leeeki commited on
Commit
d2294a9
1 Parent(s): 00312b0

add tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "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": "<s>", "eos_token": "</s>", "model_max_length": 4096, "special_tokens_map_file": "/opt/ml/.cache/huggingface/transformers/9bea998b48658e35dd618115a266f6c173183a9a4261fc6e40730d74c4b67899.e3640e465e51ce85d94923a0b396029ecc2e3e4c7764031eee57ab272637652d", "name_or_path": "monologg/kobigbird-bert-base", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff