src/submission/check_validity.py

import json
import os
import re
from collections import defaultdict
from datetime import datetime, timedelta, timezone

import huggingface_hub
from huggingface_hub import ModelCard
from huggingface_hub.hf_api import ModelInfo
from transformers import AutoConfig
from transformers.models.auto.tokenization_auto import AutoTokenizer


def already_submitted_models(requested_models_dir: str) -> set[str]:
    """Gather a list of already submitted models to avoid duplicates"""
    depth = 1
    file_names = []
    users_to_submission_dates = defaultdict(list)

    for root, _, files in os.walk(requested_models_dir):
        current_depth = root.count(os.sep) - requested_models_dir.count(os.sep)
        if current_depth == depth:
            for file in files:
                if not file.endswith(".json"):
                    continue
                with open(os.path.join(root, file), "r") as f:
                    info = json.load(f)
                    file_names.append(f"{info['model']}_{info['revision']}")

                    # Select organisation
                    if info["model"].count("/") == 0 or "submitted_time" not in info:
                        continue
                    organisation, _ = info["model"].split("/")
                    users_to_submission_dates[organisation].append(info["submitted_time"])

    return set(file_names), users_to_submission_dates