokenizer.encode(text)
encoded_tensor = torch.tensor(encoded).unsqueeze(0) # add batch dimension
return encoded_tensor
def token_ids_to_text(token_ids, tokenizer):
flat = token_ids.squeeze(0) # remove batch dimension
return tokenizer.decode(flat.tolist())
def download_and_load_gpt2(model_size, models_dir):
# Validate model size
allowed_sizes = ("124M", "355M", "774M", "1558M")
if model_size not in allowed_sizes:
raise ValueError(f"Model size not in {allowed_sizes}")
# Define paths
model_dir = os.path.join(models_dir, model_size)
base_url = "https://openaipublic.blob.core.windows.net/gpt-2/models"
filenames = [
"checkpoint", "encoder.json", "hparams.json",
"model.ckpt.data-00000-of-00001", "model.ckpt.index",
"model.ckpt.meta", "vocab.bpe"
]
# Download files
os.makedirs(model_dir, exist_ok=True)
for filename in filenames:
file_url = os.path.join(base_url, model_size, filename)
file_path = os.path.join(model_dir, filename)
download_file(file_url, file_path)
# Load settings and params
tf_ckpt_path = tf.train.latest_checkpoint(model_dir)
settings = json.load(open(os.path.join(model_dir, "hparams.json")))
params = load_gpt2_params_from_tf_ckpt(tf_ckpt_path, settings)
return settings, params
def download_file(url, destination):
# Send a GET request to download the file
with urllib.request.urlopen(url) as response:
# Get the total file size from headers, defaulting to 0 if not present
file_size = int(response.headers.get("Content-Length", 0))
# Check if file exists and has the same size
if os.path.exists(destination):
file_size_local = os.path.getsize(destination)
if file_size == file_size_local:
print(f"File already exists and is up-to-date: {destination}")
return
# Define the block size for reading the file
block_size = 1024 # 1 Kilobyte
# Initialize the progress bar with total file size
progress_bar_description = os.path.basename(url) # Extract filename from URL
with tqdm(total=file_size, unit="iB", unit_scale=True, desc=progress_bar_description) as progress_bar:
# Open the destination file in binary write mode
with open(destination, "wb") as file:
# Read the file in chunks and write to destination
while True:
chunk = response.read(block_size)
if not chunk:
break
file.write(chunk)
progress_bar.update(len(chunk)) # Update progress bar
def load_gpt2_params_from_tf_ckpt(ckpt_path, settings):
# Initialize parameters dictionary with empty blocks for each layer
params = {"blocks": [{} for _ in range(settings["n_layer"])]}
# Iterate over each variable in the checkpoint
for name, _ in tf.train.list_variables(ckpt_path):
# Load the variable and remove singleton dimensions
variable_array = np.squeeze(tf.train.load_variable(ckpt_path, name))
# Process the variable name to extract relevant parts
variable_name_parts = name.split("/")[1:] # Skip the 'model/' prefix
# Identify the target dictionary for the variable
target_dict = params
if variable_name_parts[0].startswith("h"):
layer_number = int(variable_name_parts[0][1:])
target_dict = params["blocks"][layer_number]
# Recursively access or create nested dictionaries
for key in variable_name_parts[1:-1]:
target_dict = target_dict.setdefault(key, {})
# Assign the variable array to the last key
last_key = variable_name_parts[-1]
target_dict[last_key] = variable_array
return params
def assign(left, right):
if left.shape != right.shape:
raise ValueError(f"Shape mismatch. Left: {left.shape}, Right: {right.shape}")
return torch.nn.Parameter(torch.tensor(right))
def load_weights_into_gpt(gpt, params):
