fix: use is_fast assertion
This commit is contained in:
parent
c7a6c32882
commit
ef5dd3603e
1 changed files with 1 additions and 1 deletions
|
@ -271,7 +271,7 @@ class Model(ABC):
|
||||||
|
|
||||||
chktxt = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶\u200d🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天~ ------======= нещо на Български \'\'\'\'\'\'```````""""......!!!!!!?????? I\'ve been \'told he\'s there, \'RE you sure? \'M not sure I\'ll make it, \'D you like some tea? We\'Ve a\'lL'
|
chktxt = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶\u200d🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天~ ------======= нещо на Български \'\'\'\'\'\'```````""""......!!!!!!?????? I\'ve been \'told he\'s there, \'RE you sure? \'M not sure I\'ll make it, \'D you like some tea? We\'Ve a\'lL'
|
||||||
|
|
||||||
if hasattr(tokenizer, 'backend_tokenizer'):
|
if tokenizer.is_fast:
|
||||||
chktok = tokenizer.backend_tokenizer.pre_tokenizer.pre_tokenize_str(tokenizer.backend_tokenizer.normalizer.normalize_str(chktxt))
|
chktok = tokenizer.backend_tokenizer.pre_tokenizer.pre_tokenize_str(tokenizer.backend_tokenizer.normalizer.normalize_str(chktxt))
|
||||||
chkhsh = sha256(str(chktok).encode()).hexdigest()
|
chkhsh = sha256(str(chktok).encode()).hexdigest()
|
||||||
else:
|
else:
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue