utrlm-mrl / tokenizer_config.json
ZhiyuanChen's picture
Update tokenizer_config.json
2ec72e6 verified
raw
history blame
1.45 kB
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<null>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<null>"
],
"bos_token": "<cls>",
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"codon": false,
"eos_token": "<eos>",
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"nmers": 1,
"pad_token": "<pad>",
"replace_T_with_U": true,
"sep_token": "<eos>",
"tokenizer_class": "RnaTokenizer",
"unk_token": "<unk>"
}