BulkRNABert / tokenizer_config.json
mgelard's picture
Upload tokenizer
f959c61 verified
raw
history blame
1.43 kB
{
"added_tokens_decoder": {
"64": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"66": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"67": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"68": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"69": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"tokenizer.BinnedOmicTokenizer",
null
]
},
"bos_token": "<bos>",
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"eos_token": "<eos>",
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"tokenizer_class": "BinnedOmicTokenizer",
"unk_token": "<unk>"
}