{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": true
},
{
"id": 1,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": true
},
{
"id": 2,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Prepend",
"prepend": "▁"
},
{
"type": "Replace",
"pattern": {
"String": " "
},
"content": "▁"
}
]
},
"pre_tokenizer": null,
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<s>",
"type_id": 1
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"<s>": {
"id": "<s>",
"ids": [
1
],
"tokens": [
"<s>"
]
}
}
},
"decoder": {
"type": "Sequence",
"decoders": [
{
"type": "Replace",
"pattern": {
"String": "▁"
},
"content": " "
},
{
"type": "ByteFallback"
},
{
"type": "Fuse"
},
{
"type": "Strip",
"content": " ",
"start": 1,
"stop": 0
}
]
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "<unk>",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": true,
"byte_fallback": true,
"vocab": {
"<unk>": 0,
"<s>": 1,
"</s>": 2,
"A": 3,
"B": 4,
"C": 5,
"D": 6,
"E": 7,
"F": 8,
"G": 9,
"H": 10,
"I": 11,
"J": 12,
"K": 13,
"L": 14,
"M": 15,
"N": 16,
"O": 17,
"P": 18,
"Q": 19,
"R": 20,
"S": 21,
"T": 22,
"U": 23,
"V": 24,
"W": 25,
"X": 26,
"Y": 27,
"Z": 28
},
"merges": []
}
}