testocr / tokenizer.json
LazerLambda's picture
Rename MLW_Tokenizer.json to tokenizer.json
a004414
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[BOS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[EOS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": null,
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[EOS]",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"[EOS]": {
"id": "[EOS]",
"ids": [
2
],
"tokens": [
"[EOS]"
]
}
}
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "[UNK]",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"vocab": {
"[BOS]": 0,
"[UNK]": 1,
"[EOS]": 2,
" ": 3,
"#": 4,
"*": 5,
"-": 6,
".": 7,
">": 8,
"A": 9,
"B": 10,
"C": 11,
"E": 12,
"L": 13,
"M": 14,
"N": 15,
"O": 16,
"P": 17,
"Q": 18,
"R": 19,
"S": 20,
"T": 21,
"U": 22,
"V": 23,
"W": 24,
"Z": 25,
"`": 26,
"a": 27,
"b": 28,
"c": 29,
"d": 30,
"e": 31,
"f": 32,
"g": 33,
"h": 34,
"i": 35,
"j": 36,
"k": 37,
"l": 38,
"m": 39,
"n": 40,
"o": 41,
"p": 42,
"q": 43,
"r": 44,
"s": 45,
"t": 46,
"u": 47,
"v": 48,
"w": 49,
"x": 50,
"y": 51,
"z": 52,
"|": 53,
"us": 54,
"ti": 55,
"ri": 56,
"um": 57,
"co": 58,
"ra": 59,
"li": 60
},
"merges": [
"u s",
"t i",
"r i",
"u m",
"c o",
"r a",
"l i"
]
}
}