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 - Update docs and implementations

Browse Source
This commit is contained in:
Anthony MOI
2020-03-04 16:47:05 -05:00
parent 2393506dc7
commit f1460fadb9
3 changed files with 12 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
bindings/python/README.md
View File

@ -121,7 +121,7 @@ you need together:
#### Use a pre-trained tokenizer
```python
from tokenizers import Tokenizer, models, pre_tokenizers, decoders
from tokenizers import Tokenizer, models, pre_tokenizers, decoders, normalizers
# Load a BPE Model
vocab = "./path/to/vocab.json"
@ -132,7 +132,8 @@ bpe = models.BPE.from_files(vocab, merges)
tokenizer = Tokenizer(bpe)
# Customize pre-tokenization and decoding
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=True)
tokenizer.normalizer = normalizers.ByteLevel(add_prefix_space=True)
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel()
tokenizer.decoder = decoders.ByteLevel()
# And then encode:
@ -157,7 +158,8 @@ from tokenizers import Tokenizer, models, pre_tokenizers, decoders, trainers
tokenizer = Tokenizer(models.BPE.empty())
# Customize pre-tokenization and decoding
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=True)
tokenizer.normalizer = normalizers.ByteLevel(add_prefix_space=True)
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel()
tokenizer.decoder = decoders.ByteLevel()
# And then train