mii/tokenizers
1
0
Fork 0
mirror of https://github.com/mii443/tokenizers.git synced 2025-08-22 16:25:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update bindings and typings

Browse Source
This commit is contained in:
Anthony MOI
2020-03-10 12:28:24 -04:00
parent efbbfea558
commit 45f3eaaf72
8 changed files with 45 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
bindings/python/README.md
View File

@ -134,7 +134,7 @@ tokenizer = Tokenizer(bpe)
# Customize pre-tokenization and decoding
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=True)
tokenizer.decoder = decoders.ByteLevel()
tokenizer.post_processor = processors.ByteLevel()
tokenizer.post_processor = processors.ByteLevel(trim_offsets=True)
# And then encode:
encoded = tokenizer.encode("I can feel the magic, can you?")
@ -160,7 +160,7 @@ tokenizer = Tokenizer(models.BPE.empty())
# Customize pre-tokenization and decoding
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=True)
tokenizer.decoder = decoders.ByteLevel()
tokenizer.post_processor = processors.ByteLevel()
tokenizer.post_processor = processors.ByteLevel(trim_offsets=True)
# And then train
trainer = trainers.BpeTrainer(vocab_size=20000, min_frequency=2)