Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 15, 2024
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f428652
fix(gguf-py): special tokens are no longer skipped when add_<token>_t…
vriesdemichael Feb 14, 2024
3b5dc11
fix(gguf-py): added missing cls and mask token ids to the gguf metadata
vriesdemichael Feb 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions gguf-py/gguf/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,8 @@ class Tokenizer:
UNK_ID = "tokenizer.ggml.unknown_token_id"
SEP_ID = "tokenizer.ggml.seperator_token_id"
PAD_ID = "tokenizer.ggml.padding_token_id"
CLS_ID = "tokenizer.ggml.cls_token_id"
MASK_ID = "tokenizer.ggml.mask_token_id"
ADD_BOS = "tokenizer.ggml.add_bos_token"
ADD_EOS = "tokenizer.ggml.add_eos_token"
ADD_PREFIX = "tokenizer.ggml.add_space_prefix"
Expand Down Expand Up @@ -685,5 +687,7 @@ def get_type(val: Any) -> GGUFValueType:
KEY_TOKENIZER_UNK_ID = Keys.Tokenizer.UNK_ID
KEY_TOKENIZER_SEP_ID = Keys.Tokenizer.SEP_ID
KEY_TOKENIZER_PAD_ID = Keys.Tokenizer.PAD_ID
KEY_TOKENIZER_CLS_ID = Keys.Tokenizer.CLS_ID
KEY_TOKENIZER_MASK_ID = Keys.Tokenizer.MASK_ID
KEY_TOKENIZER_HF_JSON = Keys.Tokenizer.HF_JSON
KEY_TOKENIZER_RWKV = Keys.Tokenizer.RWKV
6 changes: 6 additions & 0 deletions gguf-py/gguf/gguf_writer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -414,6 +414,12 @@ def add_sep_token_id(self, id: int) -> None:
def add_pad_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.PAD_ID, id)

def add_cls_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.CLS_ID, id)

def add_mask_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.MASK_ID, id)

def add_add_bos_token(self, value: bool) -> None:
self.add_bool(Keys.Tokenizer.ADD_BOS, value)

Expand Down
6 changes: 1 addition & 5 deletions gguf-py/gguf/vocab.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ def __init__(
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:
Expand Down Expand Up @@ -152,10 +152,6 @@ def _try_load_from_tokenizer_json(self, path: Path) -> bool:
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
Expand Down