from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
torch.manual_seed(0)

# Set device to CPU for now
device = 'cpu'

# Load model and tokenizer
model_id = 'gpt2'
model = AutoModelForCausalLM.from_pretrained(model_id).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Print model size
print(f"Model size: {model.get_memory_footprint():,} bytes")