from openmind import AutoTokenizer, AutoModelForCausalLM, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
import argparse
import sys
import time

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="zhouhui/Qwen2-0.5B-ITA-Instruct",
    )
    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"
    start_time = time.time()      
    model = AutoModelForCausalLM.from_pretrained(model_path).to(device)
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    model.eval()

    prompt = "Ciao, chi sono? Aiutami a tradurre in italiano"
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
    outputs = model.generate(input_ids=input_ids, max_length=100)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    print(response)
    end_time = time.time()
    print(f"硬件环境：{device},推理执行时间：{end_time - start_time}秒")
    
if __name__ == "__main__":
    main()