gguf-py : add constants and method related to <|eom_id|> token

This commit is contained in:
Stanisław Szymczyk 2024-08-04 20:22:48 +02:00
parent cc50e78fbe
commit f10b0e2c39
2 changed files with 5 additions and 0 deletions

View file

@ -161,6 +161,7 @@ class Keys:
SUFFIX_ID = "tokenizer.ggml.suffix_token_id"
MIDDLE_ID = "tokenizer.ggml.middle_token_id"
EOT_ID = "tokenizer.ggml.eot_token_id"
EOM_ID = "tokenizer.ggml.eom_token_id"
class Adapter:
TYPE = "adapter.type"
@ -1327,3 +1328,4 @@ KEY_TOKENIZER_PRIFIX_ID = Keys.Tokenizer.PREFIX_ID
KEY_TOKENIZER_SUFFIX_ID = Keys.Tokenizer.SUFFIX_ID
KEY_TOKENIZER_MIDDLE_ID = Keys.Tokenizer.MIDDLE_ID
KEY_TOKENIZER_EOT_ID = Keys.Tokenizer.EOT_ID
KEY_TOKENIZER_EOM_ID = Keys.Tokenizer.EOM_ID

View file

@ -826,6 +826,9 @@ class GGUFWriter:
def add_eot_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.EOT_ID, id)
def add_eom_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.EOM_ID, id)
def _pack(self, fmt: str, value: Any, skip_pack_prefix: bool = False) -> bytes:
pack_prefix = ''
if not skip_pack_prefix: