BramVanroy

#!/usr/bin/env python
# coding=utf-8
# Copyright 2020 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#

BramVanroy

import gc

import numpy as np
import time

import pandas as pd
from tqdm import tqdm


def pack_documents_original(tokenized_documents, block_size: int = 8192, use_tqdm=True):

BramVanroy

from dataclasses import dataclass, field

import torch
from torch import LongTensor, Tensor
from transformers import (
    AutoTokenizer,
    AutoModel,
    PreTrainedModel,
    PreTrainedTokenizer,
    BatchEncoding,

BramVanroy

from typing import Counter
from datasets import load_dataset
from tqdm import tqdm


ds = load_dataset("HuggingFaceFW/fineweb-2", "nld_Latn", split="train")
ds_size = len(ds)

print(f"Dataset size: {ds_size:,}")  #
counts = Counter(ds["id"])