mii/tokenizers
1
0
Fork 0
mirror of https://github.com/mii443/tokenizers.git synced 2025-12-06 20:58:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow initial_alphabet on UnigramTrainer

Browse Source
This commit is contained in:
Anthony MOI
2020-10-22 14:32:40 -04:00
committed by Anthony MOI
parent f7c61c267a
commit 1a6f4b5204
3 changed files with 44 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
bindings/python/py_src/tokenizers/trainers/__init__.pyi
View File

@@ -46,7 +46,7 @@ class BpeTrainer(Trainer):
initial_alphabet: List[str]:
A list of characters to include in the initial alphabet, even
if not seen in the training dataset.
If the strings contains more than one character, only the first one
If the strings contain more than one character, only the first one
is kept.
continuing_subword_prefix: Optional[str]:
@@ -98,7 +98,7 @@ class WordPieceTrainer(Trainer):
initial_alphabet: List[str]:
A list of characters to include in the initial alphabet, even
if not seen in the training dataset.
If the strings contains more than one character, only the first one
If the strings contain more than one character, only the first one
is kept.
continuing_subword_prefix: Optional[str]:
@@ -136,6 +136,12 @@ class UnigramTrainer(Trainer):
special_tokens: List[Union[str, AddedToken]]:
A list of special tokens the model should know of.
initial_alphabet: List[str]:
A list of characters to include in the initial alphabet, even
if not seen in the training dataset.
If the strings contain more than one character, only the first one
is kept.
Returns:
Trainer
"""

11
bindings/python/src/trainers.rs
View File

@@ -193,6 +193,17 @@ impl PyUnigramTrainer {
"unk_token" => builder.unk_token(val.extract()?),
"max_piece_length" => builder.max_piece_length(val.extract()?),
"seed_size" => builder.seed_size(val.extract()?),
"initial_alphabet" => {
let alphabet: Vec<String> = val.extract()?;
builder.initial_alphabet(
alphabet
.into_iter()
.map(|s| s.chars().next())
.filter(|c| c.is_some())
.map(|c| c.unwrap())
.collect(),
)
}
"special_tokens" => builder.special_tokens(
val.cast_as::<PyList>()?
.into_iter()