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

[docstring] Fix docstring for CodeLlamaTokenizer (#26709)

Browse Source 
* update check_docstrings

* update docstring
This commit is contained in:
Bojun-Feng
2023-10-11 11:01:22 -05:00
committed by GitHub
parent aaccf1844e
commit 797a1babf2
2 changed files with 16 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/transformers/models/code_llama/tokenization_code_llama.py
View File

@@ -68,6 +68,11 @@ class CodeLlamaTokenizer(PreTrainedTokenizer):
Args:
vocab_file (`str`):
Path to the vocabulary file.
unk_token (`str`, *optional*, defaults to `"<unk>"`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
bos_token (`str`, *optional*, defaults to `"<s>"`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
eos_token (`str`, *optional*, defaults to `"</s>"`):
The end of sequence token.
@@ -78,23 +83,18 @@ class CodeLlamaTokenizer(PreTrainedTokenizer):
</Tip>
unk_token (`str`, *optional*, defaults to `"<unk>"`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
prefix_token (`str`, *optional*, defaults to `"▁<PRE>"`):
Prefix token used for infilling.
suffix_token (`str`, *optional*, defaults to `"▁<SUF>"`):
Suffix token used for infilling.
middle_token (`str`, *optional*, defaults to `"▁<MID>"`):
Middle token used for infilling.
suffix_token (`str`, *optional*, defaults to `"▁<SUF>"`):
Suffix token used for infilling.
eot_token (`str`, *optional*, defaults to `"▁<EOT>"`):
End of text token used for infilling.
fill_token (`str`, *optional*, defaults to `"<FILL_ME>"`):
The token used to split the input between the prefix and suffix.
suffix_first (`bool`, *optional*, default to `False`):
suffix_first (`bool`, *optional*, defaults to `False`):
Whether the input prompt and suffix should be formatted with the suffix first.
additional_special_tokens (`List[str]`, *optional*):
Additional special tokens used by the tokenizer.
sp_model_kwargs (`dict`, *optional*):
Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
@@ -110,6 +110,14 @@ class CodeLlamaTokenizer(PreTrainedTokenizer):
- `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
BPE-dropout.
add_bos_token (`bool`, *optional*, defaults to `True`):
Whether to add a beginning of sequence token at the start of sequences.
add_eos_token (`bool`, *optional*, defaults to `False`):
Whether to add an end of sequence token at the end of sequences.
clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
Whether or not to clean up the tokenization spaces.
additional_special_tokens (`List[str]`, *optional*):
Additional special tokens used by the tokenizer.
use_default_system_prompt (`bool`, *optional*, defaults to `False`):
Whether or not the default system prompt for Llama should be used.
"""

1
utils/check_docstrings.py
View File

@@ -132,7 +132,6 @@ OBJECTS_TO_IGNORE = [
"CodeGenConfig",
"CodeGenTokenizer",
"CodeGenTokenizerFast",
"CodeLlamaTokenizer",
"CodeLlamaTokenizerFast",
"ConditionalDetrConfig",
"ConditionalDetrImageProcessor",