rembert-finetuned-ner / tokenizer_config.json
malduwais's picture
Training in progress, step 500
17f6e20
raw
history blame
1.23 kB
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"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
},
"312": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"313": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"314": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"keep_accents": true,
"mask_token": "[MASK]",
"model_max_length": 256,
"pad_token": "[PAD]",
"remove_space": true,
"sep_token": "[SEP]",
"tokenizer_class": "RemBertTokenizer",
"unk_token": "[UNK]"
}