noirci / tokenizer_config.json
5000.dev
Noirci v14-base : detection de donnees personnelles en francais
0dd9c73
Raw
History Blame Contribute Delete
430 Bytes
{
"add_prefix_space": true,
"backend": "tokenizers",
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"extra_special_tokens": [
"<s>NOTUSED",
"</s>NOTUSED",
"<unk>NOTUSED"
],
"is_local": false,
"local_files_only": false,
"mask_token": "<mask>",
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "CamembertTokenizer",
"unk_token": "<unk>",
"model_max_length": 512
}