Transformers
cz_ec_bpe500 / tokenizer_config.json
iszoke's picture
Upload tokenizer
4d9566c verified
{
"added_tokens_decoder": {
"0": {
"content": "([bos])",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "([eos])",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "([unk])",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "([pad])",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "([mask])",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"497": {
"content": "(LNG)",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"498": {
"content": "(UNK)",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"499": {
"content": "(SPN)",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "([bos])",
"clean_up_tokenization_spaces": true,
"eos_token": "([eos])",
"mask_token": "([mask])",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "([pad])",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "([unk])"
}