File size: 1,491 Bytes
1cc43db |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Strip",
"strip_left": true,
"strip_right": true
},
"pre_tokenizer": {
"type": "WhitespaceSplit"
},
"post_processor": null,
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[UNK]": 0,
"[PAD]": 1,
"[CLS]": 2,
"[SEP]": 3,
"[MASK]": 4,
"6": 5,
"9": 6,
"2": 7,
"5": 8,
"1": 9,
"7": 10,
"4": 11,
"8": 12,
"0": 13,
"3": 14
},
"unk_token": "[UNK]"
}
} |