gpt.pos_emb.weight = assign(gpt.pos_emb.weight, params['wpe'])
gpt.tok_emb.weight = assign(gpt.tok_emb.weight, params['wte'])
for b in range(len(params["blocks"])):
q_w, k_w, v_w = np.split(
(params["blocks"][b]["attn"]["c_attn"])["w"], 3, axis=-1)
gpt.trf_blocks[b].att.W_query.weight = assign(
gpt.trf_blocks[b].att.W_query.weight, q_w.T)
gpt.trf_blocks[b].att.W_key.weight = assign(
gpt.trf_blocks[b].att.W_key.weight, k_w.T)
gpt.trf_blocks[b].att.W_value.weight = assign(
gpt.trf_blocks[b].att.W_value.weight, v_w.T)
q_b, k_b, v_b = np.split(
(params["blocks"][b]["attn"]["c_attn"])["b"], 3, axis=-1)
gpt.trf_blocks[b].att.W_query.bias = assign(
gpt.trf_blocks[b].att.W_query.bias, q_b)
gpt.trf_blocks[b].att.W_key.bias = assign(
gpt.trf_blocks[b].att.W_key.bias, k_b)
gpt.trf_blocks[b].att.W_value.bias = assign(
gpt.trf_blocks[b].att.W_value.bias, v_b)
gpt.trf_blocks[b].att.out_proj.weight = assign(
gpt.trf_blocks[b].att.out_proj.weight,
params["blocks"][b]["attn"]["c_proj"]["w"].T)
gpt.trf_blocks[b].att.out_proj.bias = assign(
gpt.trf_blocks[b].att.out_proj.bias,
params["blocks"][b]["attn"]["c_proj"]["b"])
gpt.trf_blocks[b].ff.layers[0].weight = assign(
gpt.trf_blocks[b].ff.layers[0].weight,
params["blocks"][b]["mlp"]["c_fc"]["w"].T)
gpt.trf_blocks[b].ff.layers[0].bias = assign(
gpt.trf_blocks[b].ff.layers[0].bias,
params["blocks"][b]["mlp"]["c_fc"]["b"])
gpt.trf_blocks[b].ff.layers[2].weight = assign(
gpt.trf_blocks[b].ff.layers[2].weight,
params["blocks"][b]["mlp"]["c_proj"]["w"].T)
gpt.trf_blocks[b].ff.layers[2].bias = assign(
gpt.trf_blocks[b].ff.layers[2].bias,
params["blocks"][b]["mlp"]["c_proj"]["b"])
gpt.trf_blocks[b].norm1.scale = assign(
gpt.trf_blocks[b].norm1.scale,
params["blocks"][b]["ln_1"]["g"])
gpt.trf_blocks[b].norm1.shift = assign(
gpt.trf_blocks[b].norm1.shift,
params["blocks"][b]["ln_1"]["b"])
gpt.trf_blocks[b].norm2.scale = assign(
gpt.trf_blocks[b].norm2.scale,
params["blocks"][b]["ln_2"]["g"])
gpt.trf_blocks[b].norm2.shift = assign(
gpt.trf_blocks[b].norm2.shift,
params["blocks"][b]["ln_2"]["b"])
gpt.final_norm.scale = assign(gpt.final_norm.scale, params["g"])
gpt.final_norm.shift = assign(gpt.final_norm.shift, params["b"])
gpt.out_head.weight = assign(gpt.out_head.weight, params["wte"])
def generate(model, idx, max_new_tokens, context_size, temperature=0.0, top_k=None, eos_id=None):
# For-loop is the same as before: Get logits, and only focus on last time step
for _ in range(max_new_tokens):
idx_cond = idx[:, -context_size:]
with torch.no_grad():
logits = model(idx_cond)
logits = logits[:, -1, :]
# New: Filter logits with top_k sampling
if top_k is not None:
# Keep only top_k values
top_logits, _ = torch.topk(logits, top_k)
min_val = top_logits[:, -1]
logits = torch.where(logits < min_val, torch.tensor(float('-inf')).to(logits.device), logits)
# New: Apply temperature scaling
if temperature > 0.0:
logits = logits / temperature
# Apply softmax to get probabilities
probs = torch.softmax(logits, dim=-1) # (batch_size, context_len)
# Sample from the distribution
idx_next = torch.multinomial(probs, num_samples=1) # (batch_size, 1)
# Otherwise same as before: get idx of the vocab entry with the highest logits value
else:
idx_next = torch.argmax(logits, dim=-1, keepdim=True) # (batch_size, 1)
if idx_next == eos_id: # Stop generating early if end-of-sequence token is encountered and eos_id is specified
break
# Same as before: append sampled index to the running sequence
idx = torch.cat((idx, idx_next), dim=1) # (batch_size, num_tokens+1)
return idx

