digit82 commited on
Commit
a9f5849
1 Parent(s): 97f6335

update special tokens

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +1 -1
  2. tokenizer_config.json +1 -1
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<eop>", "<eod>"]}
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": null, "eos_token": null, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<eop>", "<eod>"], "sp_model_kwargs": {}, "tokenizer_class": "KoBERTTokenizer"}
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": null, "sp_model_kwargs": {}, "tokenizer_class": "XLNetTokenizer"}