Pringled commited on
Commit
7ce022e
1 Parent(s): 75f74bc

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer_config.json +1 -0
  3. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "unk_token": "[UNK]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"added_tokens_decoder": {"0": {"content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "2": {"content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "3": {"content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "4": {"content": "[MASK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}}, "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_lower_case": false, "mask_token": "[MASK]", "model_max_length": 512, "pad_token": "[PAD]", "sep_token": "[SEP]", "strip_accents": null, "tokenize_chinese_chars": true, "tokenizer_class": "BertTokenizer", "unk_token": "[UNK]"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff