djsull commited on
Commit
804a49a
1 Parent(s): 1266a06

add tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "bos_token": "[CLS]", "eos_token": "[SEP]", "model_max_length": 512, "special_tokens_map_file": "/home/jhgan/.cache/huggingface/transformers/9d0c87e44b00acfbfbae931b2e4068eb6311a0c3e71e23e5400bdf57cab4bfbf.70c17d6e4d492c8f24f5bb97ab56c7f272e947112c6faf9dd846da42ba13eb23", "name_or_path": "jhgan/ko-sroberta-multitask", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff