NameError：Python 代码中未定义名称“tokenize_and_split_data”

问：

我想将数据分为变量。该函数不起作用，库未定义。我正在研究 Python google colab。train_datasettest_datasettokenize_and_split_datautilities

import datasets
import tempfile
import logging
import random
import config
import os
import yaml
import time
import torch
import transformers
import pandas as pd
import jsonlines

#from utilities import *
from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM
from transformers import TrainingArguments
from transformers import AutoModelForCausalLM

logger = logging.getLogger(__name__)
global_config = None

model_name = "EleutherAI/pythia-70m"

training_config = {
    "model": {
        "pretrained_name": model_name,
        "max_length" : 2048
    },
    "datasets": {
        "use_hf": use_hf,
        "path": dataset_path
    },
    "verbose": True
}

tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
train_dataset, test_dataset = tokenize_and_split_data(training_config, tokenizer)

print(train_dataset)
print(test_dataset)

上面是代码，我无法安装库，并且没有定义这个函数。你能帮帮我吗？utilitiestokenize_and_split_data