CNEC_1_1_robeczech-base / tokenizer_config.json
stulcrad's picture
Training in progress, step 1500
7b86e74 verified
raw
history blame
1.25 kB
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"51960": {
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"eos_token": "[SEP]",
"errors": "replace",
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "[UNK]"
}