TargetAMP-Designer / tokenizer.json
小能豆子
Upload 6 files
2c31f17 verified
Raw
History Blame Contribute Delete
5.97 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"special": true,
"content": "<|pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 1,
"special": true,
"content": "<|bos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 2,
"special": true,
"content": "<|eos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 25,
"special": true,
"content": "<|antifungal|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 26,
"special": true,
"content": "<|antibacterial|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 27,
"special": true,
"content": "<|antibiofilm|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 28,
"special": true,
"content": "<|anti-diabetic|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 29,
"special": true,
"content": "<|anti-MRSA|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 30,
"special": true,
"content": "<|anti-parasite|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 31,
"special": true,
"content": "<|anti-TB|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 32,
"special": true,
"content": "<|anti-toxin|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 33,
"special": true,
"content": "<|anticancer|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 34,
"special": true,
"content": "<|antiHIV|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 35,
"special": true,
"content": "<|antimalarial|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 36,
"special": true,
"content": "<|antioxidant|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 37,
"special": true,
"content": "<|antiviral|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 38,
"special": true,
"content": "<|insecticidal|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 39,
"special": true,
"content": "<|ion_channel|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 40,
"special": true,
"content": "<|protease_inhibitors|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 41,
"special": true,
"content": "<|spermicidal|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 42,
"special": true,
"content": "<|surface_immobilized|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 43,
"special": true,
"content": "<|wound_healing|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"vocab": {
"<|pad|>": 0,
"<|bos|>": 1,
"<|eos|>": 2,
"1": 3,
"2": 4,
"A": 5,
"C": 6,
"D": 7,
"E": 8,
"F": 9,
"G": 10,
"H": 11,
"I": 12,
"K": 13,
"L": 14,
"M": 15,
"N": 16,
"P": 17,
"Q": 18,
"R": 19,
"S": 20,
"T": 21,
"V": 22,
"W": 23,
"Y": 24,
"<|antifungal|>": 25,
"<|antibacterial|>": 26,
"<|antibiofilm|>": 27,
"<|anti-diabetic|>": 28,
"<|anti-MRSA|>": 29,
"<|anti-parasite|>": 30,
"<|anti-TB|>": 31,
"<|anti-toxin|>": 32,
"<|anticancer|>": 33,
"<|antiHIV|>": 34,
"<|antimalarial|>": 35,
"<|antioxidant|>": 36,
"<|antiviral|>": 37,
"<|insecticidal|>": 38,
"<|ion_channel|>": 39,
"<|protease_inhibitors|>": 40,
"<|spermicidal|>": 41,
"<|surface_immobilized|>": 42,
"<|wound_healing|>": 43
},
"merges": []
}
}