cfg4.4-small / tokenizer_config.json
empty-michael's picture
Upload tokenizer
8c3ba5e verified
raw
history blame
937 Bytes
{
"added_tokens_decoder": {
"5": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "0",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "0",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}