CST / tokenizer.json
wangyk22's picture
Upload 2 files
7a212f5 verified
raw
history blame
3.41 kB
{
"version": "1.0",
"truncation": null,
"padding": {
"strategy": "BatchLongest",
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "<pad>"
},
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"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": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "NFD"
},
"pre_tokenizer": {
"type": "Sequence",
"pretokenizers": [
{
"type": "Whitespace"
},
{
"type": "Split",
"pattern": {
"Regex": "[\\[\\]\\(\\)\\.]"
},
"behavior": "MergedWithPrevious",
"invert": false
},
{
"type": "Split",
"pattern": {
"Regex": "Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|H"
},
"behavior": "Isolated",
"invert": false
},
{
"type": "Split",
"pattern": {
"Regex": "=|#|-|\\+|\\\\|\\/|:|~|@|\\?|>|\\*|\\$|\\%[0-9]{2}|[0-9]"
},
"behavior": "MergedWithPrevious",
"invert": false
}
]
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 1
}
}
],
"special_tokens": {
"</s>": {
"id": "</s>",
"ids": [
3
],
"tokens": [
"</s>"
]
},
"<s>": {
"id": "<s>",
"ids": [
2
],
"tokens": [
"<s>"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"<pad>": 0,
"<unk>": 1,
"<s>": 2,
"</s>": 3,
"C": 4,
"(": 5,
")": 6,
"H": 7,
"O": 8,
"1": 9,
"c": 10,
"N": 11,
"@": 12,
"=": 13,
"[": 14,
"]": 15,
"n": 16,
"2": 17,
"3": 18,
"S": 19,
"F": 20,
"o": 21,
"#": 22,
"s": 23,
"*": 24,
"Cl": 25,
"-": 26,
"/": 27,
"4": 28,
"5": 29,
"Br": 30,
"\\": 31,
"6": 32,
"+": 33,
"8": 34,
"I": 35,
"9": 36,
"0": 37,
"7": 38,
"B": 39,
"i": 40,
"P": 41
},
"unk_token": "<unk>"
}
}