SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix outdated tokenizer doc

Browse Source
This commit is contained in:
Julien Chaumond
2019-12-17 20:07:39 -05:00
parent ea636440d1
commit a0d386455b
3 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
templates/adding_a_new_model/tokenization_xxx.py
View File

@@ -85,7 +85,7 @@ class XxxTokenizer(PreTrainedTokenizer):
Args: Args:
vocab_file: Path to a one-wordpiece-per-line vocabulary file vocab_file: Path to a one-wordpiece-per-line vocabulary file
do_lower_case: Whether to lower case the input. Only has an effect when do_wordpiece_only=False do_lower_case: Whether to lower case the input. Only has an effect when do_basic_tokenize=True
""" """
vocab_files_names = VOCAB_FILES_NAMES vocab_files_names = VOCAB_FILES_NAMES

4
transformers/tokenization_bert.py
View File

@@ -113,12 +113,12 @@ class BertTokenizer(PreTrainedTokenizer):
Args: Args:
vocab_file: Path to a one-wordpiece-per-line vocabulary file vocab_file: Path to a one-wordpiece-per-line vocabulary file
do_lower_case: Whether to lower case the input. Only has an effect when do_wordpiece_only=False do_lower_case: Whether to lower case the input. Only has an effect when do_basic_tokenize=True
do_basic_tokenize: Whether to do basic tokenization before wordpiece. do_basic_tokenize: Whether to do basic tokenization before wordpiece.
max_len: An artificial maximum length to truncate tokenized sequences to; Effective maximum length is always the max_len: An artificial maximum length to truncate tokenized sequences to; Effective maximum length is always the
minimum of this value (if specified) and the underlying BERT model's sequence length. minimum of this value (if specified) and the underlying BERT model's sequence length.
never_split: List of tokens which will never be split during tokenization. Only has an effect when never_split: List of tokens which will never be split during tokenization. Only has an effect when
do_wordpiece_only=False do_basic_tokenize=True
""" """
vocab_files_names = VOCAB_FILES_NAMES vocab_files_names = VOCAB_FILES_NAMES

4
transformers/tokenization_distilbert.py
View File

@@ -53,12 +53,12 @@ class DistilBertTokenizer(BertTokenizer):
Args: Args:
vocab_file: Path to a one-wordpiece-per-line vocabulary file vocab_file: Path to a one-wordpiece-per-line vocabulary file
do_lower_case: Whether to lower case the input. Only has an effect when do_wordpiece_only=False do_lower_case: Whether to lower case the input. Only has an effect when do_basic_tokenize=True
do_basic_tokenize: Whether to do basic tokenization before wordpiece. do_basic_tokenize: Whether to do basic tokenization before wordpiece.
max_len: An artificial maximum length to truncate tokenized sequences to; Effective maximum length is always the max_len: An artificial maximum length to truncate tokenized sequences to; Effective maximum length is always the
minimum of this value (if specified) and the underlying BERT model's sequence length. minimum of this value (if specified) and the underlying BERT model's sequence length.
never_split: List of tokens which will never be split during tokenization. Only has an effect when never_split: List of tokens which will never be split during tokenization. Only has an effect when
do_wordpiece_only=False do_basic_tokenize=True
""" """
vocab_files_names = VOCAB_FILES_NAMES vocab_files_names = VOCAB_FILES_NAMES