File size: 598 Bytes
2155c30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 | from datasets import load_dataset
from tokenizers import ByteLevelBPETokenizer
dataset = load_dataset("HuggingFaceFW/fineweb-edu", "sample-10BT", split="train", streaming=True)
def get_training_corpus():
dataset_iter = iter(dataset)
for _ in range(50000):
yield next(dataset_iter)["text"]
tokenizer = ByteLevelBPETokenizer()
tokenizer.train_from_iterator(
get_training_corpus(),
vocab_size=500,
min_frequency=2,
special_tokens=["<s>", "<pad>", "</s>", "<unk>", "<mask>"]
)
tokenizer.save_model(".", "custom_llama_tokenizer")
print("Tokenizer training complete!") |