Z-coref / tokenizer_config.json
psuwannapich's picture
merge from main
438ad43
raw
history blame
554 Bytes
{
"add_prefix_space": true,
"additional_special_tokens": [
"<s>NOTUSED",
"</s>NOTUSED",
"<_>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 510,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "CamembertTokenizer",
"unk_token": "<unk>"
}