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

fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false (#5487)

Browse source 
* fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false

* fix(gguf-py): added missing cls and mask token ids to the gguf metadata
This commit is contained in:
Michaël de Vries 2024-02-15 14:14:37 +01:00 • committed by GitHub
parent 0d4177126b
commit 73122473ff
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 11 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
gguf-py/gguf/vocab.py
View file

@ -29,7 +29,7 @@ class SpecialVocab:
if special_token_types is not None:
self.special_token_types = special_token_types
else:
self.special_token_types = ('bos', 'eos', 'unk', 'sep', 'pad')
self.special_token_types = ('bos', 'eos', 'unk', 'sep', 'pad', 'cls', 'mask')
self._load(Path(path))
def __repr__(self) -> str:
@ -152,10 +152,6 @@ class SpecialVocab:
add_entry = tokenizer_config.get(f'add_{typ}_token')
if isinstance(add_entry, bool):
self.add_special_token[typ] = add_entry
if not added_tokens:
# We will need this to get the content for the token, so if it's empty
# may as well just give up.
continue
entry = tokenizer_config.get(f'{typ}_token')
if isinstance(entry, str):
tc_content = entry