delbert-setdb1 / tokenizer_config.json
armansa1's picture
Upload DELBERT classification model
b546f4d verified
{
"added_tokens_decoder": {
"14511": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14512": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14513": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14514": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14515": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": false,
"cls_token": "<cls>",
"extra_special_tokens": {},
"fingerprint_nbits": 2048,
"fingerprint_types": [
"ECFP4",
"FCFP6",
"ATOMPAIR",
"TOPTOR"
],
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "<sep>",
"token_format": "binary",
"tokenizer_class": "MolecularTokenizer",
"unk_token": "<unk>"
}