from openmind import AutoTokenizer, AutoModelForCausalLM, is_torch_npu_available
from openmind_hub import snapshot_download
import torch
import argparse

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="models/DialoGPT-small",
    )
    args = parser.parse_args()
    return args

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
    
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    model = AutoModelForCausalLM.from_pretrained(model_path).to(device)

    # Let's chat for 5 lines
    for step in range(5):
        # encode the new user input, add the eos_token and return a tensor in Pytorch
        new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt').to(device)

        # append the new user input tokens to the chat history
        bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids

        # generated a response while limiting the total chat history to 1000 tokens, 
        chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)

        # pretty print last ouput tokens from bot
        print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
    
if __name__ == "__main__":
    main()