vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

XgenVocab fix from @smdesai

Browse source
This commit is contained in:
Aman Karmani 2023-07-10 11:06:05 -07:00
parent 58d663d327
commit 45e5df66da
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
convert.py
View file

@ -217,13 +217,13 @@ class XgenVocab:
def all_tokens(self) -> Iterable[Tuple[bytes, float]]: def all_tokens(self) -> Iterable[Tuple[bytes, float]]:
for index in range(0, self.vocab_size_base): for index in range(0, self.vocab_size_base):
token = self.xt._convert_id_to_token(index) token = self.xt.encoder.decode_single_token_bytes(index)
yield (token, float(index)) yield (token, float(index))
for index in range(self.vocab_size_base, self.vocab_size): for index in range(self.vocab_size_base, self.vocab_size):
yield (b'', float(index)) yield (b'', float(index))
def __repr__(self) -> str: def __repr__(self) -> str:
return f"<XgenVocab with {self.vocab_size_base} base tokens and {len(self.added_tokens_list)} added tokens>" return f"<XgenVocab with {self.vocab_size_base} base tokens and {self.vocab_size-self.vocab_size_base} extra tokens>"
class SentencePieceVocab: class SentencePieceVocab: