Afaf commited on
Commit
31a1307
·
verified ·
1 Parent(s): b14e169

Update utils.py

Browse files
Files changed (1) hide show
  1. utils.py +1 -1
utils.py CHANGED
@@ -18,7 +18,7 @@ def get_tokenizer(id):
18
  def get_tokenization(tokenizer, text):
19
  logging.debug(f"Tokenizing text: {text}")
20
  ids = tokenizer.encode(text).ids
21
- string_tokens = tokenizer.decode(ids)
22
  logging.debug(f"Tokens: {string_tokens}")
23
  return string_tokens
24
 
 
18
  def get_tokenization(tokenizer, text):
19
  logging.debug(f"Tokenizing text: {text}")
20
  ids = tokenizer.encode(text).ids
21
+ string_tokens = [tokenizer.id_to_token(id) for id in ids]
22
  logging.debug(f"Tokens: {string_tokens}")
23
  return string_tokens
24