Load pre-trained model and tokenizer

model = GPT2LMHeadModel.from_pretrained('gpt2') tokenizer = GPT2Tokenizer.from_pretrained('gpt2')

Define prompt and generate text

prompt = "Generate a 3D model of a hugging face" input_ids = tokenizer.encode(prompt, return_tensors='pt') output = model.generate(input_ids, max_length=50, do_sample=True)

Convert output to text and print

output_text = tokenizer.decode(output[0], skip_special_tokens=True) print(output_text)