mii/tokenizers
1
0
Fork 0
mirror of https://github.com/mii443/tokenizers.git synced 2025-12-08 05:38:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Python - Make the trainer optional on Tokenizer.train

Browse Source
This commit is contained in:
Anthony MOI
2020-10-07 21:25:32 -04:00
committed by Anthony MOI
parent c230183cf6
commit 224862fe0c
7 changed files with 15 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
bindings/python/py_src/tokenizers/implementations/bert_wordpiece.py
View File

@@ -115,4 +115,4 @@ class BertWordPieceTokenizer(BaseTokenizer):
)
if isinstance(files, str):
files = [files]
self._tokenizer.train(trainer, files)
self._tokenizer.train(files, trainer=trainer)

2
bindings/python/py_src/tokenizers/implementations/byte_level_bpe.py
View File

@@ -101,4 +101,4 @@ class ByteLevelBPETokenizer(BaseTokenizer):
)
if isinstance(files, str):
files = [files]
self._tokenizer.train(trainer, files)
self._tokenizer.train(files, trainer=trainer)

2
bindings/python/py_src/tokenizers/implementations/char_level_bpe.py
View File

@@ -123,4 +123,4 @@ class CharBPETokenizer(BaseTokenizer):
)
if isinstance(files, str):
files = [files]
self._tokenizer.train(trainer, files)
self._tokenizer.train(files, trainer=trainer)

2
bindings/python/py_src/tokenizers/implementations/sentencepiece_bpe.py
View File

@@ -74,4 +74,4 @@ class SentencePieceBPETokenizer(BaseTokenizer):
)
if isinstance(files, str):
files = [files]
self._tokenizer.train(trainer, files)
self._tokenizer.train(files, trainer=trainer)

2
bindings/python/py_src/tokenizers/implementations/sentencepiece_unigram.py
View File

@@ -75,7 +75,7 @@ class SentencePieceUnigramTokenizer(BaseTokenizer):
if isinstance(files, str):
files = [files]
self._tokenizer.train(trainer, files)
self._tokenizer.train(files, trainer=trainer)
@staticmethod
def from_spm(filename: str):