Commit
โข
fa9ef2c
1
Parent(s):
3539bb2
Upload 2 files
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -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_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "max_len": 512, "do_basic_tokenize": true, "never_split": ["+ู", "+ูู
ุง", "ู+", "+ูุง", "+ูู", "ู+", "+ูู", "+ุงู", "+ูู
", "+ุฉ", "[ุจุฑูุฏ]", "ูู+", "+ู", "+ุช", "+ู", "ุณ+", "ู+", "[ู
ุณุชุฎุฏู
]", "+ูู
", "+ุง", "ุจ+", "ู+", "+ูุง", "+ูุง", "+ูู", "+ูู
ุง", "ุงู+", "+ู", "+ูู", "+ุงุช", "[ุฑุงุจุท]"], "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-large-arabertv2"}
|