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

def average_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/japanese-gpt2-medium-openmind",
    )
    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"
        
    # Each input text should start with "query: " or "passage: ".
    # For tasks other than retrieval, you can simply use the "query: " prefix.
    input_texts = ['query: how much protein should a female eat',
                   'query: summit define',
                   "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
                   "passage: Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."]

    tokenizer = AutoTokenizer.from_pretrained(model_path)
    model = AutoModel.from_pretrained(model_path)

    # Tokenize the input texts
    batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

    outputs = model(**batch_dict)
    embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

    # normalize embeddings
    embeddings = F.normalize(embeddings, p=2, dim=1)
    scores = (embeddings[:2] @ embeddings[2:].T) * 100
    print(scores.tolist())
    
if __name__ == "__main__":
    main()

@misc{rinna-japanese-gpt2-medium,
    title = {rinna/japanese-gpt2-medium},
    author = {Zhao, Tianyu and Sawada, Kei},
    url = {https://huggingface.co/rinna/japanese-gpt2-medium}
}

@inproceedings{sawada2024release,
    title = {Release of Pre-Trained Models for the {J}apanese Language},
    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
    month = {5},
    year = {2024},
    pages = {13898--13905},
    url = {https://aclanthology.org/2024.lrec-main.1213},
    note = {\url{https://arxiv.org/abs/2404.01657}}
}