mike-ravkine commited on
Commit
dd3906f
1 Parent(s): 1073cff

Update boomer_code_tokenizer.py

Browse files

Fix tokenizer for transformers >= 4.34

From https://github.com/InternLM/InternLM/pull/419

Files changed (1) hide show
  1. boomer_code_tokenizer.py +1 -1
boomer_code_tokenizer.py CHANGED
@@ -63,10 +63,10 @@ class BoomerCodeTokenizer(PreTrainedTokenizer):
63
 
64
  def __init__(self, vocab_file, bos_token=None, eos_token='<|endoftext|>', unk_token='<|unk|>', pad_token='<|pad|>', sep_token=None, sp_model_kwargs: Optional[Dict[str, Any]]=None, **kwargs) -> None:
65
  self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
66
- super().__init__(bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, pad_token=pad_token, sep_token=sep_token, sp_model_kwargs=self.sp_model_kwargs, **kwargs)
67
  self.vocab_file = vocab_file
68
  self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
69
  self.sp_model.Load(vocab_file)
 
70
 
71
  print(self.sp_model)
72
 
 
63
 
64
  def __init__(self, vocab_file, bos_token=None, eos_token='<|endoftext|>', unk_token='<|unk|>', pad_token='<|pad|>', sep_token=None, sp_model_kwargs: Optional[Dict[str, Any]]=None, **kwargs) -> None:
65
  self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
 
66
  self.vocab_file = vocab_file
67
  self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
  self.sp_model.Load(vocab_file)
69
+ super().__init__(bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, pad_token=pad_token, sep_token=sep_token, sp_model_kwargs=self.sp_model_kwargs, **kwargs)
70
 
71
  print(self.sp_model)
72