bert-base-arabert-BioNER-EN-AR / tokenizer_config.json
StivenLancheros's picture
Training in progress, epoch 1
6ab7e00
raw
history blame
811 Bytes
{
"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": [
"+ูˆุง",
"ุณ+",
"[ู…ุณุชุฎุฏู…]",
"+ูƒ",
"+ู‡ู…",
"+ุฉ",
"+ู†",
"ู„ู„+",
"[ุจุฑูŠุฏ]",
"[ุฑุงุจุท]",
"+ู‡",
"+ูƒู†",
"+ุง",
"+ุงุช",
"+ูŠ",
"ุจ+",
"+ู†ุง",
"+ู‡ู†",
"+ูƒู…",
"ูƒ+",
"+ูŠู†",
"+ู‡ู…ุง",
"ูˆ+",
"+ูƒู…ุง",
"+ุงู†",
"+ุช",
"+ูˆู†",
"ู„+",
"+ู‡ุง",
"ุงู„+",
"ู+"
],
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}