Fixed-Vocab-Tokenizer / tokenizer_config.json
mrshlltaylor's picture
Upload tokenizer
c013431 verified
raw
history blame
No virus
297 Bytes
{
"added_tokens_decoder": {},
"clean_up_tokenization_spaces": true,
"cls_token": "0",
"mask_token": "a01",
"max_len": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "a0",
"sep_token": "a",
"tokenizer_class": "FixedVocabTokenizer",
"unk_token": "a00"
}