{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 3584,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": {
"Fixed": 3584
},
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 1,
"pad_type_id": 0,
"pad_token": "<pad>"
},
"added_tokens": [
{
"id": 0,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<pad>",
"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": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "[START_REF]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 5,
"content": "[END_REF]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 6,
"content": "[IMAGE]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 7,
"content": "<fragments>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 8,
"content": "</fragments>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 9,
"content": "<work>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 10,
"content": "</work>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 11,
"content": "[START_SUP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 12,
"content": "[END_SUP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 13,
"content": "[START_SUB]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 14,
"content": "[END_SUB]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 15,
"content": "[START_DNA]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 16,
"content": "[END_DNA]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 17,
"content": "[START_AMINO]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 18,
"content": "[END_AMINO]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 19,
"content": "[START_SMILES]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 20,
"content": "[END_SMILES]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 21,
"content": "[START_I_SMILES]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 22,
"content": "[END_I_SMILES]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "NFKC"
},
"pre_tokenizer": {
"type": "Sequence",
"pretokenizers": [
{
"type": "Split",
"pattern": {
"String": "SPL1T-TH1S-Pl3A5E"
},
"behavior": "Removed",
"invert": false
},
{
"type": "Digits",
"individual_digits": true
},
{
"type": "Split",
"pattern": {
"Regex": "[\\(\\)\\[\\]\\{\\}]|([!\"\\#\\$%\\&'\\*\\+,\\-\\./:;<=>\\?\\\\\\^_`\\|\\~])\\1*"
},
"behavior": "Isolated",
"invert": false
},
{
"type": "Split",
"pattern": {
"String": "\n"
},
"behavior": "Isolated",
"invert": false
},
{
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true,
"use_regex": true
}
]
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"</s>": {
"id": "</s>",
"ids": [
2
],
"tokens": [
"</s>"
]
},
"<s>": {
"id": "<s>",
"ids": [
0
],
"tokens": [
"<s>"
]
}
}
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"vocab": {
"<s>": 0,
"<pad>": 1,
"</s>": 2,
"<unk>": 3,
"[START_REF]": 4,
"[END_REF]": 5,
"[IMAGE]": 6,
"<fragments>": 7,
"</fragments>": 8,
"<work>": 9,
"</work>": 10,
"[START_SUP]": 11,
"[END_SUP]": 12,
"[START_SUB]": 13,
"[END_SUB]": 14,
"[START_DNA]": 15,
"[END_DNA]": 16,
"[START_AMINO]": 17,
"[END_AMINO]": 18,
"[START_SMILES]": 19,
"[END_SMILES]": 20,
"[START_I_SMILES]": 21,
"[END_I_SMILES]": 22,
"!": 23,
"\"": 24,
"#": 25,
"$": 26,
"%": 27,
"&": 28,
"'": 29,
"(": 30,
")": 31,
"*": 32,
"+": 33,
",": 34,
"-": 35,
".": 36,
"/": 37,
"0": 38,
"1": 39,
"2": 40,
"3": 41,
"4": 42,
"5": 43,
"6": 44,
"7": 45,
"8": 46,
"9": 47,
":": 48,
";": 49,
"<": 50,
"=": 51,
">": 52,
"?": 53,
"@": 54,
"A": 55,
"B": 56,
"C": 57,
"D": 58,
"E": 59,
"F": 60,
"G": 61,
"H": 62,
"I": 63,
"J": 64,
"K": 65,
"L": 66,
"M": 67,
"N": 68,
"O": 69,
"P": 70,
"Q": 71,
"R": 72,
"S": 73,
"T": 74,
"U": 75,
"V": 76,
"W": 77,
"X": 78,
"Y": 7