tokenizer-dna-clm / tokenizer_config.json
gonzalobenegas's picture
Upload tokenizer
4fe2b29 verified
raw
history blame
586 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"padding_side": "left",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}