8
ch05/07_gpt_to_llama/converting-gpt-to-llama2.ipynb
View File

@@ -1264,6 +1264,12 @@
],
"source": [
"from previous_chapters import generate, text_to_token_ids, token_ids_to_text\n",
"# If the `previous_chapters.py` file is not available locally,\n",
"# you can import it from the `llms-from-scratch` PyPI package.\n",
"# For details, see: https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg\n",
"# E.g.,\n",
"# from llms_from_scratch.ch05 import generate, text_to_token_ids, token_ids_to_text\n",
"\n",
"\n",
"\n",
"torch.manual_seed(123)\n",
@@ -1691,7 +1697,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.16"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {

5
ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb
View File

@@ -1324,6 +1324,11 @@
],
"source": [
"from previous_chapters import generate, text_to_token_ids, token_ids_to_text\n",
"# If the `previous_chapters.py` file is not available locally,\n",
"# you can import it from the `llms-from-scratch` PyPI package.\n",
"# For details, see: https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg\n",
"# E.g.,\n",
"# from llms_from_scratch.ch05 import generate, text_to_token_ids, token_ids_to_text\n",
"\n",
"\n",
"torch.manual_seed(123)\n",

8
ch05/08_memory_efficient_weight_loading/memory-efficient-state-dict.ipynb
View File

@@ -161,6 +161,12 @@
"outputs": [],
"source": [
"from previous_chapters import GPTModel\n",
"# If the `previous_chapters.py` file is not available locally,\n",
"# you can import it from the `llms-from-scratch` PyPI package.\n",
"# For details, see: https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg\n",
"# E.g.,\n",
"# from llms_from_scratch.ch04 import GPTModel\n",
"\n",
"\n",
"\n",
"BASE_CONFIG = {\n",
@@ -921,7 +927,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.16"
}
},
"nbformat": 4,

12
ch05/09_extending-tokenizers/extend-tiktoken.ipynb
View File

@@ -301,8 +301,9 @@
}
],
"source": [
"# Relative import from the gpt_download.py contained in this folder\n",
"from gpt_download import download_and_load_gpt2\n",
"from llms_from_scratch.ch05 import download_and_load_gpt2\n",
"# For llms_from_scratch installation instructions, see:\n",
"# https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg\n",
"\n",
"settings, params = download_and_load_gpt2(model_size=\"124M\", models_dir=\"gpt2\")"
]
@@ -314,8 +315,9 @@
"metadata": {},
"outputs": [],
"source": [
"# Relative import from the gpt_download.py contained in this folder\n",
"from previous_chapters import GPTModel\n",
"from llms_from_scratch.ch04 import GPTModel\n",
"# For llms_from_scratch installation instructions, see:\n",
"# https://github.com/rasbt/LLMs-from-scratch/tree/main/pkg\n",
"\n",
"GPT_CONFIG_124M = {\n",
" \"vocab_size\": 50257, # Vocabulary size\n",
@@ -763,7 +765,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.16"
}
},
"nbformat": 4,

