BERT-ceb-cased / tokenizer_config.json
GuyCalledMav's picture
Upload 12 files
9c4c6ae
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_basic_tokenize": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"name_or_path": "BERT-ceb",
"never_split": null,
"pad_token": {
"__type": "AddedToken",
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"__type": "AddedToken",
"content": "[SEP]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "RobertaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}