mii/tokenizers
1
0
Fork 0
mirror of https://github.com/mii443/tokenizers.git synced 2025-12-06 04:38:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Option to skip special tokens while decoding

Browse Source
This commit is contained in:
Anthony MOI
2019-12-19 20:03:02 -05:00
parent a8d68d516d
commit b7040e0412
3 changed files with 22 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
bindings/python/src/tokenizer.rs
View File

@@ -192,12 +192,16 @@ impl Tokenizer {
.into()
}
fn decode(&self, ids: Vec<u32>) -> PyResult<String> {
ToPyResult(self.tokenizer.decode(ids)).into()
fn decode(&self, ids: Vec<u32>, skip_special_tokens: bool) -> PyResult<String> {
ToPyResult(self.tokenizer.decode(ids, skip_special_tokens)).into()
}
fn decode_batch(&self, sentences: Vec<Vec<u32>>) -> PyResult<Vec<String>> {
ToPyResult(self.tokenizer.decode_batch(sentences)).into()
fn decode_batch(
&self,
sentences: Vec<Vec<u32>>,
skip_special_tokens: bool,
) -> PyResult<Vec<String>> {
ToPyResult(self.tokenizer.decode_batch(sentences, skip_special_tokens)).into()
}
fn token_to_id(&self, token: &str) -> Option<u32> {