from pathlib import Path

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


MODEL_PATH = "."
MODEL_SUBFOLDER = "hf"
PROMPT = "There was a little"
SEED = 0


def main() -> None:
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model_dir = Path(MODEL_PATH) / MODEL_SUBFOLDER
    tokenizer = AutoTokenizer.from_pretrained(model_dir)
    model = AutoModelForCausalLM.from_pretrained(
        model_dir,
        dtype=torch.float32,
    ).to(device)
    model.eval()

    input_ids = torch.tensor(
        [
            [tokenizer.bos_token_id]
            + tokenizer.encode(PROMPT, add_special_tokens=False)
        ],
        dtype=torch.long,
        device=device,
    )

    torch.manual_seed(SEED)
    if device.type == "cuda":
        torch.cuda.manual_seed_all(SEED)

    with torch.no_grad():
        output = model.generate(
            input_ids=input_ids,
            max_new_tokens=100,
            do_sample=True,
            temperature=0.8,
            top_p=0.95,
            top_k=40,
            repetition_penalty=1.1,
            pad_token_id=tokenizer.pad_token_id,
            eos_token_id=tokenizer.eos_token_id,
        )

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


if __name__ == "__main__":
    main()