plant-dnagemma-singlebase / tokenizer_config.json
longchen0421's picture
Upload 8 files
1c5ab4b verified
raw
history blame contribute delete
927 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"eos_token": null,
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"tokenizer_class": "EsmTokenizer",
"unk_token": "<unk>"
}