prompts = [
    "Once upon a time",
    "Lucy had a red ball.",
    "Tom and Jane were friends.",
    "A little cat wanted",
]

for p in prompts:
    inputs = tokenizer(p, return_tensors="pt").to(model.device)

    outputs = model.generate(
        **inputs,
        max_new_tokens=80,
        temperature=0.7,
        top_p=0.9,
        repetition_penalty=1.15,
        do_sample=True,
    )

    print("\nPROMPT:", p)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))