generate.py

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("gpt2-finetuned-qa")
tokenizer = AutoTokenizer.from_pretrained("gpt2-finetuned-qa")

while True:
    prompt = input("Q: ").strip()
    if prompt.lower() in ["exit", "quit"]:
        break
    full_prompt = f"Q: {prompt}\nA:"
    inputs = tokenizer(full_prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=32, pad_token_id=tokenizer.eos_token_id)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))
    print()