157
ch05/09_extending-tokenizers/gpt_download.py
View File

@@ -1,157 +0,0 @@
# 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
import os
import urllib.request
# import requests
import json
import numpy as np
import tensorflow as tf
from tqdm import tqdm
def download_and_load_gpt2(model_size, models_dir):
# Validate model size
allowed_sizes = ("124M", "355M", "774M", "1558M")
if model_size not in allowed_sizes:
raise ValueError(f"Model size not in {allowed_sizes}")
# Define paths
model_dir = os.path.join(models_dir, model_size)
base_url = "https://openaipublic.blob.core.windows.net/gpt-2/models"
backup_base_url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/gpt2"
filenames = [
"checkpoint", "encoder.json", "hparams.json",
"model.ckpt.data-00000-of-00001", "model.ckpt.index",
"model.ckpt.meta", "vocab.bpe"
]
# Download files
os.makedirs(model_dir, exist_ok=True)
for filename in filenames:
file_url = os.path.join(base_url, model_size, filename)
backup_url = os.path.join(backup_base_url, model_size, filename)
file_path = os.path.join(model_dir, filename)
download_file(file_url, file_path, backup_url)
# Load settings and params
tf_ckpt_path = tf.train.latest_checkpoint(model_dir)
settings = json.load(open(os.path.join(model_dir, "hparams.json"), "r", encoding="utf-8"))
params = load_gpt2_params_from_tf_ckpt(tf_ckpt_path, settings)
return settings, params
def download_file(url, destination, backup_url=None):
def _attempt_download(download_url):
with urllib.request.urlopen(download_url) as response:
# Get the total file size from headers, defaulting to 0 if not present
file_size = int(response.headers.get("Content-Length", 0))
# Check if file exists and has the same size
if os.path.exists(destination):
file_size_local = os.path.getsize(destination)
if file_size == file_size_local:
print(f"File already exists and is up-to-date: {destination}")
return True # Indicate success without re-downloading
block_size = 1024 # 1 Kilobyte
# Initialize the progress bar with total file size
progress_bar_description = os.path.basename(download_url)
with tqdm(total=file_size, unit="iB", unit_scale=True, desc=progress_bar_description) as progress_bar:
with open(destination, "wb") as file:
while True:
chunk = response.read(block_size)
if not chunk:
break
file.write(chunk)
progress_bar.update(len(chunk))
return True
try:
if _attempt_download(url):
return
except (urllib.error.HTTPError, urllib.error.URLError):
if backup_url is not None:
print(f"Primary URL ({url}) failed. Attempting backup URL: {backup_url}")
try:
if _attempt_download(backup_url):
return
except urllib.error.HTTPError:
pass
# If we reach here, both attempts have failed
error_message = (
f"Failed to download from both primary URL ({url})"
f"{' and backup URL (' + backup_url + ')' if backup_url else ''}."
"\nCheck your internet connection or the file availability.\n"
"For help, visit: https://github.com/rasbt/LLMs-from-scratch/discussions/273"
)
print(error_message)
except Exception as e:
print(f"An unexpected error occurred: {e}")
# Alternative way using `requests`
"""
def download_file(url, destination):
# Send a GET request to download the file in streaming mode
response = requests.get(url, stream=True)
# Get the total file size from headers, defaulting to 0 if not present
file_size = int(response.headers.get("content-length", 0))
# Check if file exists and has the same size
if os.path.exists(destination):
file_size_local = os.path.getsize(destination)
if file_size == file_size_local:
print(f"File already exists and is up-to-date: {destination}")
return
# Define the block size for reading the file
block_size = 1024 # 1 Kilobyte
# Initialize the progress bar with total file size
progress_bar_description = url.split("/")[-1] # Extract filename from URL
with tqdm(total=file_size, unit="iB", unit_scale=True, desc=progress_bar_description) as progress_bar:
# Open the destination file in binary write mode
with open(destination, "wb") as file:
# Iterate over the file data in chunks
for chunk in response.iter_content(block_size):
progress_bar.update(len(chunk)) # Update progress bar
file.write(chunk) # Write the chunk to the file
"""
def load_gpt2_params_from_tf_ckpt(ckpt_path, settings):
# Initialize parameters dictionary with empty blocks for each layer
params = {"blocks": [{} for _ in range(settings["n_layer"])]}
# Iterate over each variable in the checkpoint
for name, _ in tf.train.list_variables(ckpt_path):
# Load the variable and remove singleton dimensions
variable_array = np.squeeze(tf.train.load_variable(ckpt_path, name))
# Process the variable name to extract relevant parts
variable_name_parts = name.split("/")[1:] # Skip the 'model/' prefix
# Identify the target dictionary for the variable
target_dict = params
if variable_name_parts[0].startswith("h"):
layer_number = int(variable_name_parts[0][1:])
target_dict = params["blocks"][layer_number]
# Recursively access or create nested dictionaries
for key in variable_name_parts[1:-1]:
target_dict = target_dict.setdefault(key, {})
# Assign the variable array to the last key
last_key = variable_name_parts[-1]
target_dict[last_key] = variable_array
return params

279
ch05/09_extending-tokenizers/previous_chapters.py
View File

@@ -1,279 +0,0 @@
# 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 2-4.
# This file can be run as a standalone script.
import tiktoken
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
#####################################
# Chapter 2
#####################################
class GPTDatasetV1(Dataset):
def __init__(self, txt, tokenizer, max_length, stride):
self.input_ids = []
self.target_ids = []
# Tokenize the entire text
token_ids = tokenizer.encode(txt, allowed_special={"<|endoftext|>"})
# Use a sliding window to chunk the book into overlapping sequences of max_length
for i in range(0, len(token_ids) - max_length, stride):
input_chunk = token_ids[i:i + max_length]
target_chunk = token_ids[i + 1: i + max_length + 1]
self.input_ids.append(torch.tensor(input_chunk))
self.target_ids.append(torch.tensor(target_chunk))
def __len__(self):
return len(self.input_ids)
def __getitem__(self, idx):
return self.input_ids[idx], self.target_ids[idx]
def create_dataloader_v1(txt, batch_size=4, max_length=256,
stride=128, shuffle=True, drop_last=True, num_workers=0):
# Initialize the tokenizer
tokenizer = tiktoken.get_encoding("gpt2")
# Create dataset
dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)
# Create dataloader
dataloader = DataLoader(
dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, num_workers=num_workers)
return dataloader
#####################################
# 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
def generate_text_simple(model, idx, max_new_tokens, context_size):
# idx is (B, T) array of indices in the current context
for _ in range(max_new_tokens):
# Crop current context if it exceeds the supported context size
# E.g., if LLM supports only 5 tokens, and the context size is 10
# then only the last 5 tokens are used as context
idx_cond = idx[:, -context_size:]
# Get the predictions
with torch.no_grad():
logits = model(idx_cond)
# Focus only on the last time step
# (batch, n_token, vocab_size) becomes (batch, vocab_size)
logits = logits[:, -1, :]
# Get the idx of the vocab entry with the highest logits value
idx_next = torch.argmax(logits, dim=-1, keepdim=True) # (batch, 1)
# Append sampled index to the running sequence
idx = torch.cat((idx, idx_next), dim=1) # (batch, n_tokens+1)
return idx
if __name__ == "__main__":
GPT_CONFIG_124M = {
"vocab_size": 50257, # Vocabulary size
"context_length": 1024, # Context length
"emb_dim": 768, # Embedding dimension
"n_heads": 12, # Number of attention heads
"n_layers": 12, # Number of layers
"drop_rate": 0.1, # Dropout rate
"qkv_bias": False # Query-Key-Value bias
}
torch.manual_seed(123)
model = GPTModel(GPT_CONFIG_124M)
model.eval() # disable dropout
start_context = "Hello, I am"
tokenizer = tiktoken.get_encoding("gpt2")
encoded = tokenizer.encode(start_context)
encoded_tensor = torch.tensor(encoded).unsqueeze(0)
print(f"\n{50*'='}\n{22*' '}IN\n{50*'='}")
print("\nInput text:", start_context)
print("Encoded input text:", encoded)
print("encoded_tensor.shape:", encoded_tensor.shape)
out = generate_text_simple(
model=model,
idx=encoded_tensor,
max_new_tokens=10,
context_size=GPT_CONFIG_124M["context_length"]
)
decoded_text = tokenizer.decode(out.squeeze(0).tolist())
print(f"\n\n{50*'='}\n{22*' '}OUT\n{50*'='}")
print("\nOutput:", out)
print("Output length:", len(out[0]))
print("Output text:", decoded_text)