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

Python - Also update README

Browse Source
This commit is contained in:
Anthony MOI
2020-01-07 15:24:39 -05:00
parent cc33418044
commit 3f806a2b5f
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
bindings/python/README.md
View File

@ -61,8 +61,8 @@ bpe = models.BPE.from_files(vocab, merges)
tokenizer = Tokenizer(bpe)
# Customize pre-tokenization and decoding
tokenizer.with_pre_tokenizer(pre_tokenizers.ByteLevel.new(add_prefix_space=True))
tokenizer.with_decoder(decoders.ByteLevel.new())
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel.new(add_prefix_space=True)
tokenizer.decoder = decoders.ByteLevel.new()
# And then encode:
encoded = tokenizer.encode("I can feel the magic, can you?")
@ -85,8 +85,8 @@ from tokenizers import Tokenizer, models, pre_tokenizers, decoders, trainers
tokenizer = Tokenizer(models.BPE.empty())
# Customize pre-tokenization and decoding
tokenizer.with_pre_tokenizer(pre_tokenizers.ByteLevel.new(add_prefix_space=True))
tokenizer.with_decoder(decoders.ByteLevel.new())
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel.new(add_prefix_space=True)
tokenizer.decoder = decoders.ByteLevel.new())
# And then train
trainer = trainers.BpeTrainer.new(vocab_size=20000, min_frequency=2)