Upload tokenizer
Browse files- special_tokens_map.json +35 -5
- tokenizer_config.json +4 -0
special_tokens_map.json
CHANGED
@@ -1,7 +1,37 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
}
|
tokenizer_config.json
CHANGED
@@ -47,12 +47,16 @@
|
|
47 |
"do_lower_case": true,
|
48 |
"full_tokenizer_file": null,
|
49 |
"mask_token": "[MASK]",
|
|
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
51 |
"never_split": null,
|
52 |
"pad_token": "[PAD]",
|
53 |
"sep_token": "[SEP]",
|
|
|
54 |
"strip_accents": null,
|
55 |
"tokenize_chinese_chars": true,
|
56 |
"tokenizer_class": "MobileBertTokenizer",
|
|
|
|
|
57 |
"unk_token": "[UNK]"
|
58 |
}
|
|
|
47 |
"do_lower_case": true,
|
48 |
"full_tokenizer_file": null,
|
49 |
"mask_token": "[MASK]",
|
50 |
+
"max_length": 20,
|
51 |
"model_max_length": 1000000000000000019884624838656,
|
52 |
"never_split": null,
|
53 |
"pad_token": "[PAD]",
|
54 |
"sep_token": "[SEP]",
|
55 |
+
"stride": 0,
|
56 |
"strip_accents": null,
|
57 |
"tokenize_chinese_chars": true,
|
58 |
"tokenizer_class": "MobileBertTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
"unk_token": "[UNK]"
|
62 |
}
|