import argparse
import torch
from openmind import is_torch_npu_available, AutoTokenizer, AutoModelForCausalLM,AutoModel
import time
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] # model_output的第一个元素包含所有token嵌入
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default='InsTagger',
    )

    args = parser.parse_args()
    return args


def main():
    start_time = time.time()  # 记录开始时间

    args = parse_args()
    if args.model_name_or_path:
        model_path = args.model_name_or_path
    else:
        model_path = ""

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device='cpu'
    device='cpu'
    sentences = ['This is an example sentence', 'Each sentence is converted']

    # 从openmind_hub加载模型
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    tokenizer.add_special_tokens({'pad_token': '[PAD]'})
    model = AutoModel.from_pretrained(model_path).to(device)

    # 对句子进行分词
    encoded_input = tokenizer(sentences,return_tensors='pt',padding=True).to(device)

    # 计算token嵌入
    with torch.no_grad():
        model_output = model(**encoded_input)

    # 执行池化
    sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']).to(device)

    # 归一化嵌入
    #     sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)

    print("Sentence embeddings:")
    print(sentence_embeddings)

    end_time = time.time()  # 记录结束时间
    elapsed_time = end_time - start_time  # 计算差值
    print(f"{device}:Program finished in {elapsed_time:.2f} seconds.")  # 打印运行时间


if __name__ == "__main__":
    main()