dsba-lab commited on
Commit
a7f65cc
1 Parent(s): 9b1176b

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[EMPTY]": 32000}
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[EMPTY]"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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]", "empty_token": "[EMPTY]", "tokenize_chinese_chars": true, "strip_accents": null, "cell_trim_length": -1, "max_column_id": null, "max_row_id": null, "strip_column_names": false, "update_answer_coordinates": false, "min_question_length": null, "max_question_length": null, "model_max_length": 512, "additional_special_tokens": ["[EMPTY]"], "special_tokens_map_file": "/root/.cache/huggingface/transformers/aeaaa3afd086a040be912f92ffe7b5f85008b744624f4517c4216bcc32b51cf0.054ece8d16bd524c8a00f0e8a976c00d5de22a755ffb79e353ee2954d9289e26", "tokenizer_file": "/root/.cache/huggingface/transformers/310a974e892b181d75eed58b545cc0592d066ae4ef35cc760ea92e9b0bf65b3b.74f7933572f937b11a02b2cfb4e88a024059be36c84f53241b85b1fec49e21f7", "name_or_path": "klue/bert-base", "tokenizer_class": "TapasTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff