add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "do_basic_tokenize": true, "never_split": ["+ูุง", "ุณ+", "[ู
ุณุชุฎุฏู
]", "+ู", "+ูู
", "+ุฉ", "+ู", "ูู+", "[ุจุฑูุฏ]", "[ุฑุงุจุท]", "+ู", "+ูู", "+ุง", "+ุงุช", "+ู", "ุจ+", "+ูุง", "+ูู", "+ูู
", "ู+", "+ูู", "+ูู
ุง", "ู+", "+ูู
ุง", "+ุงู", "+ุช", "+ูู", "ู+", "+ูุง", "ุงู+", "ู+"], "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "aubmindlab/bert-base-arabert", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|