feat(frontend): early-fail tokenization guard for user requests (#31366)
Signed-off-by: limingliang <limingliang@stepfun.com> Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by: limingliang <limingliang@stepfun.com> Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
co-authored by
limingliang
DarkLight1337
parent
20d7454c9b
commit
a32cb49b60
@@ -28,6 +28,8 @@ def get_cached_tokenizer(tokenizer: HfTokenizer) -> HfTokenizer:
|
||||
tokenizer_len = len(tokenizer)
|
||||
|
||||
max_token_id = max(tokenizer_vocab.values())
|
||||
max_chars_per_token = max(len(tok) for tok in tokenizer_vocab)
|
||||
|
||||
# Some tokenizers (e.g., QwenTokenizer) have special tokens that
|
||||
# are added and included in the implementation of the vocab_size
|
||||
# property, but not in get_vocab(); if there is an implementation
|
||||
@@ -49,6 +51,10 @@ def get_cached_tokenizer(tokenizer: HfTokenizer) -> HfTokenizer:
|
||||
def max_token_id(self) -> int:
|
||||
return max_token_id
|
||||
|
||||
@property
|
||||
def max_chars_per_token(self) -> int:
|
||||
return max_chars_per_token
|
||||
|
||||
def get_vocab(self) -> dict[str, int]:
|
||||
return tokenizer_vocab
|
||||
|
||||
|
||||
Reference in New Issue
Block a user