xlmindic-rembert-multiscript / tokenizer_config.json
ibraheemmoosa's picture
Fix tokenizer
cefdda3
{
"bos_token": "<cls>",
"cls_token": "<cls>",
"do_lower_case": true,
"eos_token": "<sep>",
"keep_accents": false,
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": "<pad>",
"remove_space": true,
"sep_token": "<sep>",
"tokenizer_class": "RemBertTokenizer",
"unk_token": "<unk>"
}