import torch
from transformers import AutoTokenizer
# download model.py and pytorch_model.bin manually or via hf_hub_download
from model import GPT, GPTConfig

device = 'cuda' if torch.cuda.is_available() else 'cpu'

tokenizer = AutoTokenizer.from_pretrained("rudyon/rudygpt")
model = GPT(GPTConfig(depth=12, vocab_size=50304))
state_dict = torch.load("pytorch_model.bin", map_location=device)
model.load_state_dict(state_dict)
model.eval()
print(model.generate("Hello!"))