Commit
โข
d3e355c
1
Parent(s):
f0c9084
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +48 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"max_len": 512,
|
8 |
+
"model_max_length": 512,
|
9 |
+
"never_split": [
|
10 |
+
"+ู",
|
11 |
+
"+ูู
ุง",
|
12 |
+
"ู+",
|
13 |
+
"+ูุง",
|
14 |
+
"+ูู",
|
15 |
+
"ู+",
|
16 |
+
"+ูู",
|
17 |
+
"+ุงู",
|
18 |
+
"+ูู
",
|
19 |
+
"+ุฉ",
|
20 |
+
"[ุจุฑูุฏ]",
|
21 |
+
"ูู+",
|
22 |
+
"+ู",
|
23 |
+
"+ุช",
|
24 |
+
"+ู",
|
25 |
+
"ุณ+",
|
26 |
+
"ู+",
|
27 |
+
"[ู
ุณุชุฎุฏู
]",
|
28 |
+
"+ูู
",
|
29 |
+
"+ุง",
|
30 |
+
"ุจ+",
|
31 |
+
"ู+",
|
32 |
+
"+ูุง",
|
33 |
+
"+ูุง",
|
34 |
+
"+ูู",
|
35 |
+
"+ูู
ุง",
|
36 |
+
"ุงู+",
|
37 |
+
"+ู",
|
38 |
+
"+ูู",
|
39 |
+
"+ุงุช",
|
40 |
+
"[ุฑุงุจุท]"
|
41 |
+
],
|
42 |
+
"pad_token": "[PAD]",
|
43 |
+
"sep_token": "[SEP]",
|
44 |
+
"strip_accents": null,
|
45 |
+
"tokenize_chinese_chars": true,
|
46 |
+
"tokenizer_class": "BertTokenizer",
|
47 |
+
"unk_token": "[UNK]"
|
48 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|