pip install torch numpy transformers datasets tiktoken wandb tqdm

# Prepare data
python data/shakespeare_char/prepare.py

# Train (5 minutes on CPU)
python train.py config/train_shakespeare_char.py

# Generate text
python sample.py --out_dir=out-shakespeare-char

ROMEO:
What say'st thou? Shall I speak, and be a man?

JULIET:
I am afeard, and yet I'll speak; for thou art
One that hath been a man, and yet I know not
What thou art.

# Step 1: Prepare data (creates train.bin, val.bin)
python data/shakespeare_char/prepare.py

# Step 2: Train small model
python train.py config/train_shakespeare_char.py

# Step 3: Generate text
python sample.py --out_dir=out-shakespeare-char

# Model config
n_layer = 6          # 6 transformer layers
n_head = 6           # 6 attention heads
n_embd = 384         # 384-dim embeddings
block_size = 256     # 256 char context

# Training config
batch_size = 64
learning_rate = 1e-3
max_iters = 5000
eval_interval = 500

# Hardware
device = 'cpu'  # Or 'cuda'
compile = False # Set True for PyTorch 2.0

# Step 1: Prepare OpenWebText (takes ~1 hour)
python data/openwebtext/prepare.py

# Step 2: Train GPT-2 124M with DDP (8 GPUs)
torchrun --standalone --nproc_per_node=8 \
  train.py config/train_gpt2.py

# Step 3: Sample from trained model
python sample.py --out_dir=out

# GPT-2 (124M) architecture
n_layer = 12
n_head = 12
n_embd = 768
block_size = 1024
dropout = 0.0

# Training
batch_size = 12
gradient_accumulation_steps = 5 * 8  # Total batch ~0.5M tokens
learning_rate = 6e-4
max_iters = 600000
lr_decay_iters = 600000

# System
compile = True  # PyTorch 2.0

# In train.py or config
init_from = 'gpt2'  # Options: gpt2, gpt2-medium, gpt2-large, gpt2-xl

# Model loads OpenAI weights automatically
python train.py config/finetune_shakespeare.py

# Start from GPT-2
init_from = 'gpt2'

# Dataset
dataset = 'shakespeare_char'
batch_size = 1
block_size = 1024

# Fine-tuning
learning_rate = 3e-5  # Lower LR for fine-tuning
max_iters = 2000
warmup_iters = 100

# Regularization
weight_decay = 1e-1

# data/custom/prepare.py
import numpy as np

# Load your data
with open('my_data.txt', 'r') as f:
    text = f.read()

# Create character mappings
chars = sorted(list(set(text)))
stoi = {ch: i for i, ch in enumerate(chars)}
itos = {i: ch for i, ch in enumerate(chars)}

# Tokenize
data = np.array([stoi[ch] for ch in text], dtype=np.uint16)

# Split train/val
n = len(data)
train_data = data[:int(n*0.9)]
val_data = data[int(n*0.9):]

# Save
train_data.tofile('data/custom/train.bin')
val_data.tofile('data/custom/val.bin')

python data/custom/prepare.py
python train.py --dataset=custom

batch_size = 1  # Reduce from 12
block_size = 512  # Reduce from 1024
gradient_accumulation_steps = 40  # Increase to maintain effective batch

compile = True  # 2× speedup

dtype = 'bfloat16'  # Or 'float16'

max_iters = 10000  # Increase from 5000

# In sample.py
temperature = 0.7  # Lower from 1.0
top_k = 200       # Add top-k sampling

pip install transformers

init_from = 'gpt2'  # Valid: gpt2, gpt2-medium, gpt2-large, gpt2-xl