SynCodonLM / tokenizer.json
jheuschkel's picture
Upload 9 files
3385332 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[PAD]",
"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": "[UNK]",
"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
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 500
}
},
{
"Sequence": {
"id": "A",
"type_id": 500
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 500
}
}
],
"pair": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 500
}
},
{
"Sequence": {
"id": "A",
"type_id": 500
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 500
}
},
{
"Sequence": {
"id": "B",
"type_id": 500
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 500
}
}
],
"special_tokens": {
"[CLS]": {
"id": "[CLS]",
"ids": [1],
"tokens": ["[CLS]"]
},
"[SEP]": {
"id": "[SEP]",
"ids": [2],
"tokens": ["[SEP]"]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[PAD]": 0,
"[CLS]": 1,
"[SEP]": 2,
"[UNK]": 3,
"[MASK]": 4,
"GCT": 5,
"GCC": 6,
"GCA": 7,
"GCG": 8,
"TGT": 9,
"TGC": 10,
"GAT": 11,
"GAC": 12,
"GAA": 13,
"GAG": 14,
"TTT": 15,
"TTC": 16,
"GGT": 17,
"GGC": 18,
"GGA": 19,
"GGG": 20,
"CAT": 21,
"CAC": 22,
"ATT": 23,
"ATC": 24,
"ATA": 25,
"AAA": 26,
"AAG": 27,
"TTA": 28,
"TTG": 29,
"CTT": 30,
"CTC": 31,
"CTA": 32,
"CTG": 33,
"ATG": 34,
"AAT": 35,
"AAC": 36,
"CCT": 37,
"CCC": 38,
"CCA": 39,
"CCG": 40,
"CAA": 41,
"CAG": 42,
"CGT": 43,
"CGC": 44,
"CGA": 45,
"CGG": 46,
"AGA": 47,
"AGG": 48,
"TCT": 49,
"TCC": 50,
"TCA": 51,
"TCG": 52,
"AGT": 53,
"AGC": 54,
"ACT": 55,
"ACC": 56,
"ACA": 57,
"ACG": 58,
"GTT": 59,
"GTC": 60,
"GTA": 61,
"GTG": 62,
"TGG": 63,
"TAT": 64,
"TAC": 65,
"TAA": 66,
"TAG": 67,
"TGA": 68
},
"unk_token": "[UNK]"
}
}