bert-driverlog / tokenizer.json
lore-seri97's picture
Upload folder using huggingface_hub
a2de511 verified
{
"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": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[PAD]",
"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
},
{
"id": 5,
"content": "[A]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 6,
"content": "[SI]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 7,
"content": "[SG]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Lowercase"
},
"pre_tokenizer": {
"type": "WhitespaceSplit"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 1
}
}
],
"special_tokens": {
"[CLS]": {
"id": "[CLS]",
"ids": [
1
],
"tokens": [
"[CLS]"
]
},
"[SEP]": {
"id": "[SEP]",
"ids": [
2
],
"tokens": [
"[SEP]"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[UNK]": 0,
"[CLS]": 1,
"[SEP]": 2,
"[PAD]": 3,
"[MASK]": 4,
"[A]": 5,
"[SI]": 6,
"[SG]": 7,
"at": 8,
"truck2": 9,
"truck1": 10,
"truck3": 11,
"drive-truck": 12,
"driver1": 13,
"driver2": 14,
"driver3": 15,
"walk": 16,
"s6": 17,
"s8": 18,
"s5": 19,
"s0": 20,
"s4": 21,
"s9": 22,
"s2": 23,
"s7": 24,
"s11": 25,
"s3": 26,
"s10": 27,
"s1": 28,
"load-truck": 29,
"unload-truck": 30,
"package4": 31,
"package6": 32,
"package1": 33,
"package7": 34,
"package2": 35,
"package3": 36,
"package5": 37,
"empty": 38,
"board-truck": 39,
"disembark-truck": 40,
"[a]": 41,
"[sg]": 42,
"[si]": 43,
"p3-7": 44,
"p9-7": 45,
"p6-7": 46,
"p7-1": 47,
"p8-4": 48,
"p4-7": 49,
"p6-4": 50,
"p0-8": 51,
"p2-0": 52,
"p7-10": 53,
"p11-0": 54,
"p11-1": 55,
"p5-0": 56,
"p0-2": 57,
"p6-10": 58,
"p11-10": 59,
"p8-11": 60,
"p2-6": 61,
"p8-3": 62,
"p1-4": 63,
"p1-0": 64,
"p1-2": 65,
"p2-1": 66,
"p6-2": 67,
"p6-8": 68,
"p8-5": 69,
"p11-4": 70,
"p4-6": 71,
"p2-3": 72,
"p6-11": 73,
"p2-5": 74,
"p3-9": 75,
"p4-0": 76,
"p2-7": 77,
"p6-5": 78,
"p10-0": 79,
"p9-4": 80,
"p3-2": 81,
"p7-9": 82,
"p3-1": 83,
"p0-1": 84
},
"unk_token": "[UNK]"
}
}