mirror of
https://github.com/mii443/tokenizers.git
synced 2025-09-01 23:09:34 +00:00
Doc - Hotfix training from iterators tutorial
This commit is contained in:
@ -14,7 +14,7 @@ class TestTrainFromIterators:
|
|||||||
tokenizer = Tokenizer(models.Unigram())
|
tokenizer = Tokenizer(models.Unigram())
|
||||||
tokenizer.normalizer = normalizers.NFKC()
|
tokenizer.normalizer = normalizers.NFKC()
|
||||||
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel()
|
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel()
|
||||||
tokenizer.decoders = decoders.ByteLevel()
|
tokenizer.decoder = decoders.ByteLevel()
|
||||||
|
|
||||||
trainer = trainers.UnigramTrainer(
|
trainer = trainers.UnigramTrainer(
|
||||||
vocab_size=20000,
|
vocab_size=20000,
|
||||||
|
Reference in New Issue
Block a user