!pip install datasets evaluate transformers[sentencepiece]

from datasets import load_dataset

dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")


def get_training_corpus():
    for i in range(0, len(dataset), 1000):
        yield dataset[i : i + 1000]["text"]

with open("wikitext-2.txt", "w", encoding="utf-8") as f:
    for i in range(len(dataset)):
        f.write(dataset[i]["text"] + "\n")

from tokenizers import (
    decoders,
    models,
    normalizers,
    pre_tokenizers,
    processors,
    trainers,
    Tokenizer,
)

tokenizer = Tokenizer(models.WordPiece(unk_token="[UNK]"))

tokenizer.normalizer = normalizers.BertNormalizer(lowercase=True)

tokenizer.normalizer = normalizers.Sequence(
    [normalizers.NFD(), normalizers.Lowercase(), normalizers.StripAccents()]
)

print(tokenizer.normalizer.normalize_str("Héllò hôw are ü?"))

tokenizer.pre_tokenizer = pre_tokenizers.BertPreTokenizer()

tokenizer.pre_tokenizer = pre_tokenizers.Whitespace()

tokenizer.pre_tokenizer.pre_tokenize_str("Let's test my pre-tokenizer.")

pre_tokenizer = pre_tokenizers.WhitespaceSplit()
pre_tokenizer.pre_tokenize_str("Let's test my pre-tokenizer.")

pre_tokenizer = pre_tokenizers.Sequence(
    [pre_tokenizers.WhitespaceSplit(), pre_tokenizers.Punctuation()]
)
pre_tokenizer.pre_tokenize_str("Let's test my pre-tokenizer.")

special_tokens = ["[UNK]", "[PAD]", "[CLS]", "[SEP]", "[MASK]"]
trainer = trainers.WordPieceTrainer(vocab_size=25000, special_tokens=special_tokens)

tokenizer.train_from_iterator(get_training_corpus(), trainer=trainer)

tokenizer.model = models.WordPiece(unk_token="[UNK]")
tokenizer.train(["wikitext-2.txt"], trainer=trainer)

encoding = tokenizer.encode("Let's test this tokenizer.")
print(encoding.tokens)

cls_token_id = tokenizer.token_to_id("[CLS]")
sep_token_id = tokenizer.token_to_id("[SEP]")
print(cls_token_id, sep_token_id)

tokenizer.post_processor = processors.TemplateProcessing(
    single=f"[CLS]:0 $A:0 [SEP]:0",
    pair=f"[CLS]:0 $A:0 [SEP]:0 $B:1 [SEP]:1",
    special_tokens=[("[CLS]", cls_token_id), ("[SEP]", sep_token_id)],
)

encoding = tokenizer.encode("Let's test this tokenizer.")
print(encoding.tokens)

encoding = tokenizer.encode("Let's test this tokenizer...", "on a pair of sentences.")
print(encoding.tokens)
print(encoding.type_ids)

tokenizer.decoder = decoders.WordPiece(prefix="##")

tokenizer.decode(encoding.ids)

tokenizer.save("tokenizer.json")

new_tokenizer = Tokenizer.from_file("tokenizer.json")

from transformers import PreTrainedTokenizerFast

wrapped_tokenizer = PreTrainedTokenizerFast(
    tokenizer_object=tokenizer,
    # tokenizer_file="tokenizer.json", # Bạn có thể tải từ tệp tokenizer
    unk_token="[UNK]",
    pad_token="[PAD]",
    cls_token="[CLS]",
    sep_token="[SEP]",
    mask_token="[MASK]",
)

from transformers import BertTokenizerFast

wrapped_tokenizer = BertTokenizerFast(tokenizer_object=tokenizer)

tokenizer = Tokenizer(models.BPE())

tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=False)

tokenizer.pre_tokenizer.pre_tokenize_str("Let's test pre-tokenization!")

trainer = trainers.BpeTrainer(vocab_size=25000, special_tokens=["<|endoftext|>"])
tokenizer.train_from_iterator(get_training_corpus(), trainer=trainer)

tokenizer.model = models.BPE()
tokenizer.train(["wikitext-2.txt"], trainer=trainer)

encoding = tokenizer.encode("Let's test this tokenizer.")
print(encoding.tokens)

tokenizer.post_processor = processors.ByteLevel(trim_offsets=False)

sentence = "Let's test this tokenizer."
encoding = tokenizer.encode(sentence)
start, end = encoding.offsets[4]
sentence[start:end]

tokenizer.decoder = decoders.ByteLevel()

tokenizer.decode(encoding.ids)

from transformers import PreTrainedTokenizerFast

wrapped_tokenizer = PreTrainedTokenizerFast(
    tokenizer_object=tokenizer,
    bos_token="<|endoftext|>",
    eos_token="<|endoftext|>",
)

from transformers import GPT2TokenizerFast

wrapped_tokenizer = GPT2TokenizerFast(tokenizer_object=tokenizer)

tokenizer = Tokenizer(models.Unigram())

from tokenizers import Regex

tokenizer.normalizer = normalizers.Sequence(
    [
        normalizers.Replace("``", '"'),
        normalizers.Replace("''", '"'),
        normalizers.NFKD(),
        normalizers.StripAccents(),
        normalizers.Replace(Regex(" {2,}"), " "),
    ]
)

tokenizer.pre_tokenizer = pre_tokenizers.Metaspace()

tokenizer.pre_tokenizer.pre_tokenize_str("Let's test the pre-tokenizer!")

special_tokens = ["<cls>", "<sep>", "<unk>", "<pad>", "<mask>", "<s>", "</s>"]
trainer = trainers.UnigramTrainer(
    vocab_size=25000, special_tokens=special_tokens, unk_token="<unk>"
)
tokenizer.train_from_iterator(get_training_corpus(), trainer=trainer)

tokenizer.model = models.Unigram()
tokenizer.train(["wikitext-2.txt"], trainer=trainer)

encoding = tokenizer.encode("Let's test this tokenizer.")
print(encoding.tokens)

cls_token_id = tokenizer.token_to_id("<cls>")
sep_token_id = tokenizer.token_to_id("<sep>")
print(cls_token_id, sep_token_id)

tokenizer.post_processor = processors.TemplateProcessing(
    single="$A:0 <sep>:0 <cls>:2",
    pair="$A:0 <sep>:0 $B:1 <sep>:1 <cls>:2",
    special_tokens=[("<sep>", sep_token_id), ("<cls>", cls_token_id)],
)

encoding = tokenizer.encode("Let's test this tokenizer...", "on a pair of sentences!")
print(encoding.tokens)
print(encoding.type_ids)

tokenizer.decoder = decoders.Metaspace()

from transformers import PreTrainedTokenizerFast

wrapped_tokenizer = PreTrainedTokenizerFast(
    tokenizer_object=tokenizer,
    bos_token="<s>",
    eos_token="</s>",
    unk_token="<unk>",
    pad_token="<pad>",
    cls_token="<cls>",
    sep_token="<sep>",
    mask_token="<mask>",
    padding_side="left",
)

from transformers import XLNetTokenizerFast

wrapped_tokenizer = XLNetTokenizerFast(tokenizer_object=tokenizer)