(
self, text: bytes, add_bos: bool = True, special: bool = True
)
| 79 | self.hf_tokenizer = hf_tokenizer |
| 80 | |
| 81 | def tokenize( |
| 82 | self, text: bytes, add_bos: bool = True, special: bool = True |
| 83 | ) -> List[int]: |
| 84 | return self.hf_tokenizer.encode( |
| 85 | text.decode("utf-8", errors="ignore"), add_special_tokens=special |
| 86 | ) |
| 87 | |
| 88 | def detokenize( |
| 89 | self, |