turing-usp commited on
Commit
fa8c62c
1 Parent(s): 8a2e195

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -1
  2. tokenizer_config.json +1 -1
  3. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {}
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"tokenizer_class": "PreTrainedTokenizerFast"}
 
1
+ {"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/leme/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "neuralmind/bert-base-portuguese-cased", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff