bert-depots / tokenizer.json
lore-seri97's picture
Upload folder using huggingface_hub
98c5095 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,
"on": 8,
"at": 9,
"lift": 10,
"distributor2": 11,
"distributor1": 12,
"distributor0": 13,
"drop": 14,
"depot1": 15,
"depot2": 16,
"depot0": 17,
"crate9": 18,
"crate2": 19,
"crate1": 20,
"crate0": 21,
"crate6": 22,
"crate8": 23,
"crate4": 24,
"crate5": 25,
"load": 26,
"crate3": 27,
"crate7": 28,
"truck1": 29,
"truck2": 30,
"truck0": 31,
"unload": 32,
"hoist1": 33,
"hoist2": 34,
"hoist5": 35,
"hoist3": 36,
"hoist0": 37,
"hoist4": 38,
"drive": 39,
"clear": 40,
"available": 41,
"pallet5": 42,
"pallet2": 43,
"pallet3": 44,
"pallet1": 45,
"pallet4": 46,
"pallet0": 47,
"[a]": 48,
"[sg]": 49,
"[si]": 50
},
"unk_token": "[UNK]"
}
}