Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +86 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"id2label": {
|
| 7 |
+
"0": "O",
|
| 8 |
+
"1": "B-Title",
|
| 9 |
+
"10": "B-Algorithm",
|
| 10 |
+
"11": "B-Figure",
|
| 11 |
+
"12": "B-Table",
|
| 12 |
+
"13": "B-Caption",
|
| 13 |
+
"14": "B-Header",
|
| 14 |
+
"15": "B-Footer",
|
| 15 |
+
"16": "B-Footnote",
|
| 16 |
+
"17": "I-Title",
|
| 17 |
+
"18": "I-Author",
|
| 18 |
+
"19": "I-Abstract",
|
| 19 |
+
"2": "B-Author",
|
| 20 |
+
"20": "I-Keywords",
|
| 21 |
+
"21": "I-Section",
|
| 22 |
+
"22": "I-Paragraph",
|
| 23 |
+
"23": "I-List",
|
| 24 |
+
"24": "I-Bibliography",
|
| 25 |
+
"25": "I-Equation",
|
| 26 |
+
"26": "I-Algorithm",
|
| 27 |
+
"27": "I-Figure",
|
| 28 |
+
"28": "I-Table",
|
| 29 |
+
"29": "I-Caption",
|
| 30 |
+
"3": "B-Abstract",
|
| 31 |
+
"30": "I-Header",
|
| 32 |
+
"31": "I-Footer",
|
| 33 |
+
"32": "I-Footnote",
|
| 34 |
+
"4": "B-Keywords",
|
| 35 |
+
"5": "B-Section",
|
| 36 |
+
"6": "B-Paragraph",
|
| 37 |
+
"7": "B-List",
|
| 38 |
+
"8": "B-Bibliography",
|
| 39 |
+
"9": "B-Equation"
|
| 40 |
+
},
|
| 41 |
+
"label2id": {
|
| 42 |
+
"B-Abstract": 3,
|
| 43 |
+
"B-Algorithm": 10,
|
| 44 |
+
"B-Author": 2,
|
| 45 |
+
"B-Bibliography": 8,
|
| 46 |
+
"B-Caption": 13,
|
| 47 |
+
"B-Equation": 9,
|
| 48 |
+
"B-Figure": 11,
|
| 49 |
+
"B-Footer": 15,
|
| 50 |
+
"B-Footnote": 16,
|
| 51 |
+
"B-Header": 14,
|
| 52 |
+
"B-Keywords": 4,
|
| 53 |
+
"B-List": 7,
|
| 54 |
+
"B-Paragraph": 6,
|
| 55 |
+
"B-Section": 5,
|
| 56 |
+
"B-Table": 12,
|
| 57 |
+
"B-Title": 1,
|
| 58 |
+
"I-Abstract": 19,
|
| 59 |
+
"I-Algorithm": 26,
|
| 60 |
+
"I-Author": 18,
|
| 61 |
+
"I-Bibliography": 24,
|
| 62 |
+
"I-Caption": 29,
|
| 63 |
+
"I-Equation": 25,
|
| 64 |
+
"I-Figure": 27,
|
| 65 |
+
"I-Footer": 31,
|
| 66 |
+
"I-Footnote": 32,
|
| 67 |
+
"I-Header": 30,
|
| 68 |
+
"I-Keywords": 20,
|
| 69 |
+
"I-List": 23,
|
| 70 |
+
"I-Paragraph": 22,
|
| 71 |
+
"I-Section": 21,
|
| 72 |
+
"I-Table": 28,
|
| 73 |
+
"I-Title": 17,
|
| 74 |
+
"O": 0
|
| 75 |
+
},
|
| 76 |
+
"mask_token": "[MASK]",
|
| 77 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 78 |
+
"never_split": null,
|
| 79 |
+
"num_labels": 33,
|
| 80 |
+
"pad_token": "[PAD]",
|
| 81 |
+
"sep_token": "[SEP]",
|
| 82 |
+
"strip_accents": null,
|
| 83 |
+
"tokenize_chinese_chars": true,
|
| 84 |
+
"tokenizer_class": "BertTokenizer",
|
| 85 |
+
"unk_token": "[UNK]"
|
| 86 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|