autotrain-enhancedauto-72049138835 / tokenizer_config.json
system's picture
system HF staff
Commit From AutoTrain
bb7ccbc
raw
history blame contribute delete
816 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"full_tokenizer_file": null,
"mask_token": "[MASK]",
"max_len": 512,
"model_max_length": 512,
"never_split": [
"+وا",
"س+",
"[مستخدم]",
"+ك",
"+هم",
"+ة",
"+ن",
"لل+",
"[بريد]",
"[رابط]",
"+ه",
"+كن",
"+ا",
"+ات",
"+ي",
"ب+",
"+نا",
"+هن",
"+كم",
"ك+",
"+ين",
"+هما",
"و+",
"+كما",
"+ان",
"+ت",
"+ون",
"ل+",
"+ها",
"ال+",
"ف+"
],